@article{PugetGanzBertrametal.2025, author = {Puget, Chlo{\´e} and Ganz, Jonathan and Bertram, Christof and Conrad, Thomas and Baeblich, Malte and Voss, Anne and Landmann, Katharina and Haake, Alexander F. H. and Spree, Andreas and Hartung, Svenja and Aeschlimann, Leonore and Soto, Sara and de Brot, Simone and Dettwiler, Martina and Aupperle-Lellbach, Heike and Bolfa, Pompei and Bartel, Alexander and Kiupel, Matti and Breininger, Katharina and Aubreville, Marc and Klopfleisch, Robert}, title = {Artificial intelligence predicts c-KIT exon 11 genotype by phenotype in canine cutaneous mast cell tumors: Can human observers learn it?}, volume = {63}, journal = {Veterinary Pathology}, number = {2}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858251380284}, pages = {369 -- 379}, year = {2025}, abstract = {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.}, 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{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} } @article{BertramAubrevilleDonovanetal.2021, author = {Bertram, Christof and Aubreville, Marc and Donovan, Taryn and Bartel, Alexander and Wilm, Frauke and Marzahl, Christian and Assenmacher, Charles-Antoine and Becker, Kathrin and Bennett, Mark and Corner, Sarah M. and Cossic, Brieuc and Denk, Daniela and Dettwiler, Martina and Garcia Gonzalez, Beatriz and Gurtner, Corinne and Haverkamp, Ann-Kathrin and Heier, Annabelle and Lehmbecker, Annika and Merz, Sophie and Noland, Erica L. and Plog, Stephanie and Schmidt, Anja and Sebastian, Franziska and Sledge, Dodd G. and Smedley, Rebecca C. and Tecilla, Marco and Thaiwong, Tuddow and Fuchs-Baumgartinger, Andrea and Meuten, Donald J. and Breininger, Katharina and Kiupel, Matti and Maier, Andreas and Klopfleisch, Robert}, title = {Computer-assisted mitotic count using a deep learning-based algorithm improves interobserver reproducibility and accuracy}, volume = {59}, journal = {Veterinary Pathology}, number = {2}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858211067478}, pages = {211 -- 226}, year = {2021}, abstract = {The mitotic count (MC) is an important histological parameter for prognostication of malignant neoplasms. However, it has inter- and intraobserver discrepancies due to difficulties in selecting the region of interest (MC-ROI) and in identifying or classifying mitotic figures (MFs). Recent progress in the field of artificial intelligence has allowed the development of high-performance algorithms that may improve standardization of the MC. As algorithmic predictions are not flawless, computer-assisted review by pathologists may ensure reliability. In the present study, we compared partial (MC-ROI preselection) and full (additional visualization of MF candidates and display of algorithmic confidence values) computer-assisted MC analysis to the routine (unaided) MC analysis by 23 pathologists for whole-slide images of 50 canine cutaneous mast cell tumors (ccMCTs). Algorithmic predictions aimed to assist pathologists in detecting mitotic hotspot locations, reducing omission of MFs, and improving classification against imposters. The interobserver consistency for the MC significantly increased with computer assistance (interobserver correlation coefficient, ICC = 0.92) compared to the unaided approach (ICC = 0.70). Classification into prognostic stratifications had a higher accuracy with computer assistance. The algorithmically preselected hotspot MC-ROIs had a consistently higher MCs than the manually selected MC-ROIs. Compared to a ground truth (developed with immunohistochemistry for phosphohistone H3), pathologist performance in detecting individual MF was augmented when using computer assistance (F1-score of 0.68 increased to 0.79) with a reduction in false negatives by 38\%. The results of this study demonstrate that computer assistance may lead to more reproducible and accurate MCs in ccMCTs.}, language = {en} } @inproceedings{MarzahlWilmTharunetal.2021, author = {Marzahl, Christian and Wilm, Frauke and Tharun, Lars and Perner, Sven and Kr{\"o}ger, Christine and Voigt, J{\"o}rn and Klopfleisch, Robert and Maier, Andreas and Aubreville, Marc and Breininger, Katharina}, title = {Robust quad-tree based registration on whole slide images}, booktitle = {Proceedings of Machine Learning Research: Proceedings of COMPAY 2021}, number = {156}, publisher = {PMLR}, address = {[s. l.]}, url = {https://proceedings.mlr.press/v156/marzahl21a.html}, pages = {181 -- 190}, year = {2021}, 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} } @unpublished{GanzMarzahlAmmelingetal.2024, author = {Ganz, Jonathan and Marzahl, Christian and Ammeling, Jonas and Rosbach, Emely and Richter, Barbara and Puget, Chlo{\´e} and Denk, Daniela and Demeter, Elena A. and Tabaran, Flaviu A. and Wasinger, Gabriel and Lipnik, Karoline and Tecilla, Marco and Valentine, Matthew J. and Dark, Michael and Abele, Niklas and Bolfa, Pompei and Erber, Ramona and Klopfleisch, Robert and Merz, Sophie and Donovan, Taryn and Jabari, Samir and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Information Mismatch in PHH3-Assisted Mitosis Annotation Leads to Interpretation Shifts in H\&E Slide Analysis}, titleParent = {Research Square}, publisher = {Research Square}, address = {Durham}, doi = {https://doi.org/10.21203/rs.3.rs-4900505/v1}, year = {2024}, abstract = {The count of mitotic figures (MFs) observed in hematoxylin and eosin (H\&E)-stained slides is an important prognostic marker, as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. In a computer-aided setting, deep learning algorithms can help to mitigate this, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithms' performance. Unlike H\&E, where identification of MFs is based mainly on morphological features, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H\&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H\&E staining alone, the use of this ground truth could potentially introduce an interpretation shift and even label noise into the H\&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. Subsequently, MF detectors, including a novel dual-stain detector, were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models' performance. We found that the annotators' object-level agreement significantly increased when using PHH3-assisted labeling (F1: 0.53 to 0.74). However, this enhancement in label consistency did not translate to improved performance for H\&E-based detectors, neither during the training phase nor the evaluation phase. Conversely, the dual-stain detector was able to benefit from the higher consistency. This reveals an information mismatch between the H\&E and PHH3-stained images as the cause of this effect, which renders PHH3-assisted annotations not well-aligned for use with H\&E-based detectors. Based on our findings, we propose an improved PHH3-assisted labeling procedure.}, language = {en} } @unpublished{AmmelingHeckerGanzetal.2023, author = {Ammeling, Jonas and Hecker, Moritz and Ganz, Jonathan and Donovan, Taryn and Klopfleisch, Robert and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Automated Volume Corrected Mitotic Index Calculation Through Annotation-Free Deep Learning using Immunohistochemistry as Reference Standard}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2311.08949}, year = {2023}, abstract = {The volume-corrected mitotic index (M/V-Index) was shown to provide prognostic value in invasive breast carcinomas. However, despite its prognostic significance, it is not established as the standard method for assessing aggressive biological behaviour, due to the high additional workload associated with determining the epithelial proportion. In this work, we show that using a deep learning pipeline solely trained with an annotation-free, immunohistochemistry-based approach, provides accurate estimations of epithelial segmentation in canine breast carcinomas. We compare our automatic framework with the manually annotated M/V-Index in a study with three board-certified pathologists. Our results indicate that the deep learning-based pipeline shows expert-level performance, while providing time efficiency and reproducibility.}, language = {en} } @unpublished{WilmFragosoGarciaBertrametal.2022, author = {Wilm, Frauke and Fragoso-Garcia, Marco and Bertram, Christof and Stathonikos, Nikolas and {\"O}ttl, Mathias and Qiu, Jingna and Klopfleisch, Robert and Maier, Andreas and Aubreville, Marc and Breininger, Katharina}, title = {Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2211.16141}, year = {2022}, language = {en} } @unpublished{AmmelingSchmidtGanzetal.2022, author = {Ammeling, Jonas and Schmidt, Lars-Henning and Ganz, Jonathan and Niedermair, Tanja and Brochhausen-Delius, Christoph and Schulz, Christian and Breininger, Katharina and Aubreville, Marc}, title = {Attention-based Multiple Instance Learning for Survival Prediction on Lung Cancer Tissue Microarrays}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2212.07724}, year = {2022}, abstract = {Attention-based multiple instance learning (AMIL) algorithms have proven to be successful in utilizing gigapixel whole-slide images (WSIs) for a variety of different computational pathology tasks such as outcome prediction and cancer subtyping problems. We extended an AMIL approach to the task of survival prediction by utilizing the classical Cox partial likelihood as a loss function, converting the AMIL model into a nonlinear proportional hazards model. We applied the model to tissue microarray (TMA) slides of 330 lung cancer patients. The results show that AMIL approaches can handle very small amounts of tissue from a TMA and reach similar C-index performance compared to established survival prediction methods trained with highly discriminative clinical factors such as age, cancer grade, and cancer stage.}, language = {en} } @unpublished{AubrevillePanSievertetal.2023, author = {Aubreville, Marc and Pan, Zhaoya and Sievert, Matti and Ammeling, Jonas and Ganz, Jonathan and Oetter, Nicolai and Stelzle, Florian and Frenken, Ann-Kathrin and Breininger, Katharina and Goncalves, Miguel}, title = {Few Shot Learning for the Classification of Confocal Laser Endomicroscopy Images of Head and Neck Tumors}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2311.07216}, year = {2023}, abstract = {The surgical removal of head and neck tumors requires safe margins, which are usually confirmed intraoperatively by means of frozen sections. This method is, in itself, an oversampling procedure, which has a relatively low sensitivity compared to the definitive tissue analysis on paraffin-embedded sections. Confocal laser endomicroscopy (CLE) is an in-vivo imaging technique that has shown its potential in the live optical biopsy of tissue. An automated analysis of this notoriously difficult to interpret modality would help surgeons. However, the images of CLE show a wide variability of patterns, caused both by individual factors but also, and most strongly, by the anatomical structures of the imaged tissue, making it a challenging pattern recognition task. In this work, we evaluate four popular few shot learning (FSL) methods towards their capability of generalizing to unseen anatomical domains in CLE images. We evