@article{PrueferWeisserGlushychetal.2025, author = {Pr{\"u}fer, Kevin and Weisser, Eduard and Glushych, Viktor and Tr{\"o}ber, Philipp and Hartmann, Christoph and Volk, Wolfram}, title = {Seebeck Coefficient Modification via Extreme High-Speed Laser Material Deposition for Tool Materials}, volume = {2025}, journal = {Procedia CIRP}, number = {137}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2212-8271}, doi = {https://doi.org/10.1016/j.procir.2025.02.265}, pages = {265 -- 270}, year = {2025}, abstract = {During blanking and cold forming of metals, thermoelectricity almost always occurs. While thermoelectric voltages can be used for temperature measurement via a tool-workpiece thermocouple, currents significantly influence adhesion formation. In both cases, the thermoelectric behavior of tool and workpiece materials, characterized by the Seebeck coefficient, plays a decisive role. While a large difference in coefficients increases the accuracy of temperature measurement, similar coefficients improve wear behavior. Currently, there is no method to adjust the Seebeck coefficient of materials without experimental procedures, which restricts the selection of tool materials based on their Seebeck coefficient. This study presents a novel approach for adjusting the Seebeck coefficient of tool steels using tailored coatings applied by extreme high-speed laser material deposition (EHLA). Therefore, an analysis was conducted to investigate the effects of chemical composition, substrate material and its heat treatment on the thermoelectric and mechanical behavior of the coating. The results demonstrate that targeted modification via tailored EHLA coatings is possible.}, language = {en} } @inproceedings{PlatzKlanDecker2023, author = {Platz, Melanie and Klan, Friederike and Decker, Alexander Johannes}, title = {Developing and promoting search engine literacy in primary education}, booktitle = {Proceedings of 4th International Open Search Symposium \#ossym2022, CERN, Geneva Switzerland, 10-12 October 2022}, editor = {Granitzer, Michael and G{\"u}etl, Christian and Plote, Christine and Voigt, Stefan and Wagner, Andreas}, publisher = {Zenodo}, address = {Genf}, isbn = {978-92-9083-646-9}, doi = {https://doi.org/10.5281/zenodo.8066392}, pages = {43 -- 48}, year = {2023}, 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{HaryantoVaculin2025, author = {Haryanto, Aditya and Vaculin, Ondrej}, title = {YoFlow Method for Scenario Based Automatic Accident Detection}, volume = {7}, journal = {IEEE Open Journal of Intelligent Transportation Systems}, publisher = {IEEE}, address = {New York}, issn = {2687-7813}, doi = {https://doi.org/10.1109/OJITS.2025.3639557}, pages = {61 -- 73}, year = {2025}, abstract = {Recent advances in sensor and computing technologies have enabled road side units (RSUs) to not only monitor traffic flow but also process data in real time to improve road safety. However, leveraging RSUs for proactive accident detection remains a challenging and underexplored task, partly due to the lack of diverse accident data. To address this, this study proposes two key contributions: (i) a scenario-based synthetic data generation framework, and (ii) YoFlow, a novel system for vehicle-tovehicle accident detection from a simulated RSU camera perspective. The proposed framework leverages the PEGASUS method for scenario generation strategy and BeamNG.tech for generating synthetic traffic videos. This approach led to the development of the SB-SIF dataset, which includes five representative intersection crash scenarios derived from German accident data. The SB-SIF dataset contains 914 crash videos, 123 near-miss events, and 924 normal traffic instances and is publicly available at: https://doi.org/10.5281/zenodo.15267252. The proposed YoFlow system identifies accidents by analyzing temporal variations in vehicle speed vectors, using YOLO for vehicle classification and CUDA-accelerated dense optical flow to capture abrupt motion changes. The extracted features are processed and classified using an XGBoost model, achieving 94\% recall and 90\% precision in accident detection.}, language = {en} } @article{KauppHuber2025, author = {Kaupp, Sabine and Huber, Florian}, title = {Does mental model similarity equal innovation team performance?