TY - INPR A1 - Rosbach, Emely A1 - Ammeling, Jonas A1 - Krügel, Sebastian A1 - Kießig, Angelika A1 - Fritz, Alexis A1 - Ganz, Jonathan A1 - Puget, Chloé A1 - Donovan, Taryn A1 - Klang, Andrea A1 - Köller, Maximilian C. A1 - Bolfa, Pompei A1 - Tecilla, Marco A1 - Denk, Daniela A1 - Kiupel, Matti A1 - Paraschou, Georgios A1 - Kok, Mun Keong A1 - Haake, Alexander F. H. A1 - de Krijger, Ronald R. A1 - Sonnen, Andreas F.-P. A1 - Kasantikul, Tanit A1 - Dorrestein, Gerry M. A1 - Smedley, Rebecca C. A1 - Stathonikos, Nikolas A1 - Uhl, Matthias A1 - Bertram, Christof A1 - Riener, Andreas A1 - Aubreville, Marc T1 - "When TwoWrongs Don’t Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology UR - https://doi.org/10.48550/arXiv.2411.01007 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2411.01007 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Rosbach, Emely A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Riener, Andreas A1 - Aubreville, Marc T1 - Automation Bias in AI-Assisted Medical Decision-Making under Time Pressure in Computational Pathology UR - https://doi.org/10.48550/arXiv.2411.00998 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2411.00998 ER - TY - JOUR A1 - Mueller, Juliane A1 - Richter, Monika A1 - Schaefer, Kathrin A1 - Ganz, Jonathan A1 - Lohscheller, Jörg A1 - Mueller, Steffen T1 - How to measure children’s feet: 3D foot scanning compared with established 2D manual or digital methods JF - Journal of Foot and Ankle Research N2 - 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. UR - https://doi.org/10.1186/s13047-023-00618-y KW - Foot length KW - Foot width KW - Shoe size KW - Shoe industry Y1 - 2023 UR - https://doi.org/10.1186/s13047-023-00618-y UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-37243 SN - 1757-1146 VL - 16 PB - BioMed Central CY - London ER - TY - INPR A1 - Aubreville, Marc A1 - Stathonikos, Nikolas A1 - Donovan, Taryn A1 - Klopfleisch, Robert A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Wilm, Frauke A1 - Veta, Mitko A1 - Jabari, Samir A1 - Eckstein, Markus A1 - Annuscheit, Jonas A1 - Krumnow, Christian A1 - Bozaba, Engin A1 - Cayir, Sercan A1 - Gu, Hongyan A1 - Chen, Xiang A1 - Jahanifar, Mostafa A1 - Shephard, Adam A1 - Kondo, Satoshi A1 - Kasai, Satoshi A1 - Kotte, Sujatha A1 - Saipradeep, Vangala A1 - Lafarge, Maxime W. A1 - Koelzer, Viktor H. A1 - Wang, Ziyue A1 - Zhang, Yongbing A1 - Yang, Sen A1 - Wang, Xiyue A1 - Breininger, Katharina A1 - Bertram, Christof T1 - Domain generalization across tumor types, laboratories, and species – Insights from the 2022 edition of the Mitosis Domain Generalization Challenge N2 - 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. UR - https://doi.org/10.48550/arXiv.2309.15589 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2309.15589 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41514 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Haghofer, Andreas A1 - Parlak, Eda A1 - Bartel, Alexander A1 - Donovan, Taryn A1 - Assenmacher, Charles-Antoine A1 - Bolfa, Pompei A1 - Dark, Michael A1 - Fuchs-Baumgartinger, Andrea A1 - Klang, Andrea A1 - Jäger, Kathrin A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Richter, Barbara A1 - Schulman, F. Yvonne A1 - Ganz, Jonathan A1 - Scharinger, Josef A1 - Aubreville, Marc A1 - Winkler, Stephan M. A1 - Kiupel, Matti A1 - Bertram, Christof T1 - Nuclear Morphometry using a Deep Learning-based Algorithm has Prognostic Relevance for Canine Cutaneous Mast Cell Tumors N2 - 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. UR - https://doi.org/10.48550/arXiv.2309.15031 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2309.15031 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41401 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Ganz, Jonathan A1 - Marzahl, Christian A1 - Ammeling, Jonas 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 - On the Value of PHH3 for Mitotic Figure Detection on H&E-stained Images 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. 