@inproceedings{UllrichBayerlHutzelmannetal.2025, author = {Ullrich, Henning and Bayerl, Dominik and Hutzelmann, Thomas and Hof, Hans-Joachim}, title = {Application of Quantum Key Distribution in Intelligent Transport Systems}, pages = {5}, booktitle = {Proceedings of the 2nd Cyber Security in CarS Workshop (CSCS'25)}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-1928-8}, doi = {https://doi.org/10.1145/3736130.3762692}, year = {2025}, abstract = {Quantum Key Distribution (QKD) enables two parties to generate a secret key, based on quantum physical properties. The secrecy of the exchanged key is guaranteed by these quantum physical properties, even against an attacker using a quantum computer. QKD therefore offers an Quantum Information Theoretically Secure (Q-ITS) alternative to Post Quantum Cryptography (PQC) schemes. This paper discusses advantages and challenges of deploying a QKD system in an Intelligent Transport System (ITS), by examining two exemplary use cases. Approaches to effectively implement QKD in these use cases are proposed, with a short discussion of advantages over the use of classical and PQC schemes.}, language = {en} } @inproceedings{MichlHofKatzenbeisser2025, author = {Michl, Marco and Hof, Hans-Joachim and Katzenbeisser, Stefan}, title = {From Access to Trust: Policy-Based Automotive Trust Management With XACML}, pages = {6}, booktitle = {Proceedings of the 2nd Cyber Security in CarS Workshop (CSCS'25)}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-1928-8}, doi = {https://doi.org/10.1145/3736130.3764511}, year = {2025}, abstract = {Trust is a fundamental requirement in vehicular systems, particularly in the context of autonomous and cooperative driving, where decisions often depend on data received from other vehicles or infrastructure. This paper presents a novel approach to integrating trust-based reasoning—specifically, decision-making based on subjective logic—into Attribute-Based Access Control (ABAC) systems, using the XACML policy language. We draw a parallel between trust management and access control, showing that trust assessments can be modeled as access decisions and expressed through standard access control policies. This integration allows for the reuse of mature ABAC infrastructure to represent and enforce trust-based decisions. Furthermore, we demonstrate how trust discounting mechanisms, which combine node-based and data-based trust, can be implemented within XACML policies. To evaluate this approach, we introduce a Rust-based XACML engine capable of interpreting trust-enhanced policies. Its integration in both inter- and intra-vehicle scenarios is discussed, assuming a modern zone-based architecture. Our results suggest that policy-based trust management can be efficiently implemented, enabling flexible and standardized trust reasoning in automotive environments.}, language = {en} } @inproceedings{LavesHutzelmannMayeretal.2025, author = {Laves, Claudius and Hutzelmann, Thomas and Mayer, Kevin and Hof, Hans-Joachim}, title = {Driving Down Premiums: A Security and Forensic Analysis of the DriveWell Insurance System}, pages = {9}, booktitle = {Proceedings of the 2nd Cyber Security in CarS Workshop (CSCS'25)}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-1928-8}, doi = {https://doi.org/10.1145/3736130.3762688}, year = {2025}, abstract = {Modern car insurance companies can dynamically adjust premiums with mobile sensor units that constantly record, analyze, and grade driving behavior. However, attackers can tamper with these systems to cheat the insurance company and reduce their premiums. We developed an attacker model for this threat in conjunction with a risk assessment using the ISO/SAE 21434 Risk Rating Methodology, a widely accepted standard for evaluating and managing risks in automotive systems. To support and showcase our model, we examined the static IT security of the mobile sensor unit DriveWell and its companion Android application HUK Mein Auto. In particular, we utilized digital forensic tools to analyze the stored data in the sensor's internal storage and the app's smartphone storage, with a focus on encryption mechanisms for locally stored data and internet communication. During this analysis, we spotted a critical vulnerability that enables attackers to manipulate their insurance scores and potentially reduce premiums by up to 30\%. Our model and real-world analysis provide a solid foundation for reducing the risk of such manipulation of insurance premiums.}, language = {en} } @unpublished{AubrevilleStathonikosDonovanetal.2023, author = {Aubreville, Marc and Stathonikos, Nikolas and Donovan, Taryn and Klopfleisch, Robert and Ganz, Jonathan and Ammeling, Jonas and Wilm, Frauke and Veta, Mitko and Jabari, Samir and Eckstein, Markus and Annuscheit, Jonas and Krumnow, Christian and Bozaba, Engin and Cayir, Sercan and Gu, Hongyan and Chen, Xiang and Jahanifar, Mostafa and Shephard, Adam and Kondo, Satoshi and Kasai, Satoshi and Kotte, Sujatha and Saipradeep, Vangala and Lafarge, Maxime W. and Koelzer, Viktor H. and Wang, Ziyue and Zhang, Yongbing and Yang, Sen and Wang, Xiyue and Breininger, Katharina and Bertram, Christof}, title = {Domain generalization across tumor types, laboratories, and species - Insights from the 2022 edition of the Mitosis Domain Generalization Challenge}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2309.15589}, year = {2023}, abstract = {Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert consensus and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an F1 score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, but with only minor changes in the order of participants in the ranking.}, language = {en} } @unpublished{HaghoferParlakBarteletal.2023, author = {Haghofer, Andreas and Parlak, Eda and Bartel, Alexander and Donovan, Taryn and Assenmacher, Charles-Antoine and Bolfa, Pompei and Dark, Michael and Fuchs-Baumgartinger, Andrea and Klang, Andrea and J{\"a}ger, Kathrin and Klopfleisch, Robert and Merz, Sophie and Richter, Barbara and Schulman, F. Yvonne and Ganz, Jonathan and Scharinger, Josef and Aubreville, Marc and Winkler, Stephan M. and Kiupel, Matti and Bertram, Christof}, title = {Nuclear Morphometry using a Deep Learning-based Algorithm has Prognostic Relevance for Canine Cutaneous Mast Cell Tumors}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2309.15031}, year = {2023}, abstract = {Variation in nuclear size and shape is an important criterion of malignancy for many tumor types; however, categorical estimates by pathologists have poor reproducibility. Measurements of nuclear characteristics (morphometry) can improve reproducibility, but manual methods are time consuming. In this study, we evaluated fully automated morphometry using a deep learning-based algorithm in 96 canine cutaneous mast cell tumors with information on patient survival. Algorithmic morphometry was compared with karyomegaly estimates by 11 pathologists, manual nuclear morphometry of 12 cells by 9 pathologists, and the mitotic count as a benchmark. The prognostic value of automated morphometry was high with an area under the ROC curve regarding the tumor-specific survival of 0.943 (95\% CI: 0.889 - 0.996) for the standard deviation (SD) of nuclear area, which was higher than manual morphometry of all pathologists combined (0.868, 95\% CI: 0.737 - 0.991) and the mitotic count (0.885, 95\% CI: 0.765 - 1.00). At the proposed thresholds, the hazard ratio for algorithmic morphometry (SD of nuclear area ≥9.0μm2) was 18.3 (95\% CI: 5.0 - 67.1), for manual morphometry (SD of nuclear area ≥10.9μm2) 9.0 (95\% CI: 6.0 - 13.4), for karyomegaly estimates 7.6 (95\% CI: 5.7 - 10.1), and for the mitotic count 30.5 (95\% CI: 7.8 - 118.0). Inter-rater reproducibility for karyomegaly estimates was fair (κ = 0.226) with highly variable sensitivity/specificity values for the individual pathologists. Reproducibility for manual morphometry (SD of nuclear area) was good (ICC = 0.654). This study supports the use of algorithmic morphometry as a prognostic test to overcome the limitations of estimates and manual measurements.}, language = {en} } @unpublished{GanzMarzahlAmmelingetal.2024, author = {Ganz, Jonathan and Marzahl, Christian and Ammeling, Jonas and Richter, Barbara and Puget, Chlo{\´e} and Denk, Daniela and Demeter, Elena A. and Tabaran, Flaviu A. and Wasinger, Gabriel and Lipnik, Karoline and Tecilla, Marco and Valentine, Matthew J. and Dark, Michael and Abele, Niklas and Bolfa, Pompei and Erber, Ramona and Klopfleisch, Robert and Merz, Sophie and Donovan, Taryn and Jabari, Samir and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {On the Value of PHH3 for Mitotic Figure Detection on H\&E-stained Images}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2406.19899}, year = {2024}, abstract = {The count of mitotic figures (MFs) observed in hematoxylin and eosin (H\&E)-stained slides is an important prognostic marker as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. Deep learning algorithms can standardize this task, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithm's performance. Unlike H\&E, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H\&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H\&E stain alone, the use of this ground truth could potentially introduce noise into the H\&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. We found that the annotators' object-level agreement increased when using PHH3-assisted labeling. Subsequently, MF detectors were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models' performance. Additionally, a novel dual-stain MF detector was developed to investigate the interpretation-shift of PHH3-assisted labels used in H\&E, which clearly outperformed single-stain detectors. However, the PHH3-assisted labels did not have a positive effect on solely H\&E-based models. The high performance of our dual-input detector reveals an information mismatch between the H\&E and PHH3-stained images as the cause of this effect.}, language = {en} } @unpublished{GanzAmmelingRosbachetal.2024, author = {Ganz, Jonathan and Ammeling, Jonas and Rosbach, Emely and Lausser, Ludwig and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2412.06365}, year = {2024}, abstract = {Foundation models (FMs), i.e., models trained on a vast amount of typically unlabeled data, have become popular and available recently for the domain of histopathology. The key idea is to extract semantically rich vectors from any input patch, allowing for the use of simple subsequent classification networks potentially reducing the required amounts of labeled data, and increasing domain robustness. In this work, we investigate to which degree this also holds for mitotic figure classification. Utilizing two popular public mitotic figure datasets, we compared linear probing of five publicly available FMs against models trained on ImageNet and a simple ResNet50 end-to-end-trained baseline. We found that the end-to-end-trained baseline outperformed all FM-based classifiers, regardless of the amount of data provided. Additionally, we did not observe the FM-based classifiers to be more robust against domain shifts, rendering both of the above assumptions incorrect.}, language = {en} } @unpublished{PugetGanzOstermaieretal.2024, author = {Puget, Chlo{\´e} and Ganz, Jonathan and Ostermaier, Julian and Konrad, Thomas and Parlak, Eda and Bertram, Christof and Kiupel, Matti and Breininger, Katharina and Aubreville, Marc and Klopfleisch, Robert}, title = {Deep Learning model predicts the c-Kit-11 mutational status of canine cutaneous mast cell tumors by HE stained histological slides}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2401.06169}, year = {2024}, abstract = {Numerous prognostic factors are currently assessed histopathologically in biopsies of canine mast cell tumors to evaluate clinical behavior. In addition, PCR analysis of the c-Kit exon 11 mutational status is often performed to evaluate the potential success of a tyrosine kinase inhibitor therapy. This project aimed at training deep learning models (DLMs) to identify the c-Kit-11 mutational status of MCTs solely based on morphology without additional molecular analysis. HE slides of 195 mutated and 173 non-mutated tumors were stained consecutively in two different laboratories and scanned with three different slide scanners. This resulted in six different datasets (stain-scanner variations) of whole slide images. DLMs were trained with single and mixed datasets and their performances was assessed under scanner and staining domain shifts. The DLMs correctly classified HE slides according to their c-Kit 11 mutation status in, on average, 87\% of cases for the best-suited stain-scanner variant. A relevant performance drop could be observed when the stain-scanner combination of the training and test dataset differed. Multi-variant datasets improved the average accuracy but did not reach the maximum accuracy of algorithms trained and tested on the same stain-scanner variant. In summary, DLM-assisted morphological examination of MCTs can predict c-Kit-exon 11 mutational status of MCTs with high accuracy. However, the recognition performance is impeded by a change of scanner or staining protocol. Larger data sets with higher numbers of scans originating from different laboratories and scanners may lead to more robust DLMs to identify c-Kit mutations in HE slides.}, language = {en} } @article{BertramAubrevilleDonovanetal.2021, author = {Bertram, Christof and Aubreville, Marc and Donovan, Taryn and Bartel, Alexander and Wilm, Frauke and Marzahl, Christian and Assenmacher, Charles-Antoine and Becker, Kathrin and Bennett, Mark and Corner, Sarah M. and Cossic, Brieuc and Denk, Daniela and Dettwiler, Martina and Garcia Gonzalez, Beatriz and Gurtner, Corinne and Haverkamp, Ann-Kathrin and Heier, Annabelle and Lehmbecker, Annika and Merz, Sophie and Noland, Erica L. and Plog, Stephanie and Schmidt, Anja and Sebastian, Franziska and Sledge, Dodd G. and Smedley, Rebecca C. and Tecilla, Marco and Thaiwong, Tuddow and Fuchs-Baumgartinger, Andrea and Meuten, Donald J. and Breininger, Katharina and Kiupel, Matti and Maier, Andreas and Klopfleisch, Robert}, title = {Computer-assisted mitotic count using a deep learning-based algorithm improves interobserver reproducibility and accuracy}, volume = {59}, journal = {Veterinary Pathology}, number = {2}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858211067478}, pages = {211 -- 226}, year = {2021}, abstract = {The mitotic count (MC) is an important histological parameter for prognostication of malignant neoplasms. However, it has inter- and intraobserver discrepancies due to difficulties in selecting the region of interest (MC-ROI) and in identifying or classifying mitotic figures (MFs). Recent progress in the field of artificial intelligence has allowed the development of high-performance algorithms that may improve standardization of the MC. As algorithmic predictions are not flawless, computer-assisted review by pathologists may ensure reliability. In the present study, we compared partial (MC-ROI preselection) and full (additional visualization of MF candidates and display of algorithmic confidence values) computer-assisted MC analysis to the routine (unaided) MC analysis by 23 pathologists for whole-slide images of 50 canine cutaneous mast cell tumors (ccMCTs). Algorithmic predictions aimed to assist pathologists in detecting mitotic hotspot locations, reducing omission of MFs, and improving classification against imposters. The interobserver consistency for the MC significantly increased with computer assistance (interobserver correlation coefficient, ICC = 0.92) compared to the unaided approach (ICC = 0.70). Classification into prognostic stratifications had a higher accuracy with computer assistance. The algorithmically preselected hotspot MC-ROIs had a consistently higher MCs than the manually selected MC-ROIs. Compared to a ground truth (developed with immunohistochemistry for phosphohistone H3), pathologist performance in detecting individual MF was augmented when using computer assistance (F1-score of 0.68 increased to 0.79) with a reduction in false negatives by 38\%. The results of this study demonstrate that computer assistance may lead to more reproducible and accurate MCs in ccMCTs.