}, volume = {22}, journal = {Innovation \& Management Review}, number = {4}, publisher = {Emerald}, address = {Bingley}, issn = {2515-8961}, doi = {https://doi.org/10.1108/INMR-09-2023-0152}, pages = {280 -- 292}, year = {2025}, abstract = {Purpose This paper addresses challenges and opportunities of interdisciplinary teamwork in innovation management, focusing on how team mental models (TMMs) can foster more effective collaboration among team members from diverse backgrounds. The research examines the relationship between TMM similarity and team performance in interdisciplinary innovation teams. Design/methodology/approach An exploratory study was conducted with 55 participants across 15 teams. TMM similarity was measured by analyzing team interactions using a web-based interface that facilitated contrasted comparison ratings. These ratings were first processed into individual graphs via a shortest-node-finding pathfinder algorithm, then compared. Subject matter experts evaluated team performance. Findings The results reveal a significant positive correlation between TMM similarity and team performance in interdisciplinary innovation teams, suggesting that greater alignment in team members' mental models enhances overall innovation project performance. Research limitations/implications Although the academic programs sampled replicate the environment, challenges and various other aspects of innovation projects, they can only be considered proxies for innovation projects within real organizations. Further research within professional environments, using a larger sample, is recommended. Practical implications The findings highlight the value of assessing and fostering TMM similarity to improve teamwork and performance in interdisciplinary innovation projects. The interface and code used are publicly available to encourage their implementation in organizations. Originality/value This research provides novel insights into the application of TMMs within interdisciplinary innovation teams, extending the concept beyond its traditional use in unidisciplinary and structured task settings.}, language = {en} } @article{PanzerLandesbergerLuzinetal.2025, author = {Panzer, Hannes and Landesberger, Martin and Luzin, Vladimir and Rauner, Dominik and Wolf, Daniel and Zaeh, Michael}, title = {Evaluating the predictive capabilities of part-scale residual stress simulations of PBF-LB/M up to crack formation by a comparison to neutron diffraction}, volume = {2026}, pages = {111713}, journal = {Engineering Fracture Mechanics}, number = {331}, publisher = {Elsevier}, address = {Kidlington}, issn = {0013-7944}, doi = {https://doi.org/10.1016/j.engfracmech.2025.111713}, year = {2025}, abstract = {Additive manufacturing technologies have proven to be an excellent alternative to conventional production methods, especially when geometrically complex parts and low production quantities are aimed at. Specifically, powder bed fusion of metals using a laser beam (PBF-LB/M) additionally allows for the manufacturing of mechanically highly stressable parts. However, the heat input through the laser beam into the material and an irregular cooling during the processing result in the formation of high residual stresses. These lead to form deviations outside the specified tolerances and may accumulate to an extent, at which stress-induced cracking occurs. This emphasizes the need for an accurate prediction of the residual stresses during the PBF-LB/M process with the goal of a first-time-right additive manufacturing. In this study, three specimens exhibiting high residual stress formations during PBF-LB/M were manufactured from the nickel-based superalloy Inconel 718. Afterwards, the stresses were measured by means of neutron diffraction. The results provided the validation data for a subsequent finite element simulation, representing the build-up process on a part-scale, in which the data evaluation was conducted in accordance with the measurements for a high comparability. A comparison between the simulation and the neutron diffraction results of all three specimens showed a very good agreement of the normal stresses in all three coordinate directions, both for tensile and compressive stresses. The obtained results highlight the validity of the applied simplified part-scale simulation. The latter can, therefore, be utilized to increase the process understanding of residual stress and crack formations. It can also be used to enable process parameter modifications or geometry adaptions, aiming at a first-time-right additive manufacturing.