TY - INPR A1 - Puget, Chloé A1 - Ganz, Jonathan A1 - Ostermaier, Julian A1 - Konrad, Thomas A1 - Parlak, Eda A1 - Bertram, Christof A1 - Kiupel, Matti A1 - Breininger, Katharina A1 - Aubreville, Marc A1 - Klopfleisch, Robert T1 - Deep Learning model predicts the c-Kit-11 mutational status of canine cutaneous mast cell tumors by HE stained histological slides N2 - 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. UR - https://doi.org/10.48550/arXiv.2401.06169 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2401.06169 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-46020 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - Field of Interest Proposal for Augmented Mitotic Cell Count BT - Comparison of Two Convolutional Networks T2 - Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOIMAGING UR - https://doi.org/10.5220/0007365700300037 KW - Mitotic Figure KW - Cell Segmentation KW - Digital Histopathology KW - Tumor Grading Y1 - 2019 UR - https://doi.org/10.5220/0007365700300037 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-19248 SN - 978-989-758-353-7 SN - 2184-4305 VL - 2 SP - 30 EP - 37 PB - SciTePress CY - Setúbal ER - TY - JOUR A1 - Bertram, Christof A1 - Aubreville, Marc A1 - Donovan, Taryn A1 - Bartel, Alexander A1 - Wilm, Frauke A1 - Marzahl, Christian A1 - Assenmacher, Charles-Antoine A1 - Becker, Kathrin A1 - Bennett, Mark A1 - Corner, Sarah M. A1 - Cossic, Brieuc A1 - Denk, Daniela A1 - Dettwiler, Martina A1 - Garcia Gonzalez, Beatriz A1 - Gurtner, Corinne A1 - Haverkamp, Ann-Kathrin A1 - Heier, Annabelle A1 - Lehmbecker, Annika A1 - Merz, Sophie A1 - Noland, Erica L. A1 - Plog, Stephanie A1 - Schmidt, Anja A1 - Sebastian, Franziska A1 - Sledge, Dodd G. A1 - Smedley, Rebecca C. A1 - Tecilla, Marco A1 - Thaiwong, Tuddow A1 - Fuchs-Baumgartinger, Andrea A1 - Meuten, Donald J. A1 - Breininger, Katharina A1 - Kiupel, Matti A1 - Maier, Andreas A1 - Klopfleisch, Robert T1 - Computer-assisted mitotic count using a deep learning–based algorithm improves interobserver reproducibility and accuracy JF - Veterinary Pathology N2 - 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. UR - https://doi.org/10.1177/03009858211067478 KW - canine cutaneous mast cell tumors KW - artificial intelligence KW - digital pathology KW - deep learning KW - mitotic figures KW - mitotic count KW - automated image analysis KW - computer assistance Y1 - 2021 UR - https://doi.org/10.1177/03009858211067478 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-13141 SN - 1544-2217 VL - 59 IS - 2 SP - 211 EP - 226 PB - Sage CY - London ER - TY - JOUR A1 - Marzahl, Christian A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Stayt, Jason A1 - Jasensky, Anne-Katherine A1 - Bartenschlager, Florian A1 - Fragoso-Garcia, Marco A1 - Barton, Ann K. A1 - Elsemann, Svenja A1 - Jabari, Samir A1 - Krauth, Jens A1 - Madhu, Prathmesh A1 - Voigt, Jörn A1 - Hill, Jenny A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - Deep Learning-based quantification of pulmonary hemosiderophages in cytology slides JF - Scientific Reports N2 - Exercise-induced pulmonary hemorrhage (EIPH) is a common condition in sport horses with negative impact on performance. Cytology of bronchoalveolar lavage fluid by use of a scoring system is considered the most sensitive diagnostic method. Macrophages are classified depending on the degree of cytoplasmic hemosiderin content. The current gold standard is manual grading, which is however monotonous and time-consuming. We evaluated state-of-the-art deep learning-based methods for single cell macrophage classification and compared them against the performance of nine cytology experts and evaluated inter- and intra-observer variability. Additionally, we evaluated object detection methods on a novel data set of 17 completely annotated cytology whole slide images (WSI) containing 78,047 hemosiderophages. Our deep learning-based approach reached a concordance of 0.85, partially exceeding human expert concordance (0.68 to 0.86, mean of 0.73, SD of 0.04). Intra-observer variability was high (0.68 to 0.88) and inter-observer concordance was moderate (Fleiss’ kappa = 0.67). Our object detection approach has a mean average precision of 0.66 over the five classes from the whole slide gigapixel image and a computation time of below two minutes. To mitigate the high inter- and intra-rater variability, we propose our automated object detection pipeline, enabling accurate, reproducible and quick EIPH scoring in WSI. UR - https://doi.org/10.1038/s41598-020-65958-2 Y1 - 2020 UR - https://doi.org/10.1038/s41598-020-65958-2 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-11783 SN - 2045-2322 VL - 10 PB - Springer Nature CY - London ER - TY - CHAP A1 - Aubreville, Marc A1 - Goncalves, Miguel A1 - Knipfer, Christian A1 - Oetter, Nicolai A1 - Würfl, Tobias