}, language = {en} } @unpublished{GanzMarzahlAmmelingetal.2024, author = {Ganz, Jonathan and Marzahl, Christian and Ammeling, Jonas and Rosbach, Emely and Richter, Barbara and Puget, Chlo{\´e} and Denk, Daniela and Demeter, Elena A. and Tabaran, Flaviu A. and Wasinger, Gabriel and Lipnik, Karoline and Tecilla, Marco and Valentine, Matthew J. and Dark, Michael and Abele, Niklas and Bolfa, Pompei and Erber, Ramona and Klopfleisch, Robert and Merz, Sophie and Donovan, Taryn and Jabari, Samir and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Information Mismatch in PHH3-Assisted Mitosis Annotation Leads to Interpretation Shifts in H\&E Slide Analysis}, titleParent = {Research Square}, publisher = {Research Square}, address = {Durham}, doi = {https://doi.org/10.21203/rs.3.rs-4900505/v1}, year = {2024}, abstract = {The count of mitotic figures (MFs) observed in hematoxylin and eosin (H\&E)-stained slides is an important prognostic marker, as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. In a computer-aided setting, deep learning algorithms can help to mitigate this, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithms' performance. Unlike H\&E, where identification of MFs is based mainly on morphological features, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H\&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H\&E staining alone, the use of this ground truth could potentially introduce an interpretation shift and even label noise into the H\&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. Subsequently, MF detectors, including a novel dual-stain detector, were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models' performance. We found that the annotators' object-level agreement significantly increased when using PHH3-assisted labeling (F1: 0.53 to 0.74). However, this enhancement in label consistency did not translate to improved performance for H\&E-based detectors, neither during the training phase nor the evaluation phase. Conversely, the dual-stain detector was able to benefit from the higher consistency. This reveals an information mismatch between the H\&E and PHH3-stained images as the cause of this effect, which renders PHH3-assisted annotations not well-aligned for use with H\&E-based detectors. Based on our findings, we propose an improved PHH3-assisted labeling procedure.}, language = {en} } @unpublished{AmmelingHeckerGanzetal.2023, author = {Ammeling, Jonas and Hecker, Moritz and Ganz, Jonathan and Donovan, Taryn and Klopfleisch, Robert and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Automated Volume Corrected Mitotic Index Calculation Through Annotation-Free Deep Learning using Immunohistochemistry as Reference Standard}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2311.08949}, year = {2023}, abstract = {The volume-corrected mitotic index (M/V-Index) was shown to provide prognostic value in invasive breast carcinomas. However, despite its prognostic significance, it is not established as the standard method for assessing aggressive biological behaviour, due to the high additional workload associated with determining the epithelial proportion. In this work, we show that using a deep learning pipeline solely trained with an annotation-free, immunohistochemistry-based approach, provides accurate estimations of epithelial segmentation in canine breast carcinomas. We compare our automatic framework with the manually annotated M/V-Index in a study with three board-certified pathologists. Our results indicate that the deep learning-based pipeline shows expert-level performance, while providing time efficiency and reproducibility.}, language = {en} } @unpublished{AmmelingSchmidtGanzetal.2022, author = {Ammeling, Jonas and Schmidt, Lars-Henning and Ganz, Jonathan and Niedermair, Tanja and Brochhausen-Delius, Christoph and Schulz, Christian and Breininger, Katharina and Aubreville, Marc}, title = {Attention-based Multiple Instance Learning for Survival Prediction on Lung Cancer Tissue Microarrays}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2212.07724}, year = {2022}, abstract = {Attention-based multiple instance learning (AMIL) algorithms have proven to be successful in utilizing gigapixel whole-slide images (WSIs) for a variety of different computational pathology tasks such as outcome prediction and cancer subtyping problems. We extended an AMIL approach to the task of survival prediction by utilizing the classical Cox partial likelihood as a loss function, converting the AMIL model into a nonlinear proportional hazards model. We applied the model to tissue microarray (TMA) slides of 330 lung cancer patients. The results show that AMIL approaches can handle very small amounts of tissue from a TMA and reach similar C-index performance compared to established survival prediction methods trained with highly discriminative clinical factors such as age, cancer grade, and cancer stage.}, language = {en} } @unpublished{AubrevillePanSievertetal.2023, author = {Aubreville, Marc and Pan, Zhaoya and Sievert, Matti and Ammeling, Jonas and Ganz, Jonathan and Oetter, Nicolai and Stelzle, Florian and Frenken, Ann-Kathrin and Breininger, Katharina and Goncalves, Miguel}, title = {Few Shot Learning for the Classification of Confocal Laser Endomicroscopy Images of Head and Neck Tumors}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2311.07216}, year = {2023}, abstract = {The surgical removal of head and neck tumors requires safe margins, which are usually confirmed intraoperatively by means of frozen sections. This method is, in itself, an oversampling procedure, which has a relatively low sensitivity compared to the definitive tissue analysis on paraffin-embedded sections. Confocal laser endomicroscopy (CLE) is an in-vivo imaging technique that has shown its potential in the live optical biopsy of tissue. An automated analysis of this notoriously difficult to interpret modality would help surgeons. However, the images of CLE show a wide variability of patterns, caused both by individual factors but also, and most strongly, by the anatomical structures of the imaged tissue, making it a challenging pattern recognition task. In this work, we evaluate four popular few shot learning (FSL) methods towards their capability of generalizing to unseen anatomical domains in CLE images. We evaluate this on images of sinunasal tumors (SNT) from five patients and on images of the vocal folds (VF) from 11 patients using a cross-validation scheme. The best respective approach reached a median accuracy of 79.6\% on the rather homogeneous VF dataset, but only of 61.6\% for the highly diverse SNT dataset. Our results indicate that FSL on CLE images is viable, but strongly affected by the number of patients, as well as the diversity of anatomical patterns.}, language = {en} } @unpublished{PerniasRampasAubreville2023, author = {Pernias, Pablo and Rampas, Dominic and Aubreville, Marc}, title = {W{\"u}rstchen: Efficient Pretraining of Text-to-Image Models}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2306.00637}, year = {2023}, abstract = {We introduce Wuerstchen, a novel technique for text-to-image synthesis that unites competitive performance with unprecedented cost-effectiveness and ease of training on constrained hardware. Building on recent advancements in machine learning, our approach, which utilizes latent diffusion strategies at strong latent image compression rates, significantly reduces the computational burden, typically associated with state-of-the-art models, while preserving, if not enhancing, the quality of generated images. Wuerstchen achieves notable speed improvements at inference time, thereby rendering real-time applications more viable. One of the key advantages of our method lies in its modest training requirements of only 9,200 GPU hours, slashing the usual costs significantly without compromising the end performance. In a comparison against the state-of-the-art, we found the approach to yield strong competitiveness. This paper opens the door to a new line of research that prioritizes both performance and computational accessibility, hence democratizing the use of sophisticated AI technologies. Through Wuerstchen, we demonstrate a compelling stride forward in the realm of text-to-image synthesis, offering an innovative path to explore in future research.}, language = {en} } @article{HaghoferFuchsBaumgartingerLipniketal.2023, author = {Haghofer, Andreas and Fuchs-Baumgartinger, Andrea and Lipnik, Karoline and Klopfleisch, Robert and Aubreville, Marc and Scharinger, Josef and Weissenb{\"o}ck, Herbert and Winkler, Stephan M. and Bertram, Christof}, title = {Histological classification of canine and feline lymphoma using a modular approach based on deep learning and advanced image processing}, volume = {13}, pages = {19436}, journal = {Scientific Reports}, publisher = {Springer Nature}, address = {London}, issn = {2045-2322}, doi = {https://doi.org/10.1038/s41598-023-46607-w}, year = {2023}, abstract = {AbstractHistopathological examination of tissue samples is essential for identifying tumor malignancy and the diagnosis of different types of tumor. In the case of lymphoma classification, nuclear size of the neoplastic lymphocytes is one of the key features to differentiate the different subtypes. Based on the combination of artificial intelligence and advanced image processing, we provide a workflow for the classification of lymphoma with regards to their nuclear size (small, intermediate, and large). As the baseline for our workflow testing, we use a Unet++ model trained on histological images of canine lymphoma with individually labeled nuclei. As an alternative to the Unet++, we also used a publicly available pre-trained and unmodified instance segmentation model called Stardist to demonstrate that our modular classification workflow can be combined with different types of segmentation models if they can provide proper nuclei segmentation. Subsequent to nuclear segmentation, we optimize algorithmic parameters for accurate classification of nuclear size using a newly derived reference size and final image classification based on a pathologists-derived ground truth. Our image classification module achieves a classification accuracy of up to 92\% on canine lymphoma data. Compared to the accuracy ranging from 66.67 to 84\% achieved using measurements provided by three individual pathologists, our algorithm provides a higher accuracy level and reproducible results. Our workflow also demonstrates a high transferability to feline lymphoma, as shown by its accuracy of up to 84.21\%, even though our workflow was not optimized for feline lymphoma images. By determining the nuclear size distribution in tumor areas, our workflow can assist pathologists in subtyping lymphoma based on the nuclei size and potentially improve reproducibility. Our proposed approach is modular and comprehensible, thus allowing adaptation for specific tasks and increasing the users' trust in computer-assisted image classification.}, language = {en} } @article{HirlingTasnadiCaicedoetal.2023, author = {Hirling, Dominik and Tasnadi, Ervin and Caicedo, Juan and Caroprese, Maria V. and Sj{\"o}gren, Rickard and Aubreville, Marc and Koos, Krisztian and Horvath, Peter}, title = {Segmentation metric misinterpretations in bioimage analysis}, volume = {21}, journal = {Nature Methods}, number = {2}, publisher = {Springer Nature}, address = {Berlin}, issn = {1548-7091}, doi = {https://doi.org/10.1038/s41592-023-01942-8}, pages = {213 -- 216}, year = {2023}, abstract = {Quantitative evaluation of image segmentation algorithms is crucial in the field of bioimage analysis. The most common assessment scores, however, are often misinterpreted and multiple definitions coexist with the same name. Here we present the ambiguities of evaluation metrics for segmentation algorithms and show how these misinterpretations can alter leaderboards of influential competitions. We also propose guidelines for how the currently existing problems could be tackled.}, language = {en} } @article{SievertMantsopoulosMuelleretal.2022, author = {Sievert, Matti and Mantsopoulos, Konstantinos and M{\"u}ller, Sarina K. and Eckstein, Markus and Rupp, Robin and Aubreville, Marc and Stelzle, Florian and Oetter, Nicolai and Maier, Andreas and Iro, Heinrich and Goncalves, Miguel}, title = {Systematic interpretation of confocal laser endomicroscopy: larynx and pharynx confocal imaging score}, volume = {42}, journal = {Acta otorhinolaryngologica italica}, number = {1}, publisher = {Pacini}, address = {Pisa}, issn = {1827-675X}, doi = {https://doi.org/10.14639/0392-100X-N1643}, pages = {26 -- 33}, year = {2022}, abstract = {Objective. Development and validation of a confocal laser endomicroscopy (CLE) classification score for the larynx and pharynx. Methods. Thirteen patients (154 video sequences, 9240 images) with laryngeal or pharyngeal SCC were included in this prospective study between October 2020 and February 2021. Each CLE sequence was correlated with the gold standard of histopathological examination. Based on a dataset of 94 video sequences (5640 images), a scoring system was developed. In the remaining 60 sequences (3600 images), the score was validated by four CLE experts and four head and neck surgeons who were not familiar with CLE. Results. Tissue homogeneity, cell size, borders and clusters, capillary loops and the nucleus/ cytoplasm ratio were defined as the scoring criteria. Using this score, the CLE experts obtained an accuracy, sensitivity, and specificity of 90.8\%, 95.1\%, and 86.4\%, respectively, and the CLE non-experts of 86.2\%, 86.4\%, and 86.1\%. Interobserver agreement Fleiss' kappa was 0.8 and 0.6, respectively. Conclusions. CLE can be reliably evaluated based on defined and reproducible imaging features, which demonstrate a high diagnostic value. CLE can be easily integrated into the intraoperative setting and generate real-time, in-vivo microscopic images to demarcate malignant changes.}, language = {en} } @inproceedings{DecaroBogarinHeurichAppeletal.2025, author = {Decaro, Gianluca and Bogarin Heurich, Sofia and Appel, Patricia B. and Kul, Sergen and Riener, Andreas}, title = {Too Close for Comfort? The Impact of eVTOL-Overflights in Residential Areas on Non-Users' Acceptance}, booktitle = {MuC´25: Proceedings of the 2025 Conference on Mensch und Computer}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-1582-2}, doi = {https://doi.org/10.1145/3743049.3748548}, pages = {744 -- 748}, year = {2025}, abstract = {Urban Air Mobility (UAM) has the potential to revolutionize commuting by allowing passengers to travel quickly and efficiently within and between cities and airports. However, this innovation also raises concerns for residents on the ground, who are expected to tolerate frequent eVTOL overflights above their homes - an issue that this paper seeks to address. To investigate acceptance of eVTOLs from the perspective of residents on the ground being overflown at 1000 ft, 1500 ft, and 2000 ft, a virtual reality study was conducted. Results showed significant differences in emotions, the feeling of being disturbed by the noise, the spatial proximity, and the presence of the eVTOL in lower altitudes. Additionally, privacy concerns were expressed. The findings help the scientific community and regulators in developing guidelines for operating eVTOLs in residential areas in an acceptable manner for non-passengers.