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. UR - https://doi.org/10.48550/arXiv.2406.19899 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2406.19899 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-50155 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification N2 - 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. UR - https://doi.org/10.48550/arXiv.2412.06365 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2412.06365 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59672 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Ganz, Jonathan A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Jabari, Samir A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Classification of visibility in multi-stain microscopy images T2 - Medical Imaging with Deep Learning: MIDL 2022 Short Papers KW - mitotic figure classification KW - digital pathology KW - deep learning KW - dual input networks KW - attention KW - immunohistochemical staining Y1 - 2022 UR - https://openreview.net/forum?id=-GsA-mUVmm ER - 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 - Ganz, Jonathan A1 - Kirsch, Tobias A1 - Hoffmann, Lucas A1 - Maier, Andreas A1 - Breininger, Katharina A1 - Blümcke, Ingmar A1 - Jabari, Samir A1 - Aubreville, Marc T1 - Automatic and explainable grading of meningiomas from histopathology images T2 - Proceedings of Machine Learning Research: Proceedings of COMPAY 2021 KW - automatic tumor grading KW - meningioma KW - known operator learning KW - deep learning Y1 - 2021 UR - https://proceedings.mlr.press/v156/ganz21a.html VL - 2021 IS - 156 SP - 69 EP - 80 PB - PMLR CY - [s. l.] 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 - 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 - 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 - 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 - Ganz, Jonathan A1 - Lipnik, Karoline A1 - Ammeling, Jonas A1 - Richter, Barbara A1 - Puget, Chloé A1 - Parlak, Eda A1 - Diehl, Laura A1 - Klopfleisch, Robert A1 - Donovan, Taryn A1 - Kiupel, Matti A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Deep Learning-based Automatic Assessment of AgNOR-scores in Histopathology Images T2 - Bildverarbeitung für die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, Braunschweig, July 2-4, 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_49 Y1 - 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_49 SN - 978-3-658-41657-7 SN - 978-3-658-41656-0 SP - 226 EP - 231 PB - Springer Vieweg CY - Wiesbaden ER - TY - JOUR A1 - Aubreville, Marc A1 - Stathonikos, Nikolas A1 - Donovan, Taryn A1 - Klopfleisch, Robert A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Wilm, Frauke A1 - Veta, Mitko A1 - Jabari, Samir A1 - Eckstein, Markus A1 - Annuscheit, Jonas A1 - Krumnow, Christian A1 - Bozaba, Engin A1 - Cayir, Sercan A1 - Gu, Hongyan A1 - Chen, Xiang A1 - Jahanifar, Mostafa A1 - Shephard, Adam A1 - Kondo, Satoshi A1 - Kasai, Satoshi A1 - Kotte, Sujatha A1 - Saipradeep, Vangala A1 - Lafarge, Maxime W. A1 - Koelzer, Viktor H. A1 - Wang, Ziyue A1 - Zhang, Yongbing A1 - Yang, Sen A1 - Wang, Xiyue A1 - Breininger, Katharina A1 - Bertram, Christof T1 - Domain generalization across tumor types, laboratories, and species — Insights from the 2022 edition of the Mitosis Domain Generalization Challenge JF - Medical Image Analysis N2 - 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. UR - https://doi.org/10.1016/j.media.2024.103155 Y1 - 2024 UR - https://doi.org/10.1016/j.media.2024.103155 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58479 SN - 1361-8423 VL - 2024 IS - 94 PB - Elsevier CY - Amsterdam ER - TY - JOUR 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 JF - Scientific Reports 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/10.1038/s41598-024-77244-6 Y1 - 2024 UR - https://doi.org/10.1038/s41598-024-77244-6 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53559 SN - 2045-2322 VL - 14 IS - 1 PB - Springer Nature CY - London ER - TY - JOUR A1 - Haghofer, Andreas A1 - Parlak, Eda