}, language = {en} } @article{SchmidtZehAndersetal.2020, author = {Schmidt, Sebastian-Manuel and Zeh, Stefan and Anders, Karina and Hirschmann, Katrin and Stieg, Volker}, title = {Wissenschaftliche Weiterbildung neu bewertet}, volume = {2020}, journal = {Zeitschrift Hochschule und Weiterbildung}, subtitle = {Das Spannungsverh{\"a}ltnis von Bildungsauftrag und Nachfrageorientierung als strukturgebendes Element f{\"u}r bayerische Hochschulen}, number = {1}, publisher = {DGWF}, address = {Kassel}, issn = {2567-2673}, doi = {https://doi.org/10.4119/zhwb-3136}, pages = {44 -- 54}, year = {2020}, abstract = {Die Interpretation der Hochschule als Institution des lebenslangen Lernens und das {\"O}ffnen f{\"u}r neue Zielgruppen stellt die staatlichen Bildungseinrichtungen vor erhebliche Herausforderungen, die Aktualisierungshandeln erforderlich machen. Hierdurch begeben sich die staatlichen Einrichtungen auf einen bereits etablierten Bildungsmarkt, der sich vom bekannten Handlungsfeld unterscheidet, da er unentwegt ein agiles Handeln und eine schnelle Adaptionsf{\"a}higkeit auf neue Bildungsanforderungen ben{\"o}tigt. Immer {\"o}fter ist aber die Einrichtung Universit{\"a}t in einer unentwegten Grundsatzdebatte gefangen, die sich immer durch zwei Extrema auszeichnet: arbeitet man marktzentriert oder beharrt man auf seiner vorhandenen Rolle als staatliche Einrichtung mit eindeutigem Bildungsauftrag und wie setzt man nun wissenschaftliche Weiterbildung gem{\"a}ß dessen um? Kontr{\"a}r zur allgegenw{\"a}rtigen Interpretation „Bildungsauftrag vs. / oder Cash Cow" und einem notwendigen Kl{\"a}rungsbedarf der Situationslage ist genau dieses Spannungsverh{\"a}ltnis zwischen den beiden Dimensionen f{\"u}r die Umsetzung der wissenschaftlichen Weiterbildung an (bayerischen) Hochschulen notwendig. Das Spannungsfeld Bildungsauftrag und Nachfrageorientierung ist die beispiellose Triebkraft f{\"u}r Existenz, erfolgreiche Durchf{\"u}hrung und Weiterentwicklung der wissenschaftlichen Weiterbildung und des (Weiter-)Bildungsmarkts.}, language = {de} } @article{PiendlRadtkeJacobsenetal.2025, author = {Piendl, Daniel and Radtke, Maximilian-Peter and Jacobsen, Hendrik and Bock, J{\"u}rgen and Zaeh, Michael}, title = {Predictive Maintenance of Ball Screws: A Comparative Study Using Real-World Industrial Data}, volume = {2025}, journal = {Procedia CIRP}, number = {134}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2212-8271}, doi = {https://doi.org/10.1016/j.procir.2025.02.135}, pages = {390 -- 395}, year = {2025}, abstract = {Ball screws are widely used in machine tool feed drives. With increasing degradation of the ball screws, machining accuracy and economic efficiency decrease. Past investigations have shown that condition monitoring models can predict this degradation. However, these models are typically trained and evaluated using datasets derived from test benches, questioning their applicability to real machine tools. In this article, a comparative evaluation of a selection of these condition monitoring models using an industrial dataset is described. This dataset consists of measurement data from a total of nine ball screws used in three machine tools until failure. It was shown that when using data of multiple ball screws or machines, artificial neural networks or automated machine learning methods achieve a higher accuracy than statistical methods. However, for smaller datasets, statistical methods perform almost as well. The results provide an insight into the industrial applicability of the evaluated condition monitoring models.}, language = {en} } @article{KoecherBelyaevHermannetal.2023, author = {K{\"o}cher, Aljosha and Belyaev, Alexander and Hermann, Jesko and Bock, J{\"u}rgen and Meixner, Kristof and Volkmann, Magnus and Winter, Michael and Zimmermann, Patrick and Grimm, Stephan and Diedrich, Christian}, title = {A reference model for common understanding of capabilities and skills in manufacturing}, volume = {71}, journal = {at - Automatisierungstechnik}, number = {2}, publisher = {De Gruyter}, address = {Berlin}, issn = {2196-677X}, doi = {https://doi.org/10.1515/auto-2022-0117}, pages = {94 -- 104}, year = {2023}, abstract = {In manufacturing, many use cases of Industrie 4.0 require vendor-neutral and machine-interpretable information models to describe, implement and execute resource functions. Such models have been researched under the terms capabilities and skills. Standardization of such models is required, but currently not available. This paper presents a reference model developed jointly by members of various organizations in a working group of the Plattform Industrie 4.0. This model covers definitions of most important aspects of capabilities and skills. It can be seen as a basis for further standardization efforts.}, language = {en} }