}, language = {en} } @inproceedings{RollwagenHornSchmidtneretal.2025, author = {Rollwagen, Alice and Horn, Alexander and Schmidtner, Stefanie and Riener, Andreas}, title = {Communicating Uncertainty in Arrival Time Predictions for Public Transport: A Comparison of Point and Interval Forecasts}, booktitle = {MuC´25: Proceedings of the 2025 Conference on Mensch und Computer}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-1582-2}, doi = {https://doi.org/10.1145/3743049.3748542}, pages = {515 -- 519}, year = {2025}, abstract = {In public transport, arrival times are typically communicated as point forecasts, aiming to present precise estimates. However, current prediction models are unable to provide such precise and reliable estimates due to unpredictable events. This results in arrival times on passenger information systems appearing inaccurate due to the lack of communicated uncertainty. We therefore investigated interval forecasts as an alternative in an online study, aiming to better communicate uncertainty in arrival times. Our findings indicate that interval forecasts improve the communication of uncertainty. Further, user satisfaction was driven primarily by waiting time, and this relationship was moderated by the forecast concept. Point forecasts were only well received when the bus arrived as predicted, otherwise users preferred the broader interval forecasts. Participants valued accuracy over precision when judging arrival times.}, language = {en} } @inproceedings{GeierHeinl2025, author = {Geier, Johannes and Heinl, Patrizia}, title = {Towards a Metric to Assess Neural Network Resilience Against Adversarial Samples}, booktitle = {Availability, Reliability and Security: ARES 2025 EU Projects Symposium Workshops, Ghent, Belgium, August 11-14, 2025, Proceedings, Part I}, editor = {Skopik, Florian and Naessens, Vincent and De Sutter, Bjorn}, publisher = {Springer}, address = {Cham}, isbn = {978-3-032-00642-4}, doi = {https://doi.org/10.1007/978-3-032-00642-4_16}, pages = {272 -- 290}, year = {2025}, abstract = {Neural networks are vulnerable to adversarial attacks. Existing robustness evaluation methods have notable limitations, which makes robustness assessment challenging. This work explores robustness evaluation techniques and identifies key factors, including distance metrics, loss functions, attack generation algorithms, attacker models, specificity, and computational resources. Building on those factors, a novel robustness metric for classification tasks is proposed. Our metric accounts for both, targeted and untargeted attacks across three attacker models, while incorporating accuracy and loss into a weighted aggregation. The scoring includes robustness-versus-perturbation and loss-versus-perturbation curves. Our robustness metric offers a more reliable evaluation and deeper insights into model vulnerability compared to previous approaches.}, language = {en} } @article{AubrevilleStathonikosDonovanetal.2024, author = {Aubreville, Marc and Stathonikos, Nikolas and Donovan, Taryn and Klopfleisch, Robert and Ammeling, Jonas and Ganz, Jonathan and Wilm, Frauke and Veta, Mitko and Jabari, Samir and Eckstein, Markus and Annuscheit, Jonas and Krumnow, Christian and Bozaba, Engin and Cayir, Sercan and Gu, Hongyan and Chen, Xiang and Jahanifar, Mostafa and Shephard, Adam and Kondo, Satoshi and Kasai, Satoshi and Kotte, Sujatha and Saipradeep, Vangala and Lafarge, Maxime W. and Koelzer, Viktor H. and Wang, Ziyue and Zhang, Yongbing and Yang, Sen and Wang, Xiyue and Breininger, Katharina and Bertram, Christof}, title = {Domain generalization across tumor types, laboratories, and species — Insights from the 2022 edition of the Mitosis Domain Generalization Challenge}, volume = {2024}, pages = {103155}, journal = {Medical Image Analysis}, number = {94}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1361-8423}, doi = {https://doi.org/10.1016/j.media.2024.103155}, year = {2024}, abstract = {Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert majority vote and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, with only minor changes in the order of participants in the ranking.}, language = {en} } @article{GanzMarzahlAmmelingetal.2024, author = {Ganz, Jonathan and Marzahl, Christian and Ammeling, Jonas and Rosbach, Emely and Richter, Barbara and Puget, Chlo{\´e} and Denk, Daniela and Demeter, Elena A. and Tabaran, Flaviu A. and Wasinger, Gabriel and Lipnik, Karoline and Tecilla, Marco and Valentine, Matthew J. and Dark, Michael and Abele, Niklas and Bolfa, Pompei and Erber, Ramona and Klopfleisch, Robert and Merz, Sophie and Donovan, Taryn and Jabari, Samir and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Information mismatch in PHH3-assisted mitosis annotation leads to interpretation shifts in H\&E slide analysis}, volume = {14}, pages = {26273}, journal = {Scientific Reports}, number = {1}, publisher = {Springer Nature}, address = {London}, issn = {2045-2322}, doi = {https://doi.org/10.1038/s41598-024-77244-6}, year = {2024}, abstract = {The count of mitotic figures (MFs) observed in hematoxylin and eosin (H\&E)-stained slides is an important prognostic marker, as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. In a computer-aided setting, deep learning algorithms can help to mitigate this, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithms' performance. Unlike H\&E, where identification of MFs is based mainly on morphological features, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H\&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H\&E staining alone, the use of this ground truth could potentially introduce an interpretation shift and even label noise into the H\&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. Subsequently, MF detectors, including a novel dual-stain detector, were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models' performance. We found that the annotators' object-level agreement significantly increased when using PHH3-assisted labeling (F1: 0.53 to 0.74). However, this enhancement in label consistency did not translate to improved performance for H\&E-based detectors, neither during the training phase nor the evaluation phase. Conversely, the dual-stain detector was able to benefit from the higher consistency. This reveals an information mismatch between the H\&E and PHH3-stained images as the cause of this effect, which renders PHH3-assisted annotations not well-aligned for use with H\&E-based detectors. Based on our findings, we propose an improved PHH3-assisted labeling procedure.}, language = {en} } @article{HaghoferParlakBarteletal.2024, author = {Haghofer, Andreas and Parlak, Eda and Bartel, Alexander and Donovan, Taryn and Assenmacher, Charles-Antoine and Bolfa, Pompei and Dark, Michael and Fuchs-Baumgartinger, Andrea and Klang, Andrea and J{\"a}ger, Kathrin and Klopfleisch, Robert and Merz, Sophie and Richter, Barbara and Schulman, F. Yvonne and Janout, Hannah and Ganz, Jonathan and Scharinger, Josef and Aubreville, Marc and Winkler, Stephan M. and Kiupel, Matti and Bertram, Christof}, title = {Nuclear pleomorphism in canine cutaneous mast cell tumors: Comparison of reproducibility and prognostic relevance between estimates, manual morphometry, and algorithmic morphometry}, volume = {62}, journal = {Veterinary Pathology}, number = {2}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858241295399}, pages = {161 -- 177}, year = {2024}, abstract = {Variation in nuclear size and shape is an important criterion of malignancy for many tumor types; however, categorical estimates by pathologists have poor reproducibility. Measurements of nuclear characteristics can improve reproducibility, but current manual methods are time-consuming. The aim of this study was to explore the limitations of estimates and develop alternative morphometric solutions for canine cutaneous mast cell tumors (ccMCTs). We assessed the following nuclear evaluation methods for accuracy, reproducibility, and prognostic utility: (1) anisokaryosis estimates by 11 pathologists; (2) gold standard manual morphometry of at least 100 nuclei; (3) practicable manual morphometry with stratified sampling of 12 nuclei by 9 pathologists; and (4) automated morphometry using deep learning-based segmentation. The study included 96 ccMCTs with available outcome information. Inter-rater reproducibility of anisokaryosis estimates was low (k = 0.226), whereas it was good (intraclass correlation = 0.654) for practicable morphometry of the standard deviation (SD) of nuclear size. As compared with gold standard manual morphometry (area under the ROC curve [AUC] = 0.839, 95\% confidence interval [CI] = 0.701-0.977), the prognostic value (tumor-specific survival) of SDs of nuclear area for practicable manual morphometry and automated morphometry were high with an AUC of 0.868 (95\% CI = 0.737-0.991) and 0.943 (95\% CI = 0.889-0.996), respectively. This study supports the use of manual morphometry with stratified sampling of 12 nuclei and algorithmic morphometry to overcome the poor reproducibility of estimates. Further studies are needed to validate our findings, determine inter-algorithmic reproducibility and algorithmic robustness, and explore tumor heterogeneity of nuclear features in entire tumor sections.}, language = {en} } @article{StathonikosAubrevilledeVriesetal.2024, author = {Stathonikos, Nikolas and Aubreville, Marc and de Vries, Sjoerd and Wilm, Frauke and Bertram, Christof and Veta, Mitko and van Diest, Paul J}, title = {Breast cancer survival prediction using an automated mitosis detection pipeline}, volume = {10}, pages = {e70008}, journal = {The Journal of Pathology: Clinical Research}, number = {6}, publisher = {Wiley}, address = {Chichester}, issn = {2056-4538}, doi = {https://doi.org/10.1002/2056-4538.70008}, year = {2024}, abstract = {AbstractMitotic count (MC) is the most common measure to assess tumor proliferation in breast cancer patients and is highly predictive of patient outcomes. It is, however, subject to inter- and intraobserver variation and reproducibility challenges that may hamper its clinical utility. In past studies, artificial intelligence (AI)-supported MC has been shown to correlate well with traditional MC on glass slides. Considering the potential of AI to improve reproducibility of MC between pathologists, we undertook the next validation step by evaluating the prognostic value of a fully automatic method to detect and count mitoses on whole slide images using a deep learning model. The model was developed in the context of the Mitosis Domain Generalization Challenge 2021 (MIDOG21) grand challenge and was expanded by a novel automatic area selector method to find the optimal mitotic hotspot and calculate the MC per 2 mm2. We employed this method on a breast cancer cohort with long-term follow-up from the University Medical Centre Utrecht (N = 912) and compared predictive values for overall survival of AI-based MC and light-microscopic MC, previously assessed during routine diagnostics. The MIDOG21 model was prognostically comparable to the original MC from the pathology report in uni- and multivariate survival analysis. In conclusion, a fully automated MC AI algorithm was validated in a large cohort of breast cancer with regard to retained prognostic value compared with traditional light-microscopic MC.}, language = {en} } @article{GlahnHaghoferDonovanetal.2024, author = {Glahn, Imaine and Haghofer, Andreas and Donovan, Taryn and Degasperi, Brigitte and Bartel, Alexander and Kreilmeier-Berger, Theresa and Hyndman, Philip S. and Janout, Hannah and Assenmacher, Charles-Antoine and Bartenschlager, Florian and Bolfa, Pompei and Dark, Michael and Klang, Andrea and Klopfleisch, Robert and Merz, Sophie and Richter, Barbara and Schulman, F. Yvonne and Ganz, Jonathan and Scharinger, Josef and Aubreville, Marc and Winkler, Stephan M. and Bertram, Christof}, title = {Automated Nuclear Morphometry: A Deep Learning Approach for Prognostication in Canine Pulmonary Carcinoma to Enhance Reproducibility}, volume = {11}, pages = {278}, journal = {Veterinary Sciences}, number = {6}, publisher = {MDPI}, address = {Basel}, issn = {2306-7381}, doi = {https://doi.org/10.3390/vetsci11060278}, year = {2024}, abstract = {The integration of deep learning-based tools into diagnostic workflows is increasingly prevalent due to their efficiency and reproducibility in various settings. We investigated the utility of automated nuclear morphometry for assessing nuclear pleomorphism (NP), a criterion of malignancy in the current grading system in canine pulmonary carcinoma (cPC), and its prognostic implications. We developed a deep learning-based algorithm for evaluating NP (variation in size, i.e., anisokaryosis and/or shape) using a segmentation model. Its performance was evaluated on 46 cPC cases with comprehensive follow-up data regarding its accuracy in nuclear segmentation and its prognostic ability. Its assessment of NP was compared to manual morphometry and established prognostic tests (pathologists' NP estimates (n = 11), mitotic count, histological grading, and TNM-stage). The standard deviation (SD) of the nuclear area, indicative of anisokaryosis, exhibited good discriminatory ability for tumor-specific survival, with an area under the curve (AUC) of 0.80 and a hazard ratio (HR) of 3.38. The algorithm achieved values comparable to manual morphometry. In contrast, the pathologists' estimates of anisokaryosis resulted in HR values ranging from 0.86 to 34.8, with slight inter-observer reproducibility (k = 0.204). Other conventional tests had no significant prognostic value in our study cohort. Fully automated morphometry promises a time-efficient and reproducible assessment of NP with a high prognostic value. Further refinement of the algorithm, particularly to address undersegmentation, and application to a larger study population are required.}, language = {en} } @article{GanzAmmelingJabarietal.2024, author = {Ganz, Jonathan and Ammeling, Jonas and Jabari, Samir and Breininger, Katharina and Aubreville, Marc}, title = {Re-identification from histopathology images}, volume = {2025}, pages = {103335}, journal = {Medical Image Analysis}, number = {99}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1361-8423}, doi = {https://doi.org/10.1016/j.media.2024.103335}, year = {2024}, abstract = {In numerous studies, deep learning algorithms have proven their potential for the analysis of histopathology images, for example, for revealing the subtypes of tumors or the primary origin of metastases. These models require large datasets for training, which must be anonymized to prevent possible patient identity leaks. This study demonstrates that even relatively simple deep learning algorithms can re-identify patients in large histopathology datasets with substantial accuracy. In addition, we compared a comprehensive set of state-of-the-art whole slide image classifiers and feature extractors for the given task. We evaluated our algorithms on two TCIA datasets including lung squamous cell carcinoma (LSCC) and lung adenocarcinoma (LUAD). We also demonstrate the algorithm's performance on an in-house dataset of meningioma tissue. We predicted the source patient of a slide with 𝐹1 scores of up to 80.1\% and 77.19\% on the LSCC and LUAD datasets, respectively, and with 77.09\% on our meningioma dataset. Based on our findings, we formulated a risk assessment scheme to estimate the risk to the patient's privacy prior to publication.}, language = {en} } @article{WilmIhlingMehesetal.2023, author = {Wilm, Frauke and Ihling, Christian and M{\´e}hes, G{\´a}bor and Terracciano, Luigi and Puget, Chlo{\´e} and Klopfleisch, Robert and Sch{\"u}ffler, Peter and Aubreville, Marc and Maier, Andreas and Mrowiec, Thomas and Breininger, Katharina}, title = {Pan-tumor T-lymphocyte detection using deep neural networks: Recommendations for transfer learning in immunohistochemistry}, volume = {2023}, pages = {100301}, journal = {Journal of Pathology Informatics}, number = {14}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2153-3539}, doi = {https://doi.org/10.1016/j.jpi.2023.100301}, year = {2023}, abstract = {The success of immuno-oncology treatments promises long-term cancer remission for an increasing number of patients. The response to checkpoint inhibitor drugs has shown a correlation with the presence of immune cells in the tumor and tumor microenvironment. An in-depth understanding of the spatial localization of immune cells is therefore critical for understanding the tumor's immune landscape and predicting drug response. Computer-aided systems are well suited for efficiently quantifying immune cells in their spatial context. Conventional image analysis approaches are often based on color features and therefore require a high level of manual interaction. More robust image analysis methods based on deep learning are expected to decrease this reliance on human interaction and improve the reproducibility of immune cell scoring. However, these methods require sufficient training data and previous work has reported low robustness of these algorithms when they are tested on out-of-distribution data from different pathology labs or samples from different organs. In this work, we used a new image analysis pipeline to explicitly evaluate the robustness of marker-labeled lymphocyte quantification algorithms depending on the number of training samples before and after being transferred to a new tumor indication. For these experiments, we adapted the RetinaNet architecture for the task of T-lymphocyte detection and employed transfer learning to bridge the domain gap between tumor indications and reduce the annotation costs for unseen domains. On our test set, we achieved human-level performance for almost all tumor indications with an average precision of 0.74 in-domain and 0.72-0.74 cross-domain. From our results, we derive recommendations for model development regarding annotation extent, training sample selection, and label extraction for the development of robust algorithms for immune cell scoring. By extending the task of marker-labeled lymphocyte quantification to a multi-class detection task, the pre-requisite for subsequent analyses, e.g., distinguishing lymphocytes in the tumor stroma from tumor-infiltrating lymphocytes, is met.