A1 - Bartel, Alexander A1 - Donovan, Taryn A1 - Assenmacher, Charles-Antoine A1 - Bolfa, Pompei A1 - Dark, Michael A1 - Fuchs-Baumgartinger, Andrea A1 - Klang, Andrea A1 - Jäger, Kathrin A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Richter, Barbara A1 - Schulman, F. Yvonne A1 - Janout, Hannah A1 - Ganz, Jonathan A1 - Scharinger, Josef A1 - Aubreville, Marc A1 - Winkler, Stephan M. A1 - Kiupel, Matti A1 - Bertram, Christof T1 - Nuclear pleomorphism in canine cutaneous mast cell tumors: Comparison of reproducibility and prognostic relevance between estimates, manual morphometry, and algorithmic morphometry JF - Veterinary Pathology N2 - 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. UR - https://doi.org/10.1177/03009858241295399 Y1 - 2024 UR - https://doi.org/10.1177/03009858241295399 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53661 SN - 1544-2217 SN - 0300-9858 VL - 62 IS - 2 SP - 161 EP - 177 PB - Sage CY - London ER - TY - JOUR A1 - Glahn, Imaine A1 - Haghofer, Andreas A1 - Donovan, Taryn A1 - Degasperi, Brigitte A1 - Bartel, Alexander A1 - Kreilmeier-Berger, Theresa A1 - Hyndman, Philip S. A1 - Janout, Hannah A1 - Assenmacher, Charles-Antoine A1 - Bartenschlager, Florian A1 - Bolfa, Pompei A1 - Dark, Michael A1 - Klang, Andrea A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Richter, Barbara A1 - Schulman, F. Yvonne A1 - Ganz, Jonathan A1 - Scharinger, Josef A1 - Aubreville, Marc A1 - Winkler, Stephan M. A1 - Bertram, Christof T1 - Automated Nuclear Morphometry: A Deep Learning Approach for Prognostication in Canine Pulmonary Carcinoma to Enhance Reproducibility JF - Veterinary Sciences N2 - 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. UR - https://doi.org/10.3390/vetsci11060278 Y1 - 2024 UR - https://doi.org/10.3390/vetsci11060278 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-48612 SN - 2306-7381 VL - 11 IS - 6 PB - MDPI CY - Basel ER - TY - JOUR A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Jabari, Samir A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Re-identification from histopathology images JF - Medical Image Analysis N2 - 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. UR - https://doi.org/10.1016/j.media.2024.103335 Y1 - 2024 UR - https://doi.org/10.1016/j.media.2024.103335 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53025 SN - 1361-8423 SN - 1361-8415 VL - 2025 IS - 99 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Aubreville, Marc A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Gehrke, Thomas A1 - Scherzad, Agmal A1 - Hackenberg, Stephan A1 - Goncalves, Miguel T1 - Prediction of tumor board procedural recommendations using large language models JF - European Archives of Oto-Rhino-Laryngology UR - https://doi.org/10.1007/s00405-024-08947-9 Y1 - 2024 UR - https://doi.org/10.1007/s00405-024-08947-9 SN - 1434-4726 SN - 0937-4477 VL - 282 IS - 3 SP - 1619 EP - 1629 PB - Springer CY - Berlin ER - TY - CHAP A1 - Ammeling, Jonas A1 - Hecker, Moritz A1 - Ganz, Jonathan A1 - Donovan, Taryn A1 - Klopfleisch, Robert A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Maier, Andreas ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Automated Mitotic Index Calculation via Deep Learning and Immunohistochemistry T2 - Bildverarbeitung für die Medizin 2024: Proceedings, German Conference on Medical Image Computing, Erlangen, March 10–12, 2024 UR - https://doi.org/10.1007/978-3-658-44037-4_37 Y1 - 2024 UR - https://doi.org/10.1007/978-3-658-44037-4_37 SN - 978-3-658-44037-4 SP - 123 EP - 128 PB - Springer Vieweg CY - Wiesbaden ER - TY - CHAP A1 - Eisenmann, Matthias A1 - Reinke, Annika A1 - Weru, Vivienn A1 - Tizabi, Minu Dietlinde A1 - Isensee, Fabian A1 - Adler, Tim J. A1 - Ali, Sharib A1 - Andrearczyk, Vincent A1 - Aubreville, Marc A1 - Baid, Ujjwal A1 - Bakas, Spyridon A1 - Balu, Niranjan A1 - Bano, Sophia A1 - Bernal, Jorge A1 - Bodenstedt, Sebastian A1 - Casella, Alessandro A1 - Cheplygina, Veronika A1 - Daum, Marie A1 - De Bruijne, Marleen A1 - Depeursinge, Adrien