@inproceedings{RosbachAmmelingKruegeletal.2025, author = {Rosbach, Emely and Ammeling, Jonas and Kr{\"u}gel, Sebastian and Kießig, Angelika and Fritz, Alexis and Ganz, Jonathan and Puget, Chlo{\´e} and Donovan, Taryn and Klang, Andrea and K{\"o}ller, Maximilian C. and Bolfa, Pompei and Tecilla, Marco and Denk, Daniela and Kiupel, Matti and Paraschou, Georgios and Kok, Mun Keong and Haake, Alexander F. H. and de Krijger, Ronald R. and Sonnen, Andreas F.-P. and Kasantikul, Tanit and Dorrestein, Gerry M. and Smedley, Rebecca C. and Stathonikos, Nikolas and Uhl, Matthias and Bertram, Christof and Riener, Andreas and Aubreville, Marc}, title = {"When Two Wrongs Don't Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology}, pages = {528}, booktitle = {CHI'25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems}, editor = {Yamashita, Naomi and Evers, Vanessa and Yatani, Koji and Ding, Xianghua and Lee, Bongshin and Chetty, Marshini and Toups-Dugas, Phoebe}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-1394-1}, doi = {https://doi.org/10.1145/3706598.3713319}, year = {2025}, abstract = {Artificial intelligence (AI)-based decision support systems hold promise for enhancing diagnostic accuracy and efficiency in computational pathology. However, human-AI collaboration can introduce and amplify cognitive biases, like confirmation bias caused by false confirmation when erroneous human opinions are reinforced by inaccurate AI output. This bias may increase under time pressure, a ubiquitous factor in routine pathology, as it strains practitioners' cognitive resources. We quantified confirmation bias triggered by AI-induced false confirmation and examined the role of time constraints in a web-based experiment, where trained pathology experts (n=28) estimated tumor cell percentages. Our results suggest that AI integration fuels confirmation bias, evidenced by a statistically significant positive linear-mixed-effects model coefficient linking AI recommendations mirroring flawed human judgment and alignment with system advice. Conversely, time pressure appeared to weaken this relationship. These findings highlight potential risks of AI in healthcare and aim to support the safe integration of clinical decision support systems.}, language = {en} } @unpublished{RosbachAmmelingKruegeletal.2024, author = {Rosbach, Emely and Ammeling, Jonas and Kr{\"u}gel, Sebastian and Kießig, Angelika and Fritz, Alexis and Ganz, Jonathan and Puget, Chlo{\´e} and Donovan, Taryn and Klang, Andrea and K{\"o}ller, Maximilian C. and Bolfa, Pompei and Tecilla, Marco and Denk, Daniela and Kiupel, Matti and Paraschou, Georgios and Kok, Mun Keong and Haake, Alexander F. H. and de Krijger, Ronald R. and Sonnen, Andreas F.-P. and Kasantikul, Tanit and Dorrestein, Gerry M. and Smedley, Rebecca C. and Stathonikos, Nikolas and Uhl, Matthias and Bertram, Christof and Riener, Andreas and Aubreville, Marc}, title = {"When TwoWrongs Don't Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2411.01007}, year = {2024}, language = {en} } @unpublished{RosbachGanzAmmelingetal.2024, author = {Rosbach, Emely and Ganz, Jonathan and Ammeling, Jonas and Riener, Andreas and Aubreville, Marc}, title = {Automation Bias in AI-Assisted Medical Decision-Making under Time Pressure in Computational Pathology}, doi = {https://doi.org/10.48550/arXiv.2411.00998}, year = {2024}, language = {en} } @article{MuellerRichterSchaeferetal.2023, author = {Mueller, Juliane and Richter, Monika and Schaefer, Kathrin and Ganz, Jonathan and Lohscheller, J{\"o}rg and Mueller, Steffen}, title = {How to measure children's feet: 3D foot scanning compared with established 2D manual or digital methods}, volume = {16}, pages = {21}, journal = {Journal of Foot and Ankle Research}, publisher = {BioMed Central}, address = {London}, issn = {1757-1146}, doi = {https://doi.org/10.1186/s13047-023-00618-y}, year = {2023}, abstract = {Background In infants and young children, a wide heterogeneity of foot shape is typical. Therefore, children, who are additionally influenced by rapid growth and maturation, are a very special cohort for foot measurements and the footwear industry. The importance of foot measurements for footwear fit, design, as well as clinical applications has been sufficiently described. New measurement techniques (3D foot scanning) allow the assessment of the individual foot shape. However, the validity in comparison to conventional methods remains unclear. Therefore, the purpose of this study was to compare 3D foot scanning with two established measurement methods (2D digital scanning/manual foot measurements). Methods Two hundred seventy seven children (125 m / 152 f; mean ± SD: 8.0 ± 1.5yrs; 130.2 ± 10.7cm; 28.0 ± 7.3kg) were included into the study. After collection of basic data (sex, age (yrs), body height (cm), body weight (kg)) geometry of the right foot was measured in static condition (stance) with three different measurement systems (fixed order): manual foot measurement, 2D foot scanning (2D desk scanner) and 3D foot scanning (hand-held 3D scanner). Main outcomes were foot length, foot width (projected; anatomical; instep), heel width and anatomical foot ball breadth. Analysis of variances for dependent samples was applied to test for differences between foot measurement methods (Post-hoc analysis: Tukey-Kramer-Test; α=0.05). Results Significant differences were found for all outcome measures comparing the three methods (p<0.0001). The span of foot length differences ranged from 3 to 6mm with 2D scans showing the smallest and 3D scans the largest deviations. Foot width measurements in comparison of 3D and 2D scans showed consistently higher values for 3D measurements with the differences ranging from 1mm to 3mm. Conclusions The findings suggests that when comparing foot data, it is important to consider the differences caused by new measurement methods. Differences of about 0.6cm are relevant when measuring foot length, as this is the difference of a complete shoe size (Parisian point). Hence, correction factors may be required to compare the results of different measurements appropriately. The presented results may have relevance in the field of ergonomics (shoe industry) as well as clinical practice.}, language = {en} } @unpublished{AubrevilleStathonikosDonovanetal.2023, author = {Aubreville, Marc and Stathonikos, Nikolas and Donovan, Taryn and Klopfleisch, Robert and Ganz, Jonathan and Ammeling, Jonas and Wilm, Frauke and Veta, Mitko and Jabari, Samir and Eckstein, Markus and Annuscheit, Jonas and Krumnow, Christian and Bozaba, Engin and Cayir, Sercan and Gu, Hongyan and Chen, Xiang and Jahanifar, Mostafa and Shephard, Adam and Kondo, Satoshi and Kasai, Satoshi and Kotte, Sujatha and Saipradeep, Vangala and Lafarge, Maxime W. and Koelzer, Viktor H. and Wang, Ziyue and Zhang, Yongbing and Yang, Sen and Wang, Xiyue and Breininger, Katharina and Bertram, Christof}, title = {Domain generalization across tumor types, laboratories, and species - Insights from the 2022 edition of the Mitosis Domain Generalization Challenge}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2309.15589}, year = {2023}, abstract = {Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert consensus and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an F1 score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, but with only minor changes in the order of participants in the ranking.}, language = {en} } @unpublished{HaghoferParlakBarteletal.2023, author = {Haghofer, Andreas and Parlak, Eda and Bartel, Alexander and Donovan, Taryn and Assenmacher, Charles-Antoine and Bolfa, Pompei and Dark, Michael and Fuchs-Baumgartinger, Andrea and Klang, Andrea and J{\"a}ger, Kathrin and Klopfleisch, Robert and Merz, Sophie and Richter, Barbara and Schulman, F. Yvonne and Ganz, Jonathan and Scharinger, Josef and Aubreville, Marc and Winkler, Stephan M. and Kiupel, Matti and Bertram, Christof}, title = {Nuclear Morphometry using a Deep Learning-based Algorithm has Prognostic Relevance for Canine Cutaneous Mast Cell Tumors}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2309.15031}, year = {2023}, abstract = {Variation in nuclear size and shape is an important criterion of malignancy for many tumor types; however, categorical estimates by pathologists have poor reproducibility. Measurements of nuclear characteristics (morphometry) can improve reproducibility, but manual methods are time consuming. In this study, we evaluated fully automated morphometry using a deep learning-based algorithm in 96 canine cutaneous mast cell tumors with information on patient survival. Algorithmic morphometry was compared with karyomegaly estimates by 11 pathologists, manual nuclear morphometry of 12 cells by 9 pathologists, and the mitotic count as a benchmark. The prognostic value of automated morphometry was high with an area under the ROC curve regarding the tumor-specific survival of 0.943 (95\% CI: 0.889 - 0.996) for the standard deviation (SD) of nuclear area, which was higher than manual morphometry of all pathologists combined (0.868, 95\% CI: 0.737 - 0.991) and the mitotic count (0.885, 95\% CI: 0.765 - 1.00). At the proposed thresholds, the hazard ratio for algorithmic morphometry (SD of nuclear area ≥9.0μm2) was 18.3 (95\% CI: 5.0 - 67.1), for manual morphometry (SD of nuclear area ≥10.9μm2) 9.0 (95\% CI: 6.0 - 13.4), for karyomegaly estimates 7.6 (95\% CI: 5.7 - 10.1), and for the mitotic count 30.5 (95\% CI: 7.8 - 118.0). Inter-rater reproducibility for karyomegaly estimates was fair (κ = 0.226) with highly variable sensitivity/specificity values for the individual pathologists. Reproducibility for manual morphometry (SD of nuclear area) was good (ICC = 0.654). This study supports the use of algorithmic morphometry as a prognostic test to overcome the limitations of estimates and manual measurements.}, language = {en} } @unpublished{GanzMarzahlAmmelingetal.2024, author = {Ganz, Jonathan and Marzahl, Christian and Ammeling, Jonas and Richter, Barbara and Puget, Chlo{\´e} and Denk, Daniela and Demeter, Elena A. and Tabaran, Flaviu A. and Wasinger, Gabriel and Lipnik, Karoline and Tecilla, Marco and Valentine, Matthew J. and Dark, Michael and Abele, Niklas and Bolfa, Pompei and Erber, Ramona and Klopfleisch, Robert and Merz, Sophie and Donovan, Taryn and Jabari, Samir and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {On the Value of PHH3 for Mitotic Figure Detection on H\&E-stained Images}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2406.19899}, year = {2024}, abstract = {The count of mitotic figures (MFs) observed in hematoxylin and eosin (H\&E)-stained slides is an important prognostic marker as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. Deep learning algorithms can standardize this task, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithm's performance. Unlike H\&E, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H\&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H\&E stain alone, the use of this ground truth could potentially introduce noise into the H\&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. We found that the annotators' object-level agreement increased when using PHH3-assisted labeling. Subsequently, MF detectors were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models' performance. Additionally, a novel dual-stain MF detector was developed to investigate the interpretation-shift of PHH3-assisted labels used in H\&E, which clearly outperformed single-stain detectors. However, the PHH3-assisted labels did not have a positive effect on solely H\&E-based models. The high performance of our dual-input detector reveals an information mismatch between the H\&E and PHH3-stained images as the cause of this effect.