}, language = {en} } @article{FragosoGarciaWilmBertrametal.2023, author = {Fragoso-Garcia, Marco and Wilm, Frauke and Bertram, Christof and Merz, Sophie and Schmidt, Anja and Donovan, Taryn and Fuchs-Baumgartinger, Andrea and Bartel, Alexander and Marzahl, Christian and Diehl, Laura and Puget, Chloe and Maier, Andreas and Aubreville, Marc and Breininger, Katharina and Klopfleisch, Robert}, title = {Automated diagnosis of 7 canine skin tumors using machine learning on H\&E-stained whole slide images}, volume = {60}, journal = {Veterinary Pathology}, number = {6}, publisher = {Sage}, address = {London}, issn = {0300-9858}, doi = {https://doi.org/10.1177/03009858231189205}, pages = {865 -- 875}, year = {2023}, abstract = {Microscopic evaluation of hematoxylin and eosin-stained slides is still the diagnostic gold standard for a variety of diseases, including neoplasms. Nevertheless, intra- and interrater variability are well documented among pathologists. So far, computer assistance via automated image analysis has shown potential to support pathologists in improving accuracy and reproducibility of quantitative tasks. In this proof of principle study, we describe a machine-learning-based algorithm for the automated diagnosis of 7 of the most common canine skin tumors: trichoblastoma, squamous cell carcinoma, peripheral nerve sheath tumor, melanoma, histiocytoma, mast cell tumor, and plasmacytoma. We selected, digitized, and annotated 350 hematoxylin and eosin-stained slides (50 per tumor type) to create a database divided into training, n = 245 whole-slide images (WSIs), validation ( n = 35 WSIs), and test sets ( n = 70 WSIs). Full annotations included the 7 tumor classes and 6 normal skin structures. The data set was used to train a convolutional neural network (CNN) for the automatic segmentation of tumor and nontumor classes. Subsequently, the detected tumor regions were classified patch-wise into 1 of the 7 tumor classes. A majority of patches-approach led to a tumor classification accuracy of the network on the slide-level of 95\% (133/140 WSIs), with a patch-level precision of 85\%. The same 140 WSIs were provided to 6 experienced pathologists for diagnosis, who achieved a similar slide-level accuracy of 98\% (137/140 correct majority votes). Our results highlight the feasibility of artificial intelligence-based methods as a support tool in diagnostic oncologic pathology with future applications in other species and tumor types.}, language = {en} } @article{KruegelAmmelingAubrevilleetal.2024, author = {Kr{\"u}gel, Sebastian and Ammeling, Jonas and Aubreville, Marc and Fritz, Alexis and Kießig, Angelika and Uhl, Matthias}, title = {Perceived responsibility in AI-supported medicine}, volume = {40}, journal = {AI \& Society: Journal of Knowledge, Culture and Communication}, publisher = {Springer}, address = {London}, issn = {1435-5655}, doi = {https://doi.org/10.1007/s00146-024-01972-6}, pages = {1485 -- 1495}, year = {2024}, abstract = {In a representative vignette study in Germany with 1,653 respondents, we investigated laypeople's attribution of moral responsibility in collaborative medical diagnosis. Specifically, we compare people's judgments in a setting in which physicians are supported by an AI-based recommender system to a setting in which they are supported by a human colleague. It turns out that people tend to attribute moral responsibility to the artificial agent, although this is traditionally considered a category mistake in normative ethics. This tendency is stronger when people believe that AI may become conscious at some point. In consequence, less responsibility is attributed to human agents in settings with hybrid diagnostic teams than in settings with human-only diagnostic teams. Our findings may have implications for behavior exhibited in contexts of collaborative medical decision making with AI-based as opposed to human recommenders because less responsibility is attributed to agents who have the mental capacity to care about outcomes.}, language = {en} } @article{SievertAubrevilleGostianetal.2022, author = {Sievert, Matti and Aubreville, Marc and Gostian, Antoniu-Oreste and Mantsopoulos, Konstantinos and Koch, Michael and M{\"u}ller, Sarina K. and Eckstein, Markus and Rupp, Robin and Stelzle, Florian and Oetter, Nicolai and Maier, Andreas and Iro, Heinrich and Goncalves, Miguel}, title = {Validity of tissue homogeneity in confocal laser endomicroscopy on the diagnosis of laryngeal and hypopharyngeal squamous cell carcinoma}, volume = {279}, journal = {European Archives of Oto-Rhino-Laryngology and Head \& Neck}, number = {8}, publisher = {Springer Nature}, address = {Cham}, issn = {1434-4726}, doi = {https://doi.org/10.1007/s00405-022-07304-y}, pages = {4147 -- 4156}, year = {2022}, abstract = {Purpose Confocal laser endomicroscopy (CLE) allows imaging of the laryngeal mucosa in a thousand-fold magnification. This study analyzes differences in tissue homogeneity between healthy mucosa and squamous cell carcinoma (SCC) via CLE. Materials and methods We included five SCC patients with planned total laryngectomy in this study between October 2020 and February 2021. We captured CLE scans of the tumor and healthy mucosa. Analysis of image homogeneity to diagnose SCC was performed by measuring the signal intensity in four regions of interest (ROI) in each frame in a total of 60 sequences. Each sequence was assigned to the corresponding histological pattern, derived from hematoxylin and eosin staining. In addition, we recorded the subjective evaluation of seven investigators regarding tissue homogeneity. Results Out of 3600 images, 1620 (45\%) correlated with benign mucosa and 1980 (55\%) with SCC. ROIs of benign mucosa and SCC had a mean and standard deviation (SD) of signal intensity of, respectively, 232.1 ± 3.34 and 467.3 ± 9.72 (P < 0.001). The mean SD between the four different ROIs was 39.1 ± 1.03 for benign and 101.5 ± 2.6 for SCC frames (P < 0.001). In addition, homogeneity yielded a sensitivity and specificity of 81.8\% and 86.2\%, respectively, regarding the investigator-dependent analysis. Conclusions SCC shows a significant tissue inhomogeneity in comparison to the healthy epithelium. The results support this feature's importance in identifying malignant mucosa areas during CLE examination. However, the examiner-dependent evaluation emphasizes that homogeneity is a sub-criterion that must be considered in a broad context.}, language = {en} } @article{SievertMantsopoulosMuelleretal.2021, author = {Sievert, Matti and Mantsopoulos, Konstantinos and M{\"u}ller, Sarina K. and Rupp, Robin and Eckstein, Markus and Stelzle, Florian and Oetter, Nicolai and Maier, Andreas and Aubreville, Marc and Iro, Heinrich and Goncalves, Miguel}, title = {Validation of a classification and scoring system for the diagnosis of laryngeal and pharyngeal squamous cell carcinomas by confocal laser endomicroscopy}, volume = {2022}, journal = {Brazilian Journal of Otorhinolaryngology}, number = {88, S4}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1808-8694}, doi = {https://doi.org/10.1016/j.bjorl.2021.06.002}, pages = {26 -- 32}, year = {2021}, abstract = {Introduction Confocal laser endomicroscopy is an optical imaging technique that allows in vivo, real-time, microscope-like images of the upper aerodigestive tract's mucosa. The assessment of morphological tissue characteristics for the correct differentiation between healthy and malignant suspected mucosa requires strict evaluation criteria. Objective This study aims to validate an eight-point score for the correct assessment of malignancy. Methods We performed confocal laser endomicroscopy between March and October 2020 in 13 patients. 197 sequences (11.820 images) originated from the marginal area of pharyngeal and laryngeal carcinomas. Specimens were taken at corresponding locations and analyzed in H\&E staining as a standard of reference. A total of six examiners evaluated the sequences based on a scoring system; they were blinded to the histopathological examination. The primary endpoints are sensitivity, specificity, and accuracy. Secondary endpoints are interrater reliability and receiver operator characteristics. Results Healthy mucosa showed epithelium with uniform size and shape with distinct cytoplasmic membranes and regular vessel architecture. Confocal laser endomicroscopy of malignant cells demonstrated a disorganized arrangement of variable cellular morphology. We calculated an accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 83.2\%, 81.3\%, 85.5\%, 86.7\%, and 79.7\%, respectively, with a κ-value of 0.64, and an area under the curve of 0.86. Conclusion The results confirm that this scoring system is applicable in the laryngeal and pharyngeal mucosa to classify benign and malignant tissue. A scoring system based on defined and reproducible characteristics can help translate this experimental method to broad clinical practice in head and neck diagnosis.}, language = {en} } @article{SievertEcksteinMantsopoulosetal.2021, author = {Sievert, Matti and Eckstein, Markus and Mantsopoulos, Konstantinos and M{\"u}ller, Sarina K. and Stelzle, Florian and Aubreville, Marc and Oetter, Nicolai and Maier, Andreas and Iro, Heinrich and Goncalves, Miguel}, title = {Impact of intraepithelial capillary loops and atypical vessels in confocal laser endomicroscopy for the diagnosis of laryngeal and hypopharyngeal squamous cell carcinoma}, volume = {279}, journal = {European Archives of Oto-Rhino-Laryngology and Head \& Neck}, number = {4}, publisher = {Springer Nature}, address = {Cham}, issn = {1434-4726}, doi = {https://doi.org/10.1007/s00405-021-06954-8}, pages = {2029 -- 2037}, year = {2021}, abstract = {Purpose Confocal laser endomicroscopy (CLE) allows surface imaging of the laryngeal and pharyngeal mucosa in vivo at a thousand-fold magnification. This study aims to compare irregular blood vessels and intraepithelial capillary loops in healthy mucosa and squamous cell carcinoma (SCC) via CLE. Materials and methods We included ten patients with confirmed SCC and planned total laryngectomy in this study between March 2020 and February 2021. CLE images of these patients were collected and compared with the corresponding histology in hematoxylin and eosin staining. We analyzed the characteristic endomicroscopic patterns of blood vessels and intraepithelial capillary loops for the diagnosis of SCC. Results In a total of 54 sequences, we identified 243 blood vessels which were analyzed regarding structure, diameter, and Fluorescein leakage, confirming that irregular, corkscrew-like vessels (24.4\% vs. 1.3\%; P < .001), dilated intraepithelial capillary loops (90.8\% vs. 28.7\%; P < .001), and increased capillary leakage (40.7\% vs. 2.5\%; P < .001), are significantly more frequently detected in SCC compared to the healthy epithelium. We defined a vessel diameter of 30 μm in capillary loops as a cut-off value, obtaining a sensitivity, specificity, PPV, and NPV and accuracy of 90.6\%, 71.3\%, 57.4\%, 94.7\%, and 77.1\%, respectively, for the detection of malignancy based solely on capillary architecture. Conclusion Capillaries within malignant lesions are fundamentally different from those in healthy mucosa regions. The capillary architecture is a significant feature aiding the identification of malignant mucosa areas during in-vivo, real-time CLE examination.}, language = {en} } @article{BertramMarzahlBarteletal.2022, author = {Bertram, Christof and Marzahl, Christian and Bartel, Alexander and Stayt, Jason and Bonsembiante, Federico and Beeler-Marfisi, Janet and Barton, Ann K. and Brocca, Ginevra and Gelain, Maria Elena and Gl{\"a}sel, Agnes C. and du Preez, Kelly and Weiler, Kristina and Weissenbacher-Lang, Christiane and Breininger, Katharina and Aubreville, Marc and Maier, Andreas and Klopfleisch, Robert and Hill, Jenny}, title = {Cytologic scoring of equine exercise-induced pulmonary hemorrhage: Performance of human experts and a deep learning-based algorithm}, volume = {60}, journal = {Veterinary Pathology}, number = {1}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858221137582}, pages = {75 -- 85}, year = {2022}, abstract = {Exercise-induced pulmonary hemorrhage (EIPH) is a relevant respiratory disease in sport horses, which can be diagnosed by examination of bronchoalveolar lavage fluid (BALF) cells using the total hemosiderin score (THS). The aim of this study was to evaluate the diagnostic accuracy and reproducibility of annotators and to validate a deep learning-based algorithm for the THS. Digitized cytological specimens stained for iron were prepared from 52 equine BALF samples. Ten annotators produced a THS for each slide according to published methods. The reference methods for comparing annotator's and algorithmic performance included a ground truth dataset, the mean annotators' THSs, and chemical iron measurements. Results of the study showed that annotators had marked interobserver variability of the THS, which was mostly due to a systematic error between annotators in grading the intracytoplasmatic hemosiderin content of individual macrophages. Regarding overall measurement error between the annotators, 87.7\% of the variance could be reduced by using standardized grades based on the ground truth. The algorithm was highly consistent with the ground truth in assigning hemosiderin grades. Compared with the ground truth THS, annotators had an accuracy of diagnosing EIPH (THS of < or ≥ 75) of 75.7\%, whereas, the algorithm had an accuracy of 92.3\% with no relevant differences in correlation with chemical iron measurements. The results show that deep learning-based algorithms are useful for improving reproducibility and routine applicability of the THS. For THS by experts, a diagnostic uncertainty interval of 40 to 110 is proposed. THSs within this interval have insufficient reproducibility regarding the EIPH diagnosis.