A1 - Dorent, Reuben A1 - Egger, Jan A1 - Ellis, David G. A1 - Engelhardt, Sandy A1 - Ganz, Melanie A1 - Ghatwary, Noha M. A1 - Girard, Gabriel A1 - Godau, Patrick A1 - Gupta, Anubha A1 - Hansen, Lasse A1 - Harada, Kanako A1 - Heinrich, Mattias A1 - Heller, Nicholas A1 - Hering, Alessa A1 - Huaulmé, Arnoud A1 - Jannin, Pierre A1 - Kavur, A. Emre A1 - Kodym, Oldrich A1 - Kozubek, Michal A1 - Li, Jianning A1 - Li, Hongwei A1 - Ma, Jun A1 - Martín-Isla, Carlos A1 - Menze, Bjoern H. A1 - Noble, Alison A1 - Oreiller, Valentin A1 - Padoy, Nicolas A1 - Pati, Sarthak A1 - Payette, Kelly A1 - Rädsch, Tim A1 - Rafael-Patiño, Jonathan A1 - Bawa, Vivek Singh A1 - Speidel, Stefanie A1 - Sudre, Carole H. A1 - Van Wijnen, Kimberlin M. H. A1 - Wagner, M. A1 - Wei, D. A1 - Yamlahi, Amine A1 - Yap, Moi Hoon A1 - Yuan, C. A1 - Zenk, Maximilian A1 - Zia, A. A1 - Zimmerer, David A1 - Aydogan, Dogu Baran A1 - Bhattarai, B. A1 - Bloch, Louise A1 - Brüngel, Raphael A1 - Cho, J. A1 - Choi, C. A1 - Dou, Q. A1 - Ezhov, Ivan A1 - Friedrich, Christoph M. A1 - Fuller, C. A1 - Gaire, Rebati Raman A1 - Galdran, Adrian A1 - García-Faura, Álvaro A1 - Grammatikopoulou, Maria A1 - Hong, S. A1 - Jahanifar, Mostafa A1 - Jang, I. A1 - Kadkhodamohammadi, Abdolrahim A1 - Kang, I. A1 - Kofler, Florian A1 - Kondo, Satoshi A1 - Kuijf, Hugo Jaco A1 - Li, M. A1 - Luu, M. A1 - Martinčič, Tomaz A1 - Morais, P. A1 - Naser, M. A. A1 - Oliveira, B. A1 - Owen, D. A1 - Pang, S. A1 - Park, Jinah A1 - Park, S. A1 - Płotka, S. A1 - Puybareau, Élodie A1 - Rajpoot, Nasir M. A1 - Ryu, K. A1 - Saeed, N. A1 - Shephard, Adam A1 - Shi, P. A1 - Štepec, Dejan A1 - Subedi, Ronast A1 - Tochon, Guillaume A1 - Torres, Helena R. A1 - Urien, Hélène A1 - Vilaça, João L. A1 - Wahid, Kareem A. A1 - Wang, H. A1 - Wang, J. A1 - Wang, L. A1 - Wang, Xiyue A1 - Wiestler, Benedikt A1 - Wodzinski, Marek A1 - Xia, F. A1 - Xie, J. A1 - Xiong, Z. A1 - Yang, Sen A1 - Yang, Y. A1 - Zhao, Z. A1 - Maier-Hein, Klaus H. A1 - Jäger, Paul F. A1 - Kopp-Schneider, Annette A1 - Maier-Hein, Lena T1 - Why is the Winner the Best? T2 - Proceedings: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition UR - https://doi.org/10.1109/CVPR52729.2023.01911 KW - Medical and biological vision KW - cell microscopy Y1 - 2023 UR - https://doi.org/10.1109/CVPR52729.2023.01911 SN - 979-8-3503-0129-8 SN - 2575-7075 SP - 19955 EP - 19967 PB - IEEE CY - Los Alamitos ER - TY - CHAP A1 - Ammeling, Jonas A1 - Manger, Carina A1 - Kwaka, Elias A1 - Krügel, Sebastian A1 - Uhl, Matthias A1 - Kießig, Angelika A1 - Fritz, Alexis A1 - Ganz, Jonathan A1 - Riener, Andreas A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Stolze, Markus ED - Loch, Frieder ED - Baldauf, Matthias ED - Alt, Florian ED - Schneegass, Christina ED - Kosch, Thomas ED - Hirzle, Teresa ED - Sadeghian, Shadan ED - Draxler, Fiona ED - Bektas, Kenan ED - Lohan, Katrin ED - Knierim, Pascal T1 - Appealing but Potentially Biasing - Investigation of the Visual Representation of Segmentation Predictions by AI Recommender Systems for Medical Decision Making T2 - Mensch und Computer 2023: Building Bridges: Tagungsband (Proceedings) UR - https://doi.org/10.1145/3603555.3608561 Y1 - 2023 UR - https://doi.org/10.1145/3603555.3608561 SN - 979-8-4007-0771-1 SP - 330 EP - 335 PB - ACM CY - New York ER - TY - CHAP A1 - Ammeling, Jonas A1 - Wilm, Frauke A1 - Ganz, Jonathan A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Sheng, Bin ED - Aubreville, Marc T1 - Reference Algorithms for the Mitosis Domain Generalization (MIDOG) 2022 Challenge T2 - Mitosis Domain Generalization and Diabetic Retinopathy Analysis UR - https://doi.org/10.1007/978-3-031-33658-4_19 Y1 - 2023 UR - https://doi.org/10.1007/978-3-031-33658-4_19 SN - 978-3-031-33658-4 SN - 978-3-031-33657-7 SP - 201 EP - 205 PB - Springer CY - Cham ER - TY - CHAP A1 - Aubreville, Marc A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Donovan, Taryn A1 - Fick, Rutger H. J. A1 - Breininger, Katharina A1 - Bertram, Christof ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Deep