A1 - Neumann, Helmut A1 - Stelzle, Florian A1 - Bohr, Christopher A1 - Maier, Andreas ED - Wiebe, Sheldon ED - Gamboa, Hugo ED - Fred, Ana ED - Bermúdez i Badia, Sergi T1 - Patch-based Carcinoma Detection on Confocal Laser Endomicroscopy Images BT - A Cross-Site Robustness Assessment T2 - Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies N2 - Deep learning technologies such as convolutional neural networks (CNN) provide powerful methods for image recognition and have recently been employed in the field of automated carcinoma detection in confocal laser endomicroscopy (CLE) images. CLE is a (sub-)surface microscopic imaging technique that reaches magnifications of up to 1000x and is thus suitable for in vivo structural tissue analysis. In this work, we aim to evaluate the prospects of a priorly developed deep learning-based algorithm targeted at the identification of oral squamous cell carcinoma with regard to its generalization to further anatomic locations of squamous cell carcinomas in the area of head and neck. We applied the algorithm on images acquired from the vocal fold area of five patients with histologically verified squamous cell carcinoma and presumably healthy control images of the clinically normal contra-lateral vocal cord. We find that the network trained on the oral cavity data reaches an accurac y of 89.45% and an area-under-the-curve (AUC) value of 0.955, when applied on the vocal cords data. Compared to the state of the art, we achieve very similar results, yet with an algorithm that was trained on a completely disjunct data set. Concatenating both data sets yielded further improvements in cross-validation with an accuracy of 90.81% and AUC of 0.970. In this study, for the first time to our knowledge, a deep learning mechanism for the identification of oral carcinomas using CLE Images could be applied to other disciplines in the area of head and neck. This study shows the prospect of the algorithmic approach to generalize well on other malignant entities of the head and neck, regardless of the anatomical location and furthermore in an examiner-independent manner. UR - https://doi.org/10.5220/0006534700270034 KW - Automatic Carcinoma Detection KW - Confocal Laser Endomicroscopy KW - Deep Convolutional Networks KW - Squamous Cell Carcinoma Y1 - 2018 UR - https://doi.org/10.5220/0006534700270034 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-26277 SN - 978-989-758-278-3 SP - 27 EP - 34 PB - SciTePress CY - Setúbal ER - TY - INPR A1 - Ganz, Jonathan A1 - Marzahl, Christian A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Richter, Barbara A1 - Puget, Chloé A1 - Denk, Daniela A1 - Demeter, Elena A. A1 - Tabaran, Flaviu A. A1 - Wasinger, Gabriel A1 - Lipnik, Karoline A1 - Tecilla, Marco A1 - Valentine, Matthew J. A1 - Dark, Michael A1 - Abele, Niklas A1 - Bolfa, Pompei A1 - Erber, Ramona A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Donovan, Taryn A1 - Jabari, Samir A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Information Mismatch in PHH3-Assisted Mitosis Annotation Leads to Interpretation Shifts in H&E Slide Analysis T2 - Research Square N2 - 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. UR - https://doi.org/10.21203/rs.3.rs-4900505/v1 Y1 - 2024 UR - https://doi.org/10.21203/rs.3.rs-4900505/v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-57630 SN - 2693-5015 PB - Research Square CY - Durham ER - TY - JOUR A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Marzahl, Christian A1 - Gurtner, Corinne A1 - Dettwiler, Martina A1 - Schmidt, Anja A1 - Bartenschlager, Florian A1 - Merz, Sophie A1 - Fragoso-Garcia, Marco A1 - Kershaw, Olivia A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - Deep learning algorithms out-perform veterinary pathologists in detecting the mitotically most active tumor region JF - Scientific reports N2 - Manual count of mitotic figures, which is determined in the tumor region with the highest mitotic activity, is a key parameter of most tumor grading schemes. It can be, however, strongly dependent on the area selection due to uneven mitotic figure distribution in the tumor section. We aimed to assess the question, how significantly the area selection could impact the mitotic count, which has a known high inter-rater disagreement. On a data set of 32 whole slide images of H&E-stained canine cutaneous mast cell tumor, fully annotated for mitotic figures, we asked eight veterinary pathologists (five board-certified, three in training) to select a field of interest for the mitotic count. To assess the potential difference on the mitotic count, we compared the mitotic count of the selected regions to the overall distribution on the slide. Additionally, we evaluated three deep learning-based methods for the assessment of highest mitotic density: In one approach, the