}, language = {en} } @article{MarzahlAubrevilleBertrametal.2021, author = {Marzahl, Christian and Aubreville, Marc and Bertram, Christof and Maier, Jennifer and Bergler, Christian and Kr{\"o}ger, Christine and Voigt, J{\"o}rn and Breininger, Katharina and Klopfleisch, Robert and Maier, Andreas}, title = {EXACT: a collaboration toolset for algorithm-aided annotation of images with annotation version control}, volume = {11}, pages = {4343}, journal = {Scientific Reports}, publisher = {Springer Nature}, address = {London}, issn = {2045-2322}, doi = {https://doi.org/10.1038/s41598-021-83827-4}, year = {2021}, abstract = {In many research areas, scientific progress is accelerated by multidisciplinary access to image data and their interdisciplinary annotation. However, keeping track of these annotations to ensure a high-quality multi-purpose data set is a challenging and labour intensive task. We developed the open-source online platform EXACT (EXpert Algorithm Collaboration Tool) that enables the collaborative interdisciplinary analysis of images from different domains online and offline. EXACT supports multi-gigapixel medical whole slide images as well as image series with thousands of images. The software utilises a flexible plugin system that can be adapted to diverse applications such as counting mitotic figures with a screening mode, finding false annotations on a novel validation view, or using the latest deep learning image analysis technologies. This is combined with a version control system which makes it possible to keep track of changes in the data sets and, for example, to link the results of deep learning experiments to specific data set versions. EXACT is freely available and has already been successfully applied to a broad range of annotation tasks, including highly diverse applications like deep learning supported cytology scoring, interdisciplinary multi-centre whole slide image tumour annotation, and highly specialised whale sound spectroscopy clustering.}, language = {en} } @article{SievertStelzleAubrevilleetal.2021, author = {Sievert, Matti and Stelzle, Florian and Aubreville, Marc and M{\"u}ller, Sarina K. and Eckstein, Markus and Oetter, Nicolai and Maier, Andreas and Mantsopoulos, Konstantinos and Iro, Heinrich and Goncalves, Miguel}, title = {Intraoperative free margins assessment of oropharyngeal squamous cell carcinoma with confocal laser endomicroscopy: a pilot study}, volume = {278}, journal = {European Archives of Oto-Rhino-Laryngology and Head \& Neck}, number = {11}, publisher = {Springer Nature}, address = {Cham}, issn = {1434-4726}, doi = {https://doi.org/10.1007/s00405-021-06659-y}, pages = {4433 -- 4439}, year = {2021}, abstract = {Purpose This pilot study aimed to assess the feasibility of intraoperative assessment of safe margins with confocal laser endomicroscopy (CLE) during oropharyngeal squamous cell carcinoma (OPSCC) surgery. Methods We included five consecutive patients confirmed OPSCC and planned tumor resection in September and October 2020. Healthy appearing mucosa in the marginal zone, and the tumor margin, were examined with CLE and biopsy during tumor resection. A total of 12,809 CLE frames were correlated with the gold standard of hematoxylin and eosin staining. Three head and neck surgeons and one pathologist were asked to identify carcinoma in a sample of 169 representative images, blinded to the histological results. Results Healthy mucosa showed epithelium with uniform size and shape with distinct cytoplasmic membranes and regular vessel architecture. CLE optical biopsy of OPSCC demonstrated a disorganized arrangement of variable cellular morphology. We calculated an accuracy, sensitivity, specificity, PPV, and NPV of 86\%, 90\%, 79\%, 88\%, and 82\%, respectively, with inter-rater reliability and κ-value of 0.60. Conclusion CLE can be easily integrated into the intraoperative setting, generate real-time, in-vivo microscopic images of the oropharynx for evaluation and demarcation of cancer. It can eventually contribute to a less radical approach by enabling a more precise evaluation of the cancer margin.}, language = {en} } @article{KruegelUhlBalcombe2021, author = {Kr{\"u}gel, Sebastian and Uhl, Matthias and Balcombe, Bryn}, title = {Automated vehicles and the morality of post-collision behavior}, volume = {23}, journal = {Ethics and Information Technology}, number = {4}, publisher = {Springer}, address = {Dordrecht}, issn = {1572-8439}, doi = {https://doi.org/10.1007/s10676-021-09607-w}, pages = {691 -- 701}, year = {2021}, abstract = {We address the considerations of the European Commission Expert Group on the ethics of connected and automated vehicles regarding data provision in the event of collisions. While human drivers' appropriate post-collision behavior is clearly defined, regulations for automated driving do not provide for collision detection. We agree it is important to systematically incorporate citizens' intuitions into the discourse on the ethics of automated vehicles. Therefore, we investigate whether people expect automated vehicles to behave like humans after an accident, even if this behavior does not directly affect the consequences of the accident. We find that appropriate post-collision behavior substantially influences people's evaluation of the underlying crash scenario. Moreover, people clearly think that automated vehicles can and should record the accident, stop at the site, and call the police. They are even willing to pay for technological features that enable post-collision behavior. Our study might begin a research program on post-collision behavior, enriching the empirically informed study of automated driving ethics that so far exclusively focuses on pre-collision behavior.}, language = {en} } @inproceedings{RodriguezArozamenaMatutePerezetal.2024, author = {Rodr{\´i}guez-Arozamena, Mario and Matute, Jose and P{\´e}rez, Joshu{\´e} and Ozbay, Burcu and Tezcan, Deryanur and Begecarslan, Enes and Mutlukaya, Irem and Mayer, Kevin and Volkersdorfer, Tina and Hof, Hans-Joachim}, title = {TRA2024 Poster - A Fail-Safe Decision Architecture for CCAM Applications}, booktitle = {Proceedings of the Transport Research Arena (TRA2024) Conference}, publisher = {Zenodo}, address = {Genf}, doi = {https://doi.org/10.5281/zenodo.10995953}, year = {2024}, language = {en} } @unpublished{PagonisHartungWuetal.2024, author = {Pagonis, Panagiotis and Hartung, Kai and Wu, Di and Georges, Munir and Gr{\"o}ttrup, S{\"o}ren}, title = {Analysis of Knowledge Tracing performance on synthesised student data}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2401.16832}, year = {2024}, abstract = {Knowledge Tracing (KT) aims to predict the future performance of students by tracking the development of their knowledge states. Despite all the recent progress made in this field, the application of KT models in education systems is still restricted from the data perspectives: 1) limited access to real life data due to data protection concerns, 2) lack of diversity in public datasets, 3) noises in benchmark datasets such as duplicate records. To resolve these problems, we simulated student data with three statistical strategies based on public datasets and tested their performance on two KT baselines. While we observe only minor performance improvement with additional synthetic data, our work shows that using only synthetic data for training can lead to similar performance as real data.}, language = {en} } @inproceedings{HartungJaegerGroettrupetal.2022, author = {Hartung, Kai and J{\"a}ger, Gerhard and Gr{\"o}ttrup, S{\"o}ren and Georges, Munir}, title = {Typological Word Order Correlations with Logistic Brownian Motion}, pages = {2022.sigtyp-1.3}, booktitle = {Proceedings of the 4th Workshop on Computational Typology and Multilingual NLP (SIGTYP 2022)}, editor = {Vylomova, Ekaterina and Ponti, Edoardo and Cotterell, Ryan}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg}, isbn = {978-1-955917-93-3}, url = {https://aclanthology.org/2022.sigtyp-1.3}, pages = {22 -- 26}, year = {2022}, abstract = {In this study we address the question to what extent syntactic word-order traits of different languages have evolved under correlation and whether such dependencies can be found universally across all languages or restricted to specific language families.To do so, we use logistic Brownian Motion under a Bayesian framework to model the trait evolution for 768 languages from 34 language families. We test for trait correlations both in single families and universally over all families. Separate models reveal no universal correlation patterns and Bayes Factor analysis of models over all covered families also strongly indicate lineage specific correlation patters instead of universal dependencies.}, language = {en} } @inproceedings{MangerAlbrechtRiener2024, author = {Manger, Carina and Albrecht, Kathrin and Riener, Andreas}, title = {Explanation Needs in Automated Driving: Insights from German Driving Education and Vehicle Acquisition}, booktitle = {MuC'24: Proceedings of the 2024 Conference on Mensch und Computer}, editor = {Maedche, Alexander and Beigl, Michael and Gerling, Kathrin and Mayer, Sven}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-0998-2}, doi = {https://doi.org/10.1145/3670653.3670679}, pages = {288 -- 298}, year = {2024}, abstract = {As driving assistance driving systems become increasingly advanced, a correct understanding of the functionality of these systems is crucial for safe use. In this work we explored drivers' explanation needs and current explanation methods from an important but underlooked perspective: driver training and vehicle acquisition. In a two-step approach, we conducted expert interviews with n = 7 driving instructors and vehicle salespeople in Germany and validated these results with an online survey of n = 105. Our results show that Driver Assistance Systems (DASs) and Advanced Driver Assistance Systems (ADASs), are currently covered in both driver training and vehicle acquisition but to a varying extent and in a very application-oriented manner. A drivers' tendency for preferring comparative explanations that build upon knowledge about similar systems was found. Based on the combined results, we emphasize the need for mandatory and standardized explanation methods to ensure a safe transition to automated driving.}, language = {en} } @inproceedings{EscherPeintnerRiener2024, author = {Escher, Bengt and Peintner, Jakob and Riener, Andreas}, title = {The Significance of the Bystander Effect on Personal Responsibility in Critical Situations in Shared Automated Vehicles}, booktitle = {16th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, September 22-25, 2024, Stanford, USA, Main Conference Proceedings}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-0510-6}, doi = {https://doi.org/10.1145/3640792.3675704}, pages = {384 -- 394}, year = {2024}, abstract = {Shared Automated Vehicles (SAVs) present a promising solution for future urban mobility. However, SAVs will reach the limits of their capabilities in some edge cases. Similar to personal AVs, passengers in SAVs might be utilized for this purpose, thus, methods for interaction between passengers and the automation or a teleoperator need to be explored. This study investigates whether the presence of other passengers leads to more passive behavior in critical situations (bystander effect). The results did not show significant differences in the participants' behavior depending on whether the ride was experienced alone or with other passengers. However, the qualitative data indicate that the presence of other passengers can trigger psychological processes that promote a bystander effect. The findings emphasize the importance of considering group effects in the context of SAVs. By understanding these dynamics, we aim to help design SAVs to promote safer and more inclusive future transport systems.}, language = {en} } @unpublished{OkumusRamicKugele2025, author = {Okumus, Fazli Faruk and Ramic, Amra and Kugele, Stefan}, title = {A Systematic Mapping Study on Contract-based Software Design for Dependable Systems}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2505.07542}, year = {2025}, abstract = {Background: Contract-based Design (CbD) is a valuable methodology for software design that allows annotation of code and architectural components with contracts, thereby enhancing clarity and reliability in software development. It establishes rules that outline the behaviour of software components and their interfaces and interactions. This modular approach enables the design process to be segmented into smaller, independently developed, tested, and verified system components, ultimately leading to more robust and dependable software. Aim: Despite the significance and well-established theoretical background of CbD, there is a need for a comprehensive systematic mapping study for reliable software systems. Our study provides an evidence-based overview of a method and demonstrates its practical feasibility. Method: To conduct this study, we systematically searched three different databases using specially formulated queries, which initially yielded 1,221 primary studies. After voting, we focused on 288 primary studies for more detailed analysis. Finally, a collaborative review allowed us to gather relevant evidence and information to address our research questions. Results: Our findings suggest potential avenues for future research trajectories in CbD, emphasising its role in improving the dependability of software systems. We highlight maturity levels across different domains and identify areas that may benefit from further research. Conclusion: Although CbD is a well-established software design approach, a more comprehensive literature review is needed to clarify its theoretical state about dependable systems. Our study addresses this gap by providing a detailed overview of CbD from various perspectives, identifying key gaps, and suggesting future research directions.}, language = {en} } @article{MaxUhl2023, author = {Max, Raphael and Uhl, Matthias}, title = {Moral luck in investment contexts: We consciously find unprofitable investments less moral}, volume = {18}, pages = {e0278677}, journal = {PLOS ONE}, number = {1}, publisher = {PLOS}, address = {San Francisco}, issn = {1932-6203}, doi = {https://doi.org/10.1371/journal.pone.0278677}, year = {2023}, abstract = {Moral luck refers to whether an actor is morally praised or blamed for an action whose outcome they could not influence. In two studies, we investigated the behavioral importance of this phenomenon in the realm of investments, which has become increasingly subject to ethical evaluations. In our first online experiment, we examined whether people's moral evaluation of an investment decision depended on its arbitrary outcome and whether their interpretation of the nature of the decision was driven by this outcome. Our results showed that profitable investments were considered more moral than unprofitable investments. Moreover, profitable investments were labeled "investments" instead of "speculation" or "gambling" more often than unprofitable ones. In our second study, we asked the subjects to assess investments independent of the outcome. After the outcome was announced, the subjects were given the opportunity to reflect and change their initial decision. The results show that people change the moral evaluation and label of investments when told that it had a bad outcome. This observation was stable across different investment contexts. These findings suggest that we must be careful with the increasing moralization of investment decisions and be sensitive to our cognitive biases.}, language = {en} } @inproceedings{deAndradeVellosoNogueiraFidelisetal.2023, author = {de Andrade, Mauren Louise S. C. and Velloso Nogueira, Matheus and Fidelis, Eduardo and Aguiar Campos, Luiz Henrique and Campos, Pietro and Sch{\"o}n, Torsten and de Abreu Faria, Lester}, title = {Exploiting GAN Capacity to Generate Synthetic Automotive Radar Data}, booktitle = {Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4}, editor = {Radeva, Petia and Farinella, Giovanni Maria and Bouatouch, Kadi}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-634-7}, doi = {https://doi.org/10.5220/0011672400003417}, pages = {262 -- 271}, year = {2023}, abstract = {In this paper, we evaluate the training of GAN for synthetic RAD image generation for four objects reflected by Frequency Modulated Continuous Wave radar: car, motorcycle, pedestrian and truck. This evaluation adds a new possibility for data augmentation when radar data labeling available is not enough. The results show that, yes, the GAN generated RAD images well, even when a specific class of the object is necessary. We also compared the scores of three GAN architectures, GAN Vanilla, CGAN, and DCGAN, in RAD synthetic imaging generation. We show that the generator can produce RAD images well enough with the results analyzed.