Learning-based Subtyping of Atypical and Normal Mitoses using a Hierarchical Anchor-free Object Detector T2 - Bildverarbeitung für die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, Braunschweig, July 2-4, 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_40 Y1 - 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_40 SN - 978-3-658-41657-7 SN - 978-3-658-41656-0 SP - 189 EP - 195 PB - Springer Vieweg CY - Wiesbaden ER - TY - JOUR A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Wilm, Frauke A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Investigation of Class Separability within Object Detection Models in Histopathology JF - IEEE Transactions on Medical Imaging UR - https://doi.org/10.1109/TMI.2025.3560134 Y1 - 2025 UR - https://doi.org/10.1109/TMI.2025.3560134 SN - 0278-0062 SN - 1558-254X VL - 44 IS - 8 SP - 3162 EP - 3174 PB - IEEE CY - New York ER - TY - JOUR A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Benchmarking Foundation Models for Mitotic Figure Classification JF - Machine Learning for Biomedical Imaging N2 - The performance of deep learning models is known to scale with data quantity and diversity. In pathology, as in many other medical imaging domains, the availability of labeled images for a specific task is often limited. Self-supervised learning techniques have enabled the use of vast amounts of unlabeled data to train large-scale neural networks, i.e., foundation models, that can address the limited data problem by providing semantically rich feature vectors that can generalize well to new tasks with minimal training effort increasing model performance and robustness. In this work, we investigate the use of foundation models for mitotic figure classification. The mitotic count, which can be derived from this classification task, is an independent prognostic marker for specific tumors and part of certain tumor grading systems. In particular, we investigate the data scaling laws on multiple current foundation models and evaluate their robustness to unseen tumor domains. Next to the commonly used linear probing paradigm, we also adapt the models using low-rank adaptation (LoRA) of their attention mechanisms. We compare all models against end-to-end-trained baselines, both CNNs and Vision Transformers. Our results demonstrate that LoRA-adapted foundation models provide superior performance to those adapted with standard linear probing, reaching performance levels close to 100 % data availability with only 10 % of training data. Furthermore, LoRA-adaptation of the most recent foundation models almost closes the out-of-domain performance gap when evaluated on unseen tumor domains. However, full fine-tuning of traditional architectures still yields competitive performance. UR - https://doi.org/10.59275/j.melba.2026-a3eb Y1 - 2026 UR - https://doi.org/10.59275/j.melba.2026-a3eb UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-66220 SN - 2766-905X VL - 3 IS - MELBA–BVM 2025 Special Issue SP - 38 EP - 55 PB - Melba editors CY - [s. l.] ER - TY - CHAP A1 - Rosbach, Emely A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Riener, Andreas A1 - Aubreville, Marc ED - Palm, Christoph ED - Breininger, Katharina ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Tolxdorff, Thomas T1 - Automation Bias in AI-assisted Medical Decision-making under Time Pressure in Computational Pathology T2 - Bildverarbeitung für die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09–11, 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_27 Y1 - 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_27 SN - 978-3-658-47422-5 SP - 129 EP - 134 PB - Springer Vieweg CY - Wiesbaden ER - TY - CHAP A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Palm, Christoph ED - Breininger, Katharina ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Tolxdorff, Thomas T1 - Is Self-supervision Enough? BT - Benchmarking Foundation Models Against End-to-end Training for Mitotic Figure Classification T2 - Bildverarbeitung