model would directly try to predict the mitotic count for the presented image patches as a regression task. The second method aims at deriving a segmentation mask for mitotic figures, which is then used to obtain a mitotic density. Finally, we evaluated a two-stage object-detection pipeline based on state-of-the-art architectures to identify individual mitotic figures. We found that the predictions by all models were, on average, better than those of the experts. The two-stage object detector performed best and outperformed most of the human pathologists on the majority of tumor cases. The correlation between the predicted and the ground truth mitotic count was also best for this approach (0.963–0.979). Further, we found considerable differences in position selection between pathologists, which could partially explain the high variance that has been reported for the manual mitotic count. To achieve better inter-rater agreement, we propose to use a computer-based area selection for support of the pathologist in the manual mitotic count. UR - https://doi.org/10.1038/s41598-020-73246-2 Y1 - 2020 UR - https://doi.org/10.1038/s41598-020-73246-2 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-11794 SN - 2045-2322 VL - 10 PB - Springer Nature CY - London ER - TY - INPR A1 - Ammeling, Jonas A1 - Hecker, Moritz A1 - Ganz, Jonathan A1 - Donovan, Taryn A1 - Klopfleisch, Robert A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Automated Volume Corrected Mitotic Index Calculation Through Annotation-Free Deep Learning using Immunohistochemistry as Reference Standard N2 - 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. UR - https://doi.org/10.48550/arXiv.2311.08949 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2311.08949 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41549 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Mualla, Firas A1 - Aubreville, Marc A1 - Maier, Andreas ED - Maier, Andreas ED - Steidl, Stefan ED - Christlein, Vincent ED - Hornegger, Joachim T1 - Microscopy T2 - Medical Imaging Systems: An Introductory Guide N2 - We perceive the physical world around us using our eyes, but only down to a certain limit. Objects with a diameter smaller than 75 μm cannot be recognized by the naked eye, and due to this reason, they remained undiscovered for the most of human history. UR - https://doi.org/10.1007/978-3-319-96520-8_5 Y1 - 2018 UR - https://doi.org/10.1007/978-3-319-96520-8_5 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-26411 SN - 978-3-319-96520-8 SP - 69 EP - 90 PB - Springer CY - Cham ER - TY - INPR A1 - Ammeling, Jonas A1 - Schmidt, Lars-Henning A1 - Ganz, Jonathan A1 - Niedermair, Tanja A1 - Brochhausen-Delius, Christoph A1 - Schulz, Christian A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Attention-based Multiple Instance Learning for Survival Prediction on Lung Cancer Tissue Microarrays N2 - 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. UR - https://doi.org/10.48550/arXiv.2212.07724 Y1 - 2022 UR - https://doi.org/10.48550/arXiv.2212.07724 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-30642 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Stoeve, Maike A1 - Aubreville, Marc A1 - Oetter, Nicolai A1 - Knipfer, Christian A1 - Neumann, Helmut A1 - Stelzle, Florian A1 - Maier, Andreas T1 - Motion Artifact Detection in Confocal Laser Endomicroscopy Images N2 - Confocal Laser Endomicroscopy (CLE), an optical imaging technique allowing non-invasive examination of the mucosa on a (sub)- cellular level, has proven to be a valuable diagnostic tool in gastroenterology and shows promising results in various anatomical regions including the oral cavity. Recently, the feasibility of automatic carcinoma detection for CLE images of sufficient quality was shown. However, in real world data sets a high amount of CLE images is corrupted by artifacts. Amongst the most prevalent artifact types are motion-induced image deteriorations. In the scope of this work, algorithmic approaches for the automatic detection of motion artifact-tainted image regions were developed. Hence, this work provides an important step towards clinical applicability of automatic carcinoma detection. Both, conventional machine learning and novel, deep learning-based approaches were assessed. The deep learning-based approach outperforms the conventional approaches, attaining an AUC of 0.90. UR - https://doi.org/10.48550/arXiv.1711.01117 Y1 - 2018 UR - https://doi.org/10.48550/arXiv.1711.01117 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-12588 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Aubreville, Marc A1 - Pan, Zhaoya A1 - Sievert, Matti A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Oetter, Nicolai A1 - Stelzle, Florian A1 - Frenken, Ann-Kathrin A1 - Breininger, Katharina A1 - Goncalves, Miguel T1 - Few