}, language = {en} } @article{MaksimovskiFestagFacchi2026, author = {Maksimovski, Daniel and Festag, Andreas and Facchi, Christian}, title = {Adaptive Message Generation Rules for V2X Maneuver Coordination Service}, volume = {14}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2026.3652364}, pages = {6417 -- 6437}, year = {2026}, abstract = {Maneuver coordination enables connected and automated vehicles (CAVs) to collaboratively plan, negotiate, and execute driving maneuvers, aiming to enhance safety, traffic flow, and energy efficiency. As part of the Vehicle-to-Everything (V2X) communication system, it operates as a dedicated service that relies on detailed, bidirectional interactions between vehicles, unlike traditional broadcast-based V2X services. While maneuver coordination is the focus of ongoing research and standardization, the rules that govern when and how vehicles generate Maneuver Coordination Messages (MCMs) within the Maneuver Coordination Service (MCS) are still not fully defined. These rules are essential for ensuring timely and reliable coordination. This paper proposes three adaptive MCM generation strategies based on the operation mode of the MCS, maneuver priority, and current channel load. The first approach defines MCM rules for intent sharing, maneuver negotiation, and execution phases, factoring in maneuver importance. The second adjusts the frequency of intent MCMs when a negotiation message is received from another vehicle. The third adapts frequency based on real-time channel load during intent sharing. For comparison, two baseline strategies are also evaluated. The proposed rules are tested for highway merging and lane change use cases in traffic scenarios with increasing vehicle density and high channel loads. A comprehensive evaluation is conducted using metrics related to the network, message generation frequency, congestion control, and maneuver coordination. The results demonstrate significantly enhanced channel efficiency and communication reliability across all metrics. For example, under the final approach, maneuver negotiation time is reduced by a factor of five in congested V2X environments.}, language = {en} } @inproceedings{RodriguezArozamenaMatutePerezetal.2025, author = {Rodr{\´i}guez-Arozamena, Mario and Matute, Jose and P{\´e}rez, Joshu{\´e} and Ozbay, Burcu and Tezcan, Deryanur and Begecarslan, Enes and Mutlukaya, Irem and Mayer, Kevin and Volkersdorfer, Tina and Hof, Hans-Joachim}, title = {A Fail-Safe Decision Architecture for CCAM Applications}, booktitle = {Transport Transitions: Advancing Sustainable and Inclusive Mobility, Proceedings of the 10th TRA Conference, 2024 Dublin, Ireland - Volume 6: Connected Mobility Ecosystems}, editor = {McNally, Ciaran and Carroll, P{\´a}raic and Martinez-Pastor, Beatriz and Ghosh, Bidisha and Efthymiou, Marina and Valantasis-Kanellos, Nikolaos}, publisher = {Springer}, address = {Cham}, isbn = {978-3-032-06763-0}, doi = {https://doi.org/10.1007/978-3-032-06763-0_104}, pages = {731 -- 737}, year = {2025}, abstract = {In the context of Connected, Cooperative, and Automated Mobility (CCAM), precise ego-vehicle positioning and environmental status assessment are crucial. However, these tasks can be susceptible to sensor failures, misuse, and cyberattacks. Automation disengagements and system redundancy are common strategies to achieve Minimum Risk Conditions when failures occur. This paper presents a Fail-Safe decision architecture formulated within the framework of the SELFY project (https://selfy-project.eu/). The main aim is to reduce inaccuracies in GNSS-derived positioning through the incorporation of sensor fusion, AI-guided situational assessment, trajectory planning, and mode decision components. Additionally, the architecture has been designed to enable real-time updates and communication with external entities, including the Vehicle Security Operations Centre.}, language = {en} } @article{OetterProellSievertetal.2024, author = {Oetter, Nicolai and Pr{\"o}ll, Jonas and Sievert, Matti and Goncalves, Miguel and Rohde, Maximilian and Nobis, Christopher-Philipp and Knipfer, Christian and Aubreville, Marc and Pan, Zhaoya and Breininger, Katharina and Maier, Andreas and Kesting, Marco and Stelzle, Florian}, title = {Oral mucosa - an examination map for confocal laser endomicroscopy within the oral cavity: an experimental clinical study}, volume = {28}, pages = {266}, journal = {Clinical Oral Investigations}, number = {5}, publisher = {Springer}, address = {Berlin}, issn = {1436-3771}, doi = {https://doi.org/10.1007/s00784-024-05664-9}, year = {2024}, abstract = {Objectives Confocal laser endomicroscopy (CLE) is an optical method that enables microscopic visualization of oral mucosa. Previous studies have shown that it is possible to differentiate between physiological and malignant oral mucosa. However, differences in mucosal architecture were not taken into account. The objective was to map the different oral mucosal morphologies and to establish a "CLE map" of physiological mucosa as baseline for further application of this powerful technology. Materials and methods The CLE database consisted of 27 patients. The following spots were examined: (1) upper lip (intraoral) (2) alveolar ridge (3) lateral tongue (4) floor of the mouth (5) hard palate (6) intercalary line. All sequences were examined by two CLE experts for morphological differences and video quality. Results Analysis revealed clear differences in image quality and possibility of depicting tissue morphologies between the various localizations of oral mucosa: imaging of the alveolar ridge and hard palate showed visually most discriminative tissue morphology. Labial mucosa was also visualized well using CLE. Here, typical morphological features such as uniform cells with regular intercellular gaps and vessels could be clearly depicted. Image generation and evaluation was particularly difficult in the area of the buccal mucosa, the lateral tongue and the floor of the mouth. Conclusion A physiological "CLE map" for the entire oral cavity could be created for the first time. Clinical relevance This will make it possible to take into account the existing physiological morphological features when differentiating between normal mucosa and oral squamous cell carcinoma in future work.}, language = {en} } @article{AmmelingGanzRosbachetal.2026, author = {Ammeling, Jonas and Ganz, Jonathan and Rosbach, Emely and Lausser, Ludwig and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Benchmarking Foundation Models for Mitotic Figure Classification}, volume = {3}, pages = {2026:003}, journal = {Machine Learning for Biomedical Imaging}, number = {MELBA-BVM 2025 Special Issue}, publisher = {Melba editors}, address = {[s. l.]}, issn = {2766-905X}, doi = {https://doi.org/10.59275/j.melba.2026-a3eb}, pages = {38 -- 55}, year = {2026}, abstract = {The performance of deep learning models is known to scale with data quantity and diversity. In pathology, as in many other medical imaging domains, the availability of labeled images for a specific task is often limited. Self-supervised learning techniques have enabled the use of vast amounts of unlabeled data to train large-scale neural networks, i.e., foundation models, that can address the limited data problem by providing semantically rich feature vectors that can generalize well to new tasks with minimal training effort increasing model performance and robustness. In this work, we investigate the use of foundation models for mitotic figure classification. The mitotic count, which can be derived from this classification task, is an independent prognostic marker for specific tumors and part of certain tumor grading systems. In particular, we investigate the data scaling laws on multiple current foundation models and evaluate their robustness to unseen tumor domains. Next to the commonly used linear probing paradigm, we also adapt the models using low-rank adaptation (LoRA) of their attention mechanisms. We compare all models against end-to-end-trained baselines, both CNNs and Vision Transformers. Our results demonstrate that LoRA-adapted foundation models provide superior performance to those adapted with standard linear probing, reaching performance levels close to 100 \% data availability with only 10 \% of training data. Furthermore, LoRA-adaptation of the most recent foundation models almost closes the out-of-domain performance gap when evaluated on unseen tumor domains. However, full fine-tuning of traditional architectures still yields competitive performance.}, language = {en} } @article{MohanSchoen2026, author = {Mohan, Adithya and Sch{\"o}n, Torsten}, title = {Toward Robust Agents: A Survey of Adversarial Attacks and Defenses in Deep Reinforcement Learning}, volume = {14}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2026.3657855}, pages = {14481 -- 14497}, year = {2026}, abstract = {Deep Reinforcement Learning (DRL) has demonstrated remarkable success in autonomous decision-making across diverse domains, including robotics, autonomous driving, and game playing. However, recent studies have uncovered a critical vulnerability: DRL agents are highly susceptible to adversarial attacks that can significantly degrade their performance or lead to catastrophic failure. These attacks exploit different components of the learning pipeline observations, actions, rewards, and policies exposing new challenges unique to DRL compared to supervised learning. This survey provides a comprehensive examination of adversarial threats and corresponding defense mechanisms within the DRL paradigm. This also aims to serve as a foundational reference for researchers and practitioners seeking to understand and mitigate adversarial vulnerabilities in DRL.}, language = {en} } @unpublished{SalamatMatternOlzemetal.2025, author = {Salamat, Babak and Mattern, Dominik and Olzem, Sebastian-Sven and Elsbacher, Gerhard and Seidel, Christian and Tonello, Andrea M.}, title = {GMP3: Learning-Driven, Bellman-Guided Trajectory Planning for UAVs in Real-Time on SE(3)}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2509.21264}, year = {2025}, abstract = {We propose GMP3, a multiphase global path planning framework that generates dynamically feasible three-dimensional trajectories for unmanned aerial vehicles (UAVs) operating in cluttered environments. The framework extends traditional path planning from Euclidean position spaces to the Lie group SE(3), allowing joint learning of translational motion and rotational dynamics. A modified Bellman-based operator is introduced to support reinforcement learning (RL) policy updates while leveraging prior trajectory information for improved convergence. GMP3 is designed as a distributed framework in which agents influence each other and share policy information along the trajectory: each agent refines its assigned segment and shares with its neighbors via a consensus-based scheme, enabling cooperative policy updates and convergence toward a path shaped globally even under kinematic constraints. We also propose DroneManager, a modular ground control software that interfaces the planner with real UAV platforms via the MAVLink protocol, supporting real-time deployment and feedback. Simulation studies and indoor flight experiments validate the effectiveness of the proposed method in constrained 3D environments, demonstrating reliable obstacle avoidance and smooth, feasible trajectories across both position and orientation. The open-source implementation is available at https://github.com/Domattee/DroneManager.}, language = {en} } @inproceedings{JimenezReyesdelosMozosPereaPanosetal.2025, author = {Jimenez, Victor and Reyes de los Mozos, Mario and Perea Pa{\~n}os, Pau and Fritzsche, Paula Cecilia and Mayer, Kevin and Volkersdorfer, Tina and Hof, Hans-Joachim and Couturier, Christophe and Ernst, Thierry and Zhang, Miao and Saied Mohamed, Mohamed and Rodr{\´i}guez-Arozamena, Mario and Aranguren-Mendieta, I{\~n}igo and P{\´e}rez, Joshu{\´e} and Jousse, Adrien and Murguia, Carlos and van de Wouw, Nathan and Bellessort, Romain and Salami, Behzad and Jevtić, Aleksandar and Bannour, Boutheina and Rodr{\´i}guez Recasens, Manel and Ropero, Isaac and Ozbay, Burcu and Eren, Ali and Bektas, Mustafa and Tezcan, Deryanur and Pilz, Christoph and Haas, Sarah and Lenz, Gernot}, title = {SELFY - Self Assessment, Protection and Healing Tools for a Trustworthy and Resilient CCAM}, booktitle = {Transport Transitions: Advancing Sustainable and Inclusive Mobility, Proceedings of the 10th TRA Conference, 2024 Dublin, Ireland - Volume 6: Connected Mobility Ecosy}, editor = {McNally, Ciaran and Carroll, P{\´a}raic and Martinez-Pastor, Beatriz and Ghosh, Bidisha and Efthymiou, Marina and Valantasis-Kanellos, Nikolaos}, publisher = {Springer}, address = {Cham}, isbn = {978-3-032-06763-0}, doi = {https://doi.org/10.1007/978-3-032-06763-0_106}, pages = {745 -- 751}, year = {2025}, abstract = {SELFY envisions an agnostic toolbox for the self-management of security and resilience of the CCAM (Connected, Cooperative and Automated Mobility) ecosystem, which can be easily deployed to extend the current Operational Design Domain (ODD), providing self-awareness, self-resilience and self-healing mechanisms and enhancing trust between stakeholders. SELFY is based on four pillars: Situational awareness, Resilience, Secure Data Sharing and Trust and provides three groups of tools. SACP (Situational Awareness and Collaborative Perception) tools aim at providing all CCAM actors with a comprehensive understanding of their environment, i.e., the perception of objects, such as other traffic participants and stationary objects. CRHS (Cooperative Resilience and Healing System) tools enable self-protection actions whenever a compromising situation is detected in relation to assets, vehicles, operations, or the system itself. TDMS (Trust and Data Management System) tools establish a secure and trusted environment for data in a collaborative and cooperative context, both for infrastructure and assets, as well as for citizen's data, such as drivers or pedestrians with special attention to privacy considerations. By defining a collaborative environment between the different tools to respond to new threats, risks and attacks SELFY facilitates the comprehension of new challenges in the cybersecurity aspect of CCAMs.}, language = {en} } @inproceedings{JimenezReyesdelosMozosPereaPanosetal.2024, author = {Jimenez, Victor and Reyes de los Mozos, Mario and Perea Pa{\~n}os, Pau and Fritzsche, Paula Cecilia and Mayer, Kevin and Volkersdorfer, Tina and Hof, Hans-Joachim and Couturier, Christophe and Ernst, Thierry and Zhang, Miao and Saied Mohamed, Mohamed and Rodr{\´i}guez-Arozamena, Mario and Aranguren-Mendieta, I{\~n}igo and P{\´e}rez, Joshu{\´e} and Jousse, Adrien and Murguia, Carlos and van de Wouw, Nathan and Bellessort, Romain and Salami, Behzad and Jevtić, Aleksandar and Bannour, Boutheina and Rodr{\´i}guez Recasens, Manel and Ropero, Isaac and Ozbay, Burcu and Eren, Ali and Bektas, Mustafa and Tezcan, Deryanur and Pilz, Christoph and Haas, Sarah and Lenz, Gernot}, title = {SELFY - Self Assessment, Protection \& Healing Tools for a Trustworthy and Resilient CCAM}, booktitle = {Proceedings of the Transport Research Arena (TRA2024) Conference}, publisher = {Zenodo}, address = {Genf}, doi = {https://doi.org/10.5281/zenodo.10978183}, year = {2024}, abstract = {SELFY envisions an agnostic toolbox for the self-management of se-curity and resilience of the CCAM (Connected, Cooperative and Automated Mo-bility) ecosystem, which can be easily deployed to extend the current Operational Design Domain (ODD), providing self-awareness, self-resilience and self-heal-ing mechanisms and enhancing trust between stakeholders. SELFY is based on four pillars: Situational awareness, Resilience, Secure Data Sharing and Trust and provides three groups of tools. SACP (Situational Awareness and Collabo-rative Perception) tools aim at providing all CCAM actors with a comprehensive understanding of their environment, i.e., the perception of objects, such as other traffic participants and stationary objects. CRHS (Cooperative Resilience and Healing System) tools enable self-protection actions whenever a compromising situation is detected in relation to assets, vehicles, operations, or the system itself. TDMS (Trust and Data Management System) tools establish a secure and trusted environment for data in a collaborative and cooperative context, both for infra-structure and assets, as well as for citizen's data, such as drivers or pedestrians with special attention to privacy considerations. By defining a collaborative en-vironment between the different tools to respond to new threats, risks and attacks SELFY facilitates the comprehension of new challenges in the cybersecurity as-pect of CCAMs.