für die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09–11, 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_15 Y1 - 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_15 SN - 978-3-658-47422-5 SP - 63 EP - 68 PB - Springer Vieweg CY - Wiesbaden ER - TY - INPR A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Benchmarking Foundation Models for Mitotic Figure Classification UR - https://doi.org/10.48550/arXiv.2508.04441 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2508.04441 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Puget, Chloé A1 - Ganz, Jonathan A1 - Bertram, Christof A1 - Conrad, Thomas A1 - Baeblich, Malte A1 - Voss, Anne A1 - Landmann, Katharina A1 - Haake, Alexander F. H. A1 - Spree, Andreas A1 - Hartung, Svenja A1 - Aeschlimann, Leonore A1 - Soto, Sara A1 - de Brot, Simone A1 - Dettwiler, Martina A1 - Aupperle-Lellbach, Heike A1 - Bolfa, Pompei A1 - Bartel, Alexander A1 - Kiupel, Matti A1 - Breininger, Katharina A1 - Aubreville, Marc A1 - Klopfleisch, Robert T1 - Artificial intelligence predicts c-KIT exon 11 genotype by phenotype in canine cutaneous mast cell tumors: Can human observers learn it? JF - Veterinary Pathology N2 - Canine cutaneous mast cell tumors (ccMCTs) are frequent neoplasms with variable biological behaviors. Internal tandem duplication mutations in c-KIT exon 11 (c-KIT-11-ITD) are associated with poor prognosis but predict therapeutic response to tyrosine kinase inhibitors. In a previous work, deep learning algorithms managed to predict the presence of c-KIT-11-ITD on digitalized hematoxylin and eosin-stained histological slides (whole-slide images, WSIs) in up to 87% of cases, suggesting the existence of morphological features characterizing ccMCTs carrying c-KIT-11-ITD. This 3-stage blinded study aimed to identify morphological features indicative of c-KIT-11-ITD and to evaluate the ability of human observers to learn this task. 17 untrained pathologists first classified 8 WSIs and 200 image patches (highly relevant for algorithmic classification) of ccMCTs as either positive or negative for c-KIT-11-ITD. Second, they self-trained to recognize c-KIT-11-ITD by looking at the same WSIs and patches correctly sorted. Third, pathologists classified 15 new WSIs and 200 new patches according to c-KIT-11-ITD status. In addition, participants reported microscopic features they considered relevant for their decision. Without training, participants correctly classified the c-KIT-11-ITD status of 63%–88% of WSIs and 43%–55% of patches. With self-training, 25%–38% of WSIs and 55%–56% of patches were correctly classified. High cellular pleomorphism, anisokaryosis, and sparse cytoplasmic granulation were commonly suggested as features associated with c-KIT-11-ITD-positive ccMCTs, none of which showed reliable predictivity in a follow-up study. The results indicate that transfer of algorithmic skills to the human observer is difficult. A c-KIT-11-ITD-specific morphological feature remains to be extracted from the artificial intelligence model. UR - https://doi.org/10.1177/03009858251380284 Y1 - 2025 UR - https://doi.org/10.1177/03009858251380284 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-63841 SN - 1544-2217 VL - 63 IS - 2 SP - 369 EP - 379 PB - Sage CY - London ER - TY - JOUR A1 - Rosbach, Emely A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Bertram, Christof A1 - Conrad, Thomas A1 - Riener, Andreas A1 - Aubreville, Marc T1 - Stuck on Suggestions: Automation Bias, the Anchoring Effect, and the Factors That Shape Them in Computational Pathology JF - Machine Learning for Biomedical Imaging N2 - Artificial intelligence (AI)-driven clinical decision support systems (CDSS) hold promise to improve diagnostic accuracy and efficiency in computational pathology. However, collaboration between human experts and AI may give rise to cognitive biases, such as automation and anchoring bias, wherein users may be inclined to blindly adopt system recommendations or be disproportionately influenced by the