Shot Learning for the Classification of Confocal Laser Endomicroscopy Images of Head and Neck Tumors N2 - 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. UR - https://doi.org/10.48550/arXiv.2311.07216 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2311.07216 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41522 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Schlagowski, Ruben A1 - Herget, Frederick A1 - Heimerl, Niklas A1 - Hammerl, Maximilian A1 - Huber, Tobias A1 - Zwolsky, Pamina A1 - Gruca, Jan A1 - André, Elisabeth ED - Smith, Gillian ED - Whitehead, Jim ED - Samuel, Ben ED - Spiel, Katta ED - van Rozen, Riemer T1 - From a Social POV: The Impact of Point of View on Player Behavior, Engagement, and Experience in a Serious Social Simulation Game T2 - Proceedings of the 19th International Conference on the Foundations of Digital Games, FDG 2024 N2 - Multiplayer games with social aspects vary widely regarding client design, e.g., point of view or camera perspective. While design paradigms usually arise from gold standards that are set by previously successful games in the industry, the impact of such paradigms is under-researched for games that serve as scientific instruments, e.g., to research social behavior. Intending to investigate how such games should be designed, we built two multiplayer clients with the same game logic, one using a first-person point of view, while the other includes a top-down camera perspective. Then, we conducted an online user study in which players tested these game clients in extensive multiplayer sessions. Analyzing speech time, in-game logs, questionnaires, and qualitative feedback, we look at the perspectives’ impact on player behavior, engagement, and game experience in a scientific or "serious games" context. In addition, we have made our designed game UNISON and both clients available as open source to facilitate future empirical social science research. UR - https://doi.org/10.1145/3649921.3649936 Y1 - 2024 UR - https://doi.org/10.1145/3649921.3649936 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-65451 SN - 979-8-4007-0955-5 PB - ACM CY - New York ER - TY - INPR A1 - Pernias, Pablo A1 - Rampas, Dominic A1 - Aubreville, Marc T1 - Würstchen: Efficient Pretraining of Text-to-Image Models N2 - 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. UR - https://doi.org/10.48550/arXiv.2306.00637 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2306.00637 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-39160 PB - arXiv CY - Ithaca ER - TY - BOOK A1 - Elstermann, Matthes A1 - Fleischmann, Albert A1 - Moser, Christoph A1 - Oppl, Stefan A1 - Schmidt, Werner A1 - Stary, Christian T1 - Contextual Process Digitalization BT - Changing Perspectives – Design Thinking – Value-Led Design N2 - This open access book presents an overview and step-by-step explanation of process management. It starts with the individual participants’ perspectives on their work in a process and its structuring and harmonization, and then moves on to its specification in a model and how it is embedded in the organizational and IT environment of the company. Lastly, the book examines the joint processing of instances in the resulting socio-technical systems. A corresponding illustration, which expands with the overview, enables readers to gain a comprehensive understanding of business process management. The book presents various facets of business process management from the perspective of the participants, and introduces a selection of models that have proved useful in practice. The design of such models supports the transition from a more-or-less unstructured or unsatisfactory way of working to a structured process that corresponds to the ideas of the company and its customers. For this second edition, several new sections dealing with the integration of IoT processes, artificial intelligence, and social behavior patterns in process mining, a whole chapter on implementation and operation, and three new case studies were added. The book is intended for professionals in industry as well as students in the field of business information systems who are looking for guidelines on how to discover, create and implement real-world processes. UR - https://doi.org/10.1007/978-3-032-06901-6 Y1 - 2026 UR - https://doi.org/10.1007/978-3-032-06901-6 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-65685 SN - 978-3-032-06901-6 PB - Springer CY - Cham ET - Second Edition ER - TY - JOUR A1 - Wan, Lei A1 - Zhao, Jianxin A1 - Wiedholz, Andreas A1 - Bied, Manuel A1 - Martinez de Lucena, Mateus A1 - Jagtap, Abhishek Dinkar A1 - Festag, Andreas A1 - Fröhlich, Antônio A1 - Keen, Hannan Ejaz A1 - Vinel, Alexey T1 - A Systematic Literature Review on Vehicular Collaborative Perception—A Computer Vision Perspective JF - IEEE Transactions