}, language = {en} } @unpublished{GanzAmmelingRosbachetal.2024, author = {Ganz, Jonathan and Ammeling, Jonas and Rosbach, Emely and Lausser, Ludwig and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2412.06365}, year = {2024}, abstract = {Foundation models (FMs), i.e., models trained on a vast amount of typically unlabeled data, have become popular and available recently for the domain of histopathology. The key idea is to extract semantically rich vectors from any input patch, allowing for the use of simple subsequent classification networks potentially reducing the required amounts of labeled data, and increasing domain robustness. In this work, we investigate to which degree this also holds for mitotic figure classification. Utilizing two popular public mitotic figure datasets, we compared linear probing of five publicly available FMs against models trained on ImageNet and a simple ResNet50 end-to-end-trained baseline. We found that the end-to-end-trained baseline outperformed all FM-based classifiers, regardless of the amount of data provided. Additionally, we did not observe the FM-based classifiers to be more robust against domain shifts, rendering both of the above assumptions incorrect.}, language = {en} } @inproceedings{GanzBertramKlopfleischetal.2022, author = {Ganz, Jonathan and Bertram, Christof and Klopfleisch, Robert and Jabari, Samir and Breininger, Katharina and Aubreville, Marc}, title = {Classification of visibility in multi-stain microscopy images}, booktitle = {Medical Imaging with Deep Learning: MIDL 2022 Short Papers}, url = {https://openreview.net/forum?id=-GsA-mUVmm}, year = {2022}, language = {en} } @unpublished{PugetGanzOstermaieretal.2024, author = {Puget, Chlo{\´e} and Ganz, Jonathan and Ostermaier, Julian and Konrad, Thomas and Parlak, Eda and Bertram, Christof and Kiupel, Matti and Breininger, Katharina and Aubreville, Marc and Klopfleisch, Robert}, title = {Deep Learning model predicts the c-Kit-11 mutational status of canine cutaneous mast cell tumors by HE stained histological slides}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2401.06169}, year = {2024}, abstract = {Numerous prognostic factors are currently assessed histopathologically in biopsies of canine mast cell tumors to evaluate clinical behavior. In addition, PCR analysis of the c-Kit exon 11 mutational status is often performed to evaluate the potential success of a tyrosine kinase inhibitor therapy. This project aimed at training deep learning models (DLMs) to identify the c-Kit-11 mutational status of MCTs solely based on morphology without additional molecular analysis. HE slides of 195 mutated and 173 non-mutated tumors were stained consecutively in two different laboratories and scanned with three different slide scanners. This resulted in six different datasets (stain-scanner variations) of whole slide images. DLMs were trained with single and mixed datasets and their performances was assessed under scanner and staining domain shifts. The DLMs correctly classified HE slides according to their c-Kit 11 mutation status in, on average, 87\% of cases for the best-suited stain-scanner variant. A relevant performance drop could be observed when the stain-scanner combination of the training and test dataset differed. Multi-variant datasets improved the average accuracy but did not reach the maximum accuracy of algorithms trained and tested on the same stain-scanner variant. In summary, DLM-assisted morphological examination of MCTs can predict c-Kit-exon 11 mutational status of MCTs with high accuracy. However, the recognition performance is impeded by a change of scanner or staining protocol. Larger data sets with higher numbers of scans originating from different laboratories and scanners may lead to more robust DLMs to identify c-Kit mutations in HE slides.}, language = {en} } @inproceedings{GanzKirschHoffmannetal.2021, author = {Ganz, Jonathan and Kirsch, Tobias and Hoffmann, Lucas and Maier, Andreas and Breininger, Katharina and Bl{\"u}mcke, Ingmar and Jabari, Samir and Aubreville, Marc}, title = {Automatic and explainable grading of meningiomas from histopathology images}, volume = {2021}, booktitle = {Proceedings of Machine Learning Research: Proceedings of COMPAY 2021}, number = {156}, publisher = {PMLR}, address = {[s. l.]}, url = {https://proceedings.mlr.press/v156/ganz21a.html}, pages = {69 -- 80}, year = {2021}, language = {en} }