presence of AI predictions, even when they are inaccurate. These biases may be exacerbated under time pressure, pervasive in routine pathology diagnostics, or shaped by individual user characteristics. To investigate these effects, we conducted a web-based experiment in which trained pathology experts (n = 28) estimated tumor cell percentages twice: once independently and once with the aid of an AI. A subset of the estimates in each condition was performed under time constraints. Our findings indicate that AI integration generally enhances diagnostic performance. However, it also introduced a 7% automation bias rate, quantified as the number of accepted negative consultations, where a previously correct independent assessment gets overturned by inaccurate AI guidance. While time pressure did not increase the frequency of automation bias occurrence, it appeared to intensify its severity, as evidenced by a performance decline linked to increased automation reliance under cognitive load. A linear mixed-effects model (LMM) analysis, simulating weighted averaging, revealed a statistically significant positive coefficient for AI advice, indicating a moderate degree of anchoring on system output. This effect was further intensified under time pressure, suggesting that anchoring bias may become more pronounced when cognitive resources are limited. A secondary LMM evaluation assessing automation reliance, used as a proxy for both automation and anchoring bias, demonstrated that professional experience and self-efficacy were associated with reduced dependence on system support, whereas higher confidence during AI-assisted decision-making was linked to increased automation reliance. Together, these findings underscore the dual nature of AI integration in clinical workflows, offering performance benefits while also introducing risks of cognitive bias–driven diagnostic errors. As an initial investigation focused on a single medical specialty and diagnostic task, this study aims to lay the groundwork for future research to explore these phenomena across diverse clinical contexts, ultimately supporting the establishment of appropriate reliance on automated systems and the safe, effective integration of human–AI collaboration in medical decision-making. UR - https://doi.org/10.59275/j.melba.2026-87b1 Y1 - 2026 UR - https://doi.org/10.59275/j.melba.2026-87b1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-67787 SN - 2766-905X VL - 3 IS - MELBA–BVM 2025 Special Issue SP - 126 EP - 147 PB - Melba editors CY - [s. l.] ER - TY - JOUR A1 - Puget, Chloé A1 - Ganz, Jonathan A1 - Ostermaier, Julian A1 - Conrad, Thomas A1 - Parlak, Eda A1 - Bertram, Christof A1 - Kiupel, Matti A1 - Breininger, Katharina A1 - Aubreville, Marc A1 - Klopfleisch, Robert T1 - Artificial intelligence can be trained to predict c-KIT-11 mutational status of canine mast cell tumors from hematoxylin and eosin-stained histological slides JF - Veterinary Pathology N2 - Numerous prognostic factors are currently assessed histologically and immunohistochemically in canine mast cell tumors (MCTs) to evaluate clinical behavior. In addition, polymerase chain reaction (PCR) is often performed to detect internal tandem duplication (ITD) mutations in exon 11 of the c-KIT gene ( c-KIT-11-ITD) to predict the therapeutic response to tyrosine kinase inhibitors. This project aimed at training deep learning models (DLMs) to identify MCTs with c-KIT-11-ITD solely based on morphology. Hematoxylin and eosin (HE) stained slides of 368 cutaneous, subcutaneous, and mucocutaneous MCTs (195 with ITD and 173 without) were stained consecutively in 2 different laboratories and scanned with 3 different slide scanners. This resulted in 6 data sets (stain-scanner variations representing diagnostic institutions) of whole-slide images. DLMs were trained with single and mixed data sets and their performances were assessed under stain-scanner variations (domain shifts). The DLM correctly classified HE slides according to their c-KIT-11-ITD