on Intelligent Transportation Systems N2 - The effectiveness of autonomous vehicles relies on reliable perception capabilities. Despite significant advancements in artificial intelligence and sensor fusion technologies, current single-vehicle perception systems continue to encounter limitations, notably visual occlusions and limited long-range detection capabilities. Collaborative Perception (CP), enabled by Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication, has emerged as a promising solution to mitigate these issues and enhance the reliability of autonomous systems. Beyond advancements in communication, the computer vision community is increasingly focusing on improving vehicular perception through collaborative approaches. However, a systematic literature review that thoroughly examines existing work and reduces subjective bias is still lacking. Such a systematic approach helps identify research gaps, recognize common trends across studies, and inform future research directions. In response, this study follows the PRISMA 2020 guidelines and includes 106 peer-reviewed articles. These publications are analyzed based on modalities, collaboration schemes, and key perception tasks. Through a comparative analysis, this review illustrates how different methods address practical issues such as pose errors, temporal latency, communication constraints, domain shifts, heterogeneity, and adversarial attacks. Furthermore, it critically examines evaluation methodologies, highlighting a misalignment between current metrics and CP’s fundamental objectives. By delving into all relevant topics in-depth, this review offers valuable insights into challenges, opportunities, and risks, serving as a reference for advancing research in vehicular collaborative perception. UR - https://doi.org/10.1109/TITS.2025.3631141 Y1 - 2025 UR - https://doi.org/10.1109/TITS.2025.3631141 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-64708 SN - 1558-0016 VL - 27 IS - 1 SP - 81 EP - 118 PB - IEEE CY - New York ER - TY - JOUR A1 - Mertes, Silvan A1 - Huber, Tobias A1 - Weitz, Katharina A1 - Heimerl, Alexander A1 - André, Elisabeth T1 - GANterfactual—Counterfactual Explanations for Medical Non-experts Using Generative Adversarial Learning JF - Frontiers in Artificial Intelligence N2 - With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, many state-of-the-art tools to explain such classifiers rely on visual highlighting of important areas of the input data. Contrary, counterfactual explanation systems try to enable a counterfactual reasoning by modifying the input image in a way such that the classifier would have made a different prediction. By doing so, the users of counterfactual explanation systems are equipped with a completely different kind of explanatory information. However, methods for generating realistic counterfactual explanations for image classifiers are still rare. Especially in medical contexts, where relevant information often consists of textural and structural information, high-quality counterfactual images have the potential to give meaningful insights into decision processes. In this work, we present GANterfactual, an approach to generate such counterfactual image explanations based on adversarial image-to-image translation techniques. Additionally, we conduct a user study to evaluate our approach in an exemplary medical use case. Our results show that, in the chosen medical use-case, counterfactual explanations lead to significantly better results regarding mental models, explanation satisfaction, trust, emotions, and self-efficacy than two state-of-the art systems that work with saliency maps, namely LIME and LRP. UR - https://doi.org/10.3389/frai.2022.825565 Y1 - 2022 UR - https://doi.org/10.3389/frai.2022.825565 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-57192 SN - 2624-8212 VL - 5 PB - Frontiers Media CY - Lausanne ER - TY - INPR A1 - Mertes, Silvan A1 - Karle, Christina A1 - Huber, Tobias A1 - Weitz, Katharina A1 - Schlagowski, Ruben A1 - André, Elisabeth T1 - Alterfactual Explanations - The Relevance of Irrelevance for Explaining AI Systems N2 - Explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial Intelligence (XAI), as they follow a natural way of reasoning that humans are familiar with. However, all common approaches from this field are based on communicating information about features or characteristics that are especially important for an AI's decision. We argue that in order to fully understand a decision, not only knowledge about relevant features is needed, but that the awareness of irrelevant information also highly contributes to the creation of a user's mental model of an AI system. Therefore, we introduce a new way of explaining AI systems. Our approach, which we call Alterfactual Explanations, is based on showing