}, language = {en} } @article{GleissnerKotonski2025, author = {Gleißner, Christian and Kotonski, Julia}, title = {The classification of rigid torus quotients with canonical singularities in dimension three}, volume = {36}, journal = {Rendiconti Lincei: Matematica e Applicazioni}, number = {2}, publisher = {EMS Press}, address = {Berlin}, issn = {1720-0768}, doi = {https://doi.org/10.4171/RLM/1070}, pages = {315 -- 352}, year = {2025}, abstract = {We provide a fine classification of rigid 3-dimensional torus quotients with isolated canonical singularities, up to biholomorphism and diffeomorphism. This complements the classification of Calabi-Yau 3-folds of type III0​, which are those quotients with Gorenstein singularities.}, language = {en} } @inproceedings{IrawatiBolukbasiRiener2025, author = {Irawati, Diah Ayu and Bolukbasi, Elif and Riener, Andreas}, title = {Advancing Generative AI Collaboration in Design-to-Code Workflows: Insights from Two Empirical Studies}, booktitle = {Proceedings of MUM 2025: The 24th International Conference on Mobile and Ubiquitous Multimedia}, editor = {Sorce, Salvatore and Elagroudy, Passant and Khamis, Mohamed}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-2015-4}, doi = {https://doi.org/10.1145/3771882.3771913}, pages = {33 -- 46}, year = {2025}, abstract = {For expert users to accept Generative AI (GenAI) as a true collaborative partner, it must move beyond simple task-awareness to an understanding of their workflow's underlying structural rules. This paper introduces a paradigm for AI collaborators that moves beyond simple task awareness to an understanding of the semantic and hierarchical relationships within a component-based system. We investigate this concept within the context of the design-to-code workflow, where inefficiencies arise from the modification of components within design systems. Through two empirical studies with designers and developers, we found that GenAI output was often rejected because it violated the component hierarchy. Designers required granular and visual control for refinements, whereas developers valued automated setup but required transparent validation of the generated code's logic. Based on these findings, we contribute design guidelines for achieving Component-Structure Awareness (CSA), with two core principles: the Atomic Recommender, which provides assistance that respects the component hierarchy, and Communication Archetypes, which allow GenAI to adapt its interaction style to the user's role and the atomic nature of their task. This work provides a new, higher-level concept for designing the next generation of truly collaborative GenAI agents.}, language = {en} } @article{JauernigUhlValentinov2021, author = {Jauernig, Johanna and Uhl, Matthias and Valentinov, Vladislav}, title = {The ethics of corporate hypocrisy: An experimental approach}, volume = {2021}, pages = {102757}, journal = {Futures}, number = {131}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0016-3287}, doi = {https://doi.org/10.1016/j.futures.2021.102757}, year = {2021}, abstract = {In the current landscape of management and business ethics scholarship, a prominent type of dissimulation is exemplified by corporate hypocrisy. The concept of corporate hypocrisy brings traditional morality to bear on the institutions of the modern society and thereby emphasizes the contested relationship between the research programs of individual and institutional ethics. Assuming that morality in the modern society resides in institutions rather than individuals, institutional ethics emphasizes limits to the ability of traditional morality to come to terms with the moral complexity of the market economy. The case of corporate hypocrisy shows however that traditional morality nurtures individual sensitivity to immoral behaviors which may undermine the modern institutional fabric theorized by institutional ethics. This argument is supported by our central experimental finding that the moral evaluation of individual and corporate hypocrisy is driven by essentially the same psychological mechanisms. Moreover, the experiment showed that both corporate and individual hypocrisy are condemned stronger than frankly wrong behavior even if their consequences are identical.}, language = {en} } @article{PeintnerMangerBergeretal.2025, author = {Peintner, Jakob and Manger, Carina and Berger, Melanie and Riener, Andreas}, title = {Balancing transparency and control: The impact of AI explanation detail on user perception in automated vehicles}, volume = {2025}, pages = {101742}, journal = {Transportation Research Interdisciplinary Perspectives}, number = {34}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2590-1982}, doi = {https://doi.org/10.1016/j.trip.2025.101742}, year = {2025}, abstract = {As automated vehicle technology advances, explainable AI has emerged as a critical tool to enable users to understand and predict the behavior of AI systems, particularly in safety-critical applications such as automated driving. However, increased transparency in AI explanations may inadvertently contribute to an "illusion of control", a cognitive bias in which drivers overestimate their influence or understanding of the AI's actions. We aim to better understand how the level of detail in AI explanations affects users of automated vehicles. In a virtual reality study, N = 44 participants experienced different explanation levels (low, medium, high) in an automated ride (SAE L4) compared to a baseline condition with no explanations. The results show a significant improvement in participants' user experience, acceptance, and explanation satisfaction, with more detailed explanations. Our findings also indicate that as AI explanations become more detailed, users' perceived level of control increases significantly, although this perception does not correlate with actual control capabilities. At the same time, it decreased their desire to take control, indicating users' susceptibility to the 'illusion of control' bias in the context of automated driving. Overall, this suggests that the design of explanation interfaces should strive for a balanced level of detail that promotes AI transparency without causing cognitive overload. At the same time, explainable AI can be utilized to decrease users' desire to intervene in the AI's actions.}, language = {en} } @article{KugeleObergfellSax2021, author = {Kugele, Stefan and Obergfell, Philipp and Sax, Eric}, title = {Model-based resource analysis and synthesis of service-oriented automotive software architectures}, volume = {20}, journal = {Software and Systems Modeling}, number = {6}, publisher = {Springer}, address = {Berlin}, issn = {1619-1374}, doi = {https://doi.org/10.1007/s10270-021-00896-9}, pages = {1945 -- 1975}, year = {2021}, abstract = {Context Automotive software architectures describe distributed functionality by an interaction of software components. One drawback of today's architectures is their strong integration into the onboard communication network based on predefined dependencies at design time. The idea is to reduce this rigid integration and technological dependencies. To this end, service-oriented architecture offers a suitable methodology since network communication is dynamically established at run-time. Aim We target to provide a methodology for analysing hardware resources and synthesising automotive service-oriented architectures based on platform-independent service models. Subsequently, we focus on transforming these models into a platform-specific architecture realisation process following AUTOSAR Adaptive. Approach For the platform-independent part, we apply the concepts of design space exploration and simulation to analyse and synthesise deployment configurations, i. e., mapping services to hardware resources at an early development stage. We refine these configurations to AUTOSAR Adaptive software architecture models representing the necessary input for a subsequent implementation process for the platform-specific part. Result We present deployment configurations that are optimal for the usage of a given set of computing resources currently under consideration for our next generation of E/E architecture. We also provide simulation results that demonstrate the ability of these configurations to meet the run time requirements. Both results helped us to decide whether a particular configuration can be implemented. As a possible software toolchain for this purpose, we finally provide a prototype. Conclusion The use of models and their analysis are proper means to get there, but the quality and speed of development must also be considered.}, language = {en} } @inproceedings{CostadeAraujoBaluReichmannetal.2025, author = {Costa de Araujo, Jo{\~a}o Paulo and Balu, Balahari Vignesh and Reichmann, Eik and Kelly, Jessica and Kugele, Stefan and Mata, N{\´u}ria and Grunske, Lars}, title = {Applying Concept-Based Models for Enhanced Safety Argumentation - Summary}, booktitle = {Software Engineering 2025: Proceedings}, editor = {Koziolek, Anne and Lamprecht, Anna-Lena and Th{\"u}m, Thomas and Burger, Erik}, publisher = {Gesellschaft f{\"u}r Informatik}, address = {Bonn}, issn = {2944-7682}, doi = {https://doi.org/10.18420/se2025-18}, pages = {65 -- 66}, year = {2025}, abstract = {In this extended abstract we summarize our work on using Concept Bottleneck Models (CBMs) for an enhanced safety argumentation of vision-based Machine Learning (ML) perception components in safety critical systems. This paper has been published at the International Symposium on Software Reliability Engineering (ISRRE'24)}, language = {en} } @inproceedings{KugeleSchreyerLamprecht2025, author = {Kugele, Stefan and Schreyer, Lorenz and Lamprecht, Martin}, title = {Cause-Effect Chain-Based Diagnosis of Automotive On-Board Energy Systems}, booktitle = {Software Engineering 2025: Proceedings}, editor = {Koziolek, Anne and Lamprecht, Anna-Lena and Th{\"u}m, Thomas and Burger, Erik}, publisher = {Gesellschaft f{\"u}r Informatik}, address = {Bonn}, issn = {2944-7682}, doi = {https://doi.org/10.18420/se2025-36}, pages = {111 -- 112}, year = {2025}, abstract = {This summary refers to the paper Cause-Effect Chain-Based Diagnosis of Automotive On-Board Energy Systems [KSL24]. This paper has been published in the Proceedings of the 18th European Conference on Software Architecture, ECSA 2024 in September 2024.}, language = {en} } @article{SalamatMatternOlzemetal.2026, author = {Salamat, Babak and Mattern, Dominik and Olzem, Sebastian-Sven and Elsbacher, Gerhard and Seidel, Christian and Tonello, Andrea M.}, title = {GMP3: Learning-Driven, Bellman-Guided Trajectory Planning for AAVs in Real-Time on SE(3)}, volume = {14}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2026.3661193}, pages = {22720 -- 22733}, year = {2026}, abstract = {We propose GMP3, a multiphase global path planning framework that generates dynamically feasible three-dimensional trajectories for unmanned aerial vehicles (UAVs) operating in cluttered environments. The framework extends traditional path planning from Euclidean position spaces to the Lie group SE(3), allowing joint learning of translational motion and rotational dynamics. A modified Bellman-based operator is introduced to support reinforcement learning (RL) policy updates while leveraging prior trajectory information for improved convergence. GMP3 is designed as a distributed framework in which agents influence each other and share policy information along the trajectory: each agent refines its assigned segment and shares with its neighbors via a consensus-based scheme, enabling cooperative policy updates and convergence toward a path shaped globally even under kinematic constraints.We also propose DroneManager, a modular ground control software that interfaces the planner with real UAVs platforms via the Micro Air Vehicle Link (MAVLink) protocol, supporting real-time deployment and feedback. Simulation studies and indoor flight experiments validate the effectiveness of the proposed method in constrained 3D environments, demonstrating reliable obstacle avoidance and smooth, feasible trajectories across both position and orientation.}, language = {en} } @article{RosbachAmmelingGanzetal.2026, author = {Rosbach, Emely and Ammeling, Jonas and Ganz, Jonathan and Bertram, Christof and Conrad, Thomas and Riener, Andreas and Aubreville, Marc}, title = {Stuck on Suggestions: Automation Bias, the Anchoring Effect, and the Factors That Shape Them in Computational Pathology}, volume = {3}, pages = {2026:007}, journal = {Machine Learning for Biomedical Imaging}, number = {MELBA-BVM 2025 Special Issue}, publisher = {Melba editors}, address = {[s. l.]}, issn = {2766-905X}, doi = {https://doi.org/10.59275/j.melba.2026-87b1}, pages = {126 -- 147}, year = {2026}, abstract = {Artificial intelligence (AI)-driven clinical decision support systems (CDSS) hold promise to improve diagnostic accuracy and efficiency in computational pathology. However, collaboration between human experts and AI may give rise to cognitive biases, such as automation and anchoring bias, wherein users may be inclined to blindly adopt system recommendations or be disproportionately influenced by the presence of AI predictions, even when they are inaccurate. These biases may be exacerbated under time pressure, pervasive in routine pathology diagnostics, or shaped by individual user characteristics. To investigate these effects, we conducted a web-based experiment in which trained pathology experts (n = 28) estimated tumor cell percentages twice: once independently and once with the aid of an AI. A subset of the estimates in each condition was performed under time constraints. Our findings indicate that AI integration generally enhances diagnostic performance. However, it also introduced a 7\% automation bias rate, quantified as the number of accepted negative consultations, where a previously correct independent assessment gets overturned by inaccurate AI guidance. While time pressure did not increase the frequency of automation bias occurrence, it appeared to intensify its severity, as evidenced by a performance decline linked to increased automation reliance under cognitive load. A linear mixed-effects model (LMM) analysis, simulating weighted averaging, revealed a statistically significant positive coefficient for AI advice, indicating a moderate degree of anchoring on system output. This effect was further intensified under time pressure, suggesting that anchoring bias may become more pronounced when cognitive resources are limited. A secondary LMM evaluation assessing automation reliance, used as a proxy for both automation and anchoring bias, demonstrated that professional experience and self-efficacy were associated with reduced dependence on system support, whereas higher confidence during AI-assisted decision-making was linked to increased automation reliance. Together, these findings underscore the dual nature of AI integration in clinical workflows, offering performance benefits while also introducing risks of cognitive bias-driven diagnostic errors. As an initial investigation focused on a single medical specialty and diagnostic task, this study aims to lay the groundwork for future research to explore these phenomena across diverse clinical contexts, ultimately supporting the establishment of appropriate reliance on automated systems and the safe, effective integration of human-AI collaboration in medical decision-making.}, language = {en} } @article{PugetGanzOstermaieretal.2024, author = {Puget, Chlo{\´e} and Ganz, Jonathan and Ostermaier, Julian and Conrad, Thomas and Parlak, Eda and Bertram, Christof and Kiupel, Matti and Breininger, Katharina and Aubreville, Marc and Klopfleisch, Robert}, title = {Artificial intelligence can be trained to predict c-KIT-11 mutational status of canine mast cell tumors from hematoxylin and eosin-stained histological slides}, volume = {62}, journal = {Veterinary Pathology}, number = {2}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858241286806}, pages = {152 -- 160}, year = {2024}, abstract = {Numerous prognostic factors are currently assessed histologically and immunohistochemically in canine mast cell tumors (MCTs) to evaluate clinical behavior. In addition, polymerase chain reaction (PCR) is often performed to detect internal tandem duplication (ITD) mutations in exon 11 of the c-KIT gene ( c-KIT-11-ITD) to predict the therapeutic response to tyrosine kinase inhibitors. This project aimed at training deep learning models (DLMs) to identify MCTs with c-KIT-11-ITD solely based on morphology. Hematoxylin and eosin (HE) stained slides of 368 cutaneous, subcutaneous, and mucocutaneous MCTs (195 with ITD and 173 without) were stained consecutively in 2 different laboratories and scanned with 3 different slide scanners. This resulted in 6 data sets (stain-scanner variations representing diagnostic institutions) of whole-slide images. DLMs were trained with single and mixed data sets and their performances were assessed under stain-scanner variations (domain shifts). The DLM correctly classified HE slides according to their c-KIT-11-ITD status in up to 87\% of cases with a 0.90 sensitivity and a 0.83 specificity. A relevant performance drop could be observed when the stain-scanner combination of training and test data set differed. Multi-institutional data sets improved the average accuracy but did not reach the maximum accuracy of algorithms trained and tested on the same stain-scanner variant (ie, intra-institutional). In summary, DLM-based morphological examination can predict c-KIT-11-ITD with high accuracy in canine MCTs in HE slides. However, staining protocol and scanner type influence accuracy. Larger data sets of scans from different laboratories and scanners may lead to more robust DLMs to identify c- KIT mutations in HE slides.}, language = {en} } @article{WilmFragosoGarciaMarzahletal.2022, author = {Wilm, Frauke and Fragoso-Garcia, Marco and Marzahl, Christian and Qiu, Jingna and Puget, Chlo{\´e} and Diehl, Laura and Bertram, Christof and Klopfleisch, Robert and Maier, Andreas and Breininger, Katharina and Aubreville, Marc}, title = {Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset}, volume = {9}, pages = {588}, journal = {Scientific Data}, publisher = {Springer}, address = {London}, issn = {2052-4463}, doi = {https://doi.org/10.1038/s41597-022-01692-w}, year = {2022}, abstract = {Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging. Recently, deep learning-based approaches have proven their potential for supporting pathologists in this regard. However, many of these supervised algorithms require a large amount of annotated data for robust development. We present a publicly available dataset of 350 whole slide images of seven different canine cutaneous tumors complemented by 12,424 polygon annotations for 13 histologic classes, including seven cutaneous tumor subtypes. In inter-rater experiments, we show a high consistency of the provided labels, especially for tumor annotations. We further validate the dataset by training a deep neural network for the task of tissue segmentation and tumor subtype classification. We achieve a class-averaged Jaccard coefficient of 0.7047, and 0.9044 for tumor in particular. For classification, we achieve a slide-level accuracy of 0.9857. Since canine cutaneous tumors possess various histologic homologies to human tumors the added value of this dataset is not limited to veterinary pathology but extends to more general fields of application.}, language = {en} } @article{AubrevilleWilmStathonikosetal.2023, author = {Aubreville, Marc and Wilm, Frauke and Stathonikos, Nikolas and Breininger, Katharina and Donovan, Taryn and Jabari, Samir and Veta, Mitko and Ganz, Jonathan and Ammeling, Jonas and van Diest, Paul J and Klopfleisch, Robert and Bertram, Christof}, title = {A comprehensive multi-domain dataset for mitotic figure detection}, volume = {10}, pages = {484}, journal = {Scientific Data}, publisher = {Springer}, address = {London}, issn = {2052-4463}, doi = {https://doi.org/10.1038/s41597-023-02327-4}, year = {2023}, abstract = {The prognostic value of mitotic figures in tumor tissue is well-established for many tumor types and automating this task is of high research interest. However, especially deep learning-based methods face performance deterioration in the presence of domain shifts, which may arise from different tumor types, slide preparation and digitization devices. We introduce the MIDOG++ dataset, an extension of the MIDOG 2021 and 2022 challenge datasets. We provide region of interest images from 503 histological specimens of seven different tumor types with variable morphology with in total labels for 11,937 mitotic figures: breast carcinoma, lung carcinoma, lymphosarcoma, neuroendocrine tumor, cutaneous mast cell tumor, cutaneous melanoma, and (sub)cutaneous soft tissue sarcoma. The specimens were processed in several laboratories utilizing diverse scanners. We evaluated the extent of the domain shift by using state-of-the-art approaches, observing notable differences in single-domain training. In a leave-one-domain-out setting, generalizability improved considerably. This mitotic figure dataset is the first that incorporates a wide domain shift based on different tumor types, laboratories, whole slide image scanners, and species.}, language = {en} } @article{MarzahlHillStaytetal.2022, author = {Marzahl, Christian and Hill, Jenny and Stayt, Jason and Bienzle, Dorothee and Welker, Lutz and Wilm, Frauke and Voigt, J{\"o}rn and Aubreville, Marc and Maier, Andreas and Klopfleisch, Robert and Breininger, Katharina and Bertram, Christof}, title = {Inter-species cell detection - datasets on pulmonary hemosiderophages in equine, human and feline specimens}, volume = {9}, pages = {269}, journal = {Scientific Data}, publisher = {Springer}, address = {London}, issn = {2052-4463}, doi = {https://doi.org/10.1038/s41597-022-01389-0}, year = {2022}, abstract = {Pulmonary hemorrhage (P-Hem) occurs among multiple species and can have various causes. Cytology of bronchoalveolar lavage fluid (BALF) using a 5-tier scoring system of alveolar macrophages based on their hemosiderin content is considered the most sensitive diagnostic method. We introduce a novel, fully annotated multi-species P-Hem dataset, which consists of 74 cytology whole slide images (WSIs) with equine, feline and human samples. To create this high-quality and high-quantity dataset, we developed an annotation pipeline combining human expertise with deep learning and data visualisation techniques. We applied a deep learning-based object detection approach trained on 17 expertly annotated equine WSIs, to the remaining 39 equine, 12 human and 7 feline WSIs. The resulting annotations were semi-automatically screened for errors on multiple types of specialised annotation maps and finally reviewed by a trained pathologist. Our dataset contains a total of 297,383 hemosiderophages classified into five grades. It is one of the largest publicly available WSIs datasets with respect to the number of annotations, the scanned area and the number of species covered.}, language = {en} } @article{GoebelMertensRiener2026, author = {G{\"o}bel, Jan-Philipp and Mertens, Jan Cedric and Riener, Andreas}, title = {Thermal imaging for the detection of driver impairment: evidence from a high-fidelity driving simulator study}, journal = {Traffic Injury Prevention}, publisher = {Taylor \& Francis}, address = {Philadelphia}, issn = {1538-9588}, doi = {https://doi.org/10.1080/15389588.2026.2624006}, year = {2026}, abstract = {Objectives Driving under the influence of alcohol (DUI) remains a major contributor to fatal traffic crashes worldwide. With increasing regulatory pressure, such as requirements by Euro NCAP for in-vehicle impairment detection, there is a growing need for reliable, real-time monitoring solutions. While traditional DUI detection approaches focus on driving behavior or eye movement analysis, this study explores the potential of thermal imaging as a noninvasive alternative for detecting alcohol impairment. Methods We conducted a large-scale experimental study with 120 participants in a high-fidelity driving simulator, capturing thermal facial data under both non-impaired and alcohol-impaired conditions. A novel temperature extraction method was developed based on facial landmarks, incorporating multiple frames to reduce noise and improve temporal stability. Ambient cabin temperature was also recorded to normalize facial temperature readings and control for environmental influences. Several machine learning classifiers, including Logistic Regression, Random Forest, Support Vector Machine (SVM), and Gradient-Boosting Models, were trained using five facial temperature features (cheek, temple, ear, forehead, and nasal tip) and evaluated via five-fold subject-wise cross-validation. Results Significant temperature changes were observed in specific facial regions (particularly the cheek, ear, temple, and nasal tip) under alcohol influence. Among the evaluated models, Logistic Regression achieved the highest average classification accuracy (62\%), while SVM demonstrated the most stable performance across folds. The model showed a slight conservative bias toward predicting the baseline (non-impaired) class, thereby reducing the risk of false positive classifications. Environmental conditions, including cabin temperature, were verified to be stable across both driving sessions, ensuring the validity of the physiological measurements. Conclusions This study demonstrates the feasibility of using thermal imaging for in-vehicle DUI detection under realistic conditions. Our contributions include the development of a robust facial temperature processing pipeline, the creation of a unique dataset collected under ecologically valid conditions, and a comprehensive comparison of seven state-of-the-art classification models. Thermal imaging represents a promising complementary modality for future driver monitoring systems focused on safety and impairment detection.}, language = {en} } @unpublished{SuemerHuberDuongetal.2025, author = {S{\"u}mer, {\"O}mer and Huber, Tobias and Duong, Dat and Ledgister Hanchard, Suzanna E. and Conati, Cristina and Andr{\´e}, Elisabeth and Solomon, Benjamin D. and Waikel, Rebekah L.}, title = {Evaluation of a Deep Learning and XAI based Facial Phenotyping Tool for Genetic Syndromes: A Clinical User Study}, publisher = {medRxiv}, address = {Cold Spring Harbor}, doi = {https://doi.org/10.1101/2025.06.08.25328588}, year = {2025}, abstract = {Artificial intelligence (AI) tools are increasingly employed in clinical genetics to assist in diagnosing genetic conditions by assessing photographs of patients. For medical uses of AI, explainable AI (XAI) methods offer a promising approach by providing interpretable outputs, such as saliency maps and region relevance visualizations. XAI has been discussed as important for regulatory purposes and to enable clinicians to better understand how AI tools work in practice. However, the real-world effects of XAI on clinician performance, confidence, and trust remain underexplored. This study involved a web-based user experiment with 31 medical geneticists to assess the impact of AI-only diagnostic assistance compared to XAI-supported diagnostics. Participants were randomly assigned to either group and completed diagnostic tasks with 18 facial images of individuals with known genetic syndromes and unaffected individuals, before and after experiencing the AI outputs. The results show that both AI-only and XAI approaches improved diagnostic accuracy and clinician confidence. The effects varied according to the accuracy of AI predictions and the clarity of syndromic features (sample difficulty). While AI support was viewed positively, users approached XAI with skepticism. Interestingly, we found a positive correlation between diagnostic improvement and XAI intervention. Although XAI support did not significantly enhance overall performance relative to AI alone, it prompted users to critically evaluate images with false predictions and influenced their confidence levels. These findings highlight the complexities of trust, perceived usefulness, and interpretability in AI-assisted diagnostics, with important implications for developing and implementing clinical decision-support tools in facial phenotyping for rare genetic diseases.}, language = {en} } @unpublished{AubrevilleGanzAmmelingetal.2024, author = {Aubreville, Marc and Ganz, Jonathan and Ammeling, Jonas and Kaltenecker, Christopher and Bertram, Christof}, title = {Model-based Cleaning of the QUILT-1M Pathology Dataset for Text-Conditional Image Synthesis}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2404.07676}, year = {2024}, abstract = {The QUILT-1M dataset is the first openly available dataset containing images harvested from various online sources. While it provides a huge data variety, the image quality and composition is highly heterogeneous, impacting its utility for text-conditional image synthesis. We propose an automatic pipeline that provides predictions of the most common impurities within the images, e.g., visibility of narrators, desktop environment and pathology software, or text within the image. Additionally, we propose to use semantic alignment filtering of the image-text pairs. Our findings demonstrate that by rigorously filtering the dataset, there is a substantial enhancement of image fidelity in text-to-image tasks.}, language = {en} } @article{BauderPaulaPfeilschifteretal.2024, author = {Bauder, Maximilian and Paula, Daniel and Pfeilschifter, Claus and Petermeier, Franziska and Kubjatko, Tibor and Riener, Andreas and Schweiger, Hans-Georg}, title = {Influences of Vehicle Communication on Human Driving Reactions: A Simulator Study on Reaction Times and Behavior for Forensic Accident Analysis}, volume = {24}, pages = {4481}, journal = {Sensors}, number = {14}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {https://doi.org/10.3390/s24144481}, year = {2024}, abstract = {Cooperative intelligent transport systems (C-ITSs) are mass-produced and sold in Europe, promising enhanced safety and comfort. Direct vehicle communication, known as vehicle-to-everything (V2X) communication, is crucial in this context. Drivers receive warnings about potential hazards by exchanging vehicle status and environmental data with other communication-enabled vehicles. However, the impact of these warnings on drivers and their inclusion in accident reconstruction remains uncertain. Unlike sensor-based warnings, V2X warnings may not provide a visible reason for the alert, potentially affecting reaction times and behavior. In this work, a simulator study on V2X warnings was conducted with 32 participants to generate findings on reaction times and behavior for accident reconstruction in connection with these systems. Two scenarios from the Car-2-Car Communication Consortium were implemented: "Stationary Vehicle Warning—Broken-Down Vehicle" and "Dangerous Situation—Electronic Emergency Brake Lights". Volkswagen's warning concept was utilized, as they are the sole provider of cooperative vehicles in Europe. Results show that V2X warnings without visible reasons did not negatively impact reaction times or behavior, with average reaction times between 0.58 s (steering) and 0.69 s (braking). No significant distraction or search for warning reasons was observed. However, additional information in the warnings caused confusion and was seldom noticed by subjects. In this study, participants responded correctly and appropriately to the shown false-positive warnings. A wrong reaction triggering an accident is possible but unlikely. Overall, V2X warnings showed no negative impacts compared with sensor-based systems. This means that there are no differences in accident reconstruction regarding the source of the warning (sensors or communication). However, it is important that it is known that there was a warning, which is why the occurrence of V2X warnings should also be saved in the EDR in the future.}, language = {en} }