status in up to 87% of cases with a 0.90 sensitivity and a 0.83 specificity. A relevant performance drop could be observed when the stain-scanner combination of training and test data set differed. Multi-institutional data sets improved the average accuracy but did not reach the maximum accuracy of algorithms trained and tested on the same stain-scanner variant (ie, intra-institutional). In summary, DLM-based morphological examination can predict c-KIT-11-ITD with high accuracy in canine MCTs in HE slides. However, staining protocol and scanner type influence accuracy. Larger data sets of scans from different laboratories and scanners may lead to more robust DLMs to identify c- KIT mutations in HE slides. UR - https://doi.org/10.1177/03009858241286806 Y1 - 2024 UR - https://doi.org/10.1177/03009858241286806 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53323 SN - 1544-2217 SN - 0300-9858 VL - 62 IS - 2 SP - 152 EP - 160 PB - Sage CY - London ER - TY - JOUR A1 - Aubreville, Marc A1 - Wilm, Frauke A1 - Stathonikos, Nikolas A1 - Breininger, Katharina A1 - Donovan, Taryn A1 - Jabari, Samir A1 - Veta, Mitko A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - van Diest, Paul J A1 - Klopfleisch, Robert A1 - Bertram, Christof T1 - A comprehensive multi-domain dataset for mitotic figure detection JF - Scientific Data N2 - The prognostic value of mitotic figures in tumor tissue is well-established for many tumor types and automating this task is of high research interest. However, especially deep learning-based methods face performance deterioration in the presence of domain shifts, which may arise from different tumor types, slide preparation and digitization devices. We introduce the MIDOG++ dataset, an extension of the MIDOG 2021 and 2022 challenge datasets. We provide region of interest images from 503 histological specimens of seven different tumor types with variable morphology with in total labels for 11,937 mitotic figures: breast carcinoma, lung carcinoma, lymphosarcoma, neuroendocrine tumor, cutaneous mast cell tumor, cutaneous melanoma, and (sub)cutaneous soft tissue sarcoma. The specimens were processed in several laboratories utilizing diverse scanners. We evaluated the extent of the domain shift by using state-of-the-art approaches, observing notable differences in single-domain training. In a leave-one-domain-out setting, generalizability improved considerably. This mitotic figure dataset is the first that incorporates a wide domain shift based on different tumor types, laboratories, whole slide image scanners, and species. UR - https://doi.org/10.1038/s41597-023-02327-4 Y1 - 2023 UR - https://doi.org/10.1038/s41597-023-02327-4 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-40068 SN - 2052-4463 N1 - Author Correction verfügbar unter https://doi.org/10.1038/s41597-024-03548-x VL - 10 PB - Springer CY - London ER - TY - INPR A1 - Aubreville, Marc A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Kaltenecker, Christopher A1 - Bertram, Christof T1 - Model-based Cleaning of the QUILT-1M Pathology Dataset for Text-Conditional Image Synthesis N2 - The QUILT-1M dataset is the first openly available dataset containing images harvested from various online sources. While it provides a huge data variety, the image quality and composition is highly heterogeneous, impacting its utility for text-conditional image synthesis. We propose an automatic pipeline that provides predictions of the most common impurities within the images, e.g., visibility of narrators, desktop environment and pathology software, or text within the image. Additionally, we propose to use semantic alignment filtering of the image-text pairs. Our findings demonstrate that by rigorously filtering the dataset, there is a substantial enhancement of image fidelity in text-to-image tasks. UR - https://doi.org/10.48550/arXiv.2404.07676 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2404.07676 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-48648 PB - arXiv CY - Ithaca ER -