an alternative reality where irrelevant features of an AI's input are altered. By doing so, the user directly sees which characteristics of the input data can change arbitrarily without influencing the AI's decision. We evaluate our approach in an extensive user study, revealing that it is able to significantly contribute to the participants' understanding of an AI. We show that alterfactual explanations are suited to convey an understanding of different aspects of the AI's reasoning than established counterfactual explanation methods. UR - https://doi.org/10.48550/arXiv.2207.09374 Y1 - 2022 UR - https://doi.org/10.48550/arXiv.2207.09374 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-57414 PB - arXiv CY - Ithaca ER - TY - BOOK A1 - Fleischmann, Albert A1 - Oppl, Stefan A1 - Schmidt, Werner A1 - Stary, Christian T1 - Contextual Process Digitalization BT - Changing Perspectives – Design Thinking – Value-Led Design N2 - This open access book presents an overview and step-by-step explanation of process management. It starts with the individual participants’ perspectives on their work in a process and its structuring and harmonization, and then moves on to its specification in a model and how it is embedded in the organizational and IT environment of the company. Lastly, the book examines the joint processing of instances in the resulting socio-technical systems. A corresponding illustration, which expands with the overview, enables readers to gain a comprehensive understanding of business process management. The book presents various facets of business process management from the perspective of the participants, and introduces a selection of models that have proved useful in practice. The design of such models supports the transition from a more-or-less unstructured or unsatisfactory way of working to a structured process that corresponds to the ideas of the company and its customers. The book is intended for professionals in industry as well as students in the field of business information systems who are looking for guidelines on how to discover, create and implement real-world processes. UR - https://doi.org/10.1007/978-3-030-38300-8 KW - open access KW - S-BPM KW - design thinking KW - business process management KW - workflow management KW - organization Y1 - 2020 UR - https://doi.org/10.1007/978-3-030-38300-8 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-21703 SN - 978-3-030-38299-5 SN - 978-3-030-38302-2 SN - 978-3-030-38300-8 PB - Springer CY - Cham ER - TY - JOUR A1 - Gregor, Markus A1 - Bauder, Maximilian A1 - Kirsten Vidal de Oliveira, Aline A1 - Mast, Pascal A1 - Rüther, Ricardo A1 - Schweiger, Hans-Georg T1 - Approaches for Lifetime Prediction of Vehicle Traction Battery Systems During a Technical Inspection: A Systematic Review JF - World Electric Vehicle Journal N2 - Creating trust in society for new technologies, such as a new types of powertrains, and making them marketable requires transparent, neutral, and independent technical verification. This is crucial for the acceptance and success of electrified vehicles in the used car markets. A key component of electric vehicles is the traction battery, whose current and future condition, particularly regarding aging, determines its residual value and safe operation. This review aims to identify and evaluate methods for predicting the lifetime of onboard traction batteries, focusing on their applicability in technical inspections. A systematic literature and patent review was conducted using targeted keywords, yielding 22 patents and 633 publications. From these, 150 distinct lifetime prediction methods were extracted and categorized into a four-level mind map. These methods are summarized, cited, and structured in detailed tables. The relationships between approaches are explained to clarify the current research landscape. Long Short-Term Memory, Convolutional Neural Networks, and Particle Filters were identified as the most frequently used techniques. However, no methods were found suitable for predicting the lifetime of traction batteries during technical vehicle inspections, which operate under short test durations, limited data access, and diverse real-world operating conditions. Most studies focused on cell-level testing and did not address complete battery systems in operational vehicles. This gap highlights the need for applied research and the development of practical methods to support battery assessment in real-world conditions. Advancing this field is essential to foster confidence in battery systems and enable a sustainable transition to electromobility. UR - https://doi.org/10.3390/wevj17010003 Y1 - 2025 UR - https://doi.org/10.3390/wevj17010003 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-65631 SN - 2032-6653 VL - 17 IS - 1 PB - MDPI CY - Basel ER - TY - JOUR A1 - Bienert, Jörg A1 - Regnet, Simon T1 - Stability Analysis for an Ultra-Lightweight Glider Airplane with Electric Driven Two-Blade Propeller JF - Vibration N2 - Safety is the most important requirement in flight operations. This also affects the application for an extreme lightweight glider in this paper. Essential properties are the target weight below 120 kgand the electric propulsion. The unsymmetric inertia from the two-blade propeller at the rear in combination with the light and flexible aluminium tube support makes it necessary to investigate the risk of mechanical instability. Starting from the equations of motion, the time-variant system matrices are set up. The simulation of Floquet multiplier and Hill’s hyper-eigenvalue problem provide the necessary information about the system stability. The conclusion is that the potential instability due to structural damping in the observed system can be avoided in the range of operation. The damping, experimentally determined by approximately 2%, is sufficient. UR - https://doi.org/10.3390/vibration9010003 Y1 - 2025 UR - https://doi.org/10.3390/vibration9010003 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-65640 SN - 2571-631X VL - 9 IS - 1 PB - MDPI CY - Basel ER - TY - BOOK A1 - Fleischmann, Albert A1 - Oppl, Stefan A1 - Schmidt, Werner A1 - Stary, Christian T1 - Ganzheitliche Digitalisierung von Prozessen BT - Perspektivenwechsel – Design Thinking – Wertegeleitete Interaktion N2 - In diesem Open-Access-Buch wird das Geschäftsprozessmanagement als ein ganzheitlicher Prozess begriffen, der der Mitwirkung aller Stakeholder bedarf. Denn das traditionelle Business Process Engineering stößt heute angesichts der Digitalisierung und der dynamischen Entwicklung von Organisationen immer mehr an seine Grenzen, beispielsweise bezüglich Agilität. Um nun das Wesen von Aufgaben und Abläufen in Organisationen zu erfassen, schlagen die Autoren einen Perspektivwechsel vor: das Denken in Kommunikationsprozessen. Dieses Konzept lässt sich wirtschaftlich, organisatorisch und technisch ohne einschlägige Vorkenntnisse umsetzen. Leserinnen und Leser finden in dem Buch konkrete Handlungsanleitungen für die Digitalisierung von organisationsrelevanten Abläufen. Daneben liefern die Autoren Einblicke in die Systemtheorie und in das Design Thinking. Ihr Ziel ist, Konzepte einfach und verständlich zu erläutern, ohne dabei komplexe Zusammenhänge zu vernachlässigen. Dank ausführlicher Konzeptdarstellung und Ausflüge in die Theorie mit Beispielen aus der Praxis, eignet es sich für Studierende und für Wissenschaftler genauso wie für Praktiker. Entwickler und andere Fachkräfte aus den Bereichen Operatives Management, Geschäftsprozessmanagement, Organisationsentwicklung, Qualitätsmanagement, Wissensmanagement werden sich von der Übersichtlichkeit und dem Nutzwert angesprochen fühlen. Der Inhalt - Modelle - Modellierungssprachen - Vorgehensweise von der Modellbildung zur Digitalisierung - Vorbereitung der Prozessimplementierung - Umsetzung - Praxisbeispiel UR - https://doi.org/10.1007/978-3-658-22648-0 Y1 - 2018 UR - https://doi.org/10.1007/978-3-658-22648-0 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-26306 SN - 978-3-658-22647-3 PB - Springer Vieweg CY - Wiesbaden ER - TY - JOUR A1 - Fleischmann, Albert A1 - Schmidt, Werner A1 - Stary, Christian T1 - Dynamic Socio-technical System Design based on Stakeholder Interaction JF - Complex Systems Informatics and Modeling Quarterly (CSIMQ) N2 - In order to directly involve stakeholders in socio-technical system design, we argue for streamlining executable process specifications with business process modeling. Due to current agility requirements of organizations, socio-technical system development is considered one of the key activities of members of the organizations. Dynamic process adaptation enable handling the volatility of business operation and IT infrastructure. Subject-oriented process representations are key enablers to dynamic adaptation due to their capability for stakeholders to create directly executable models. In this way stakeholder can be involved in change management pro-actively. Subject-oriented models (i) represent all relevant features required for system control and decision making, and (ii) are executable on demand. This effectiveness enables organizational change in a creative and efficient way, while establishing innovative design and change management tools. Subject-oriented Business Process Management capabilities are reflected in this realm revealing benefits and potential for further research. UR - https://doi.org/10.7250/csimq.2015-3.04 Y1 - 2015 UR - https://doi.org/10.7250/csimq.2015-3.04 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-56685 SN - 2255-9922 VL - 2015 IS - 3 SP - 63 EP - 83 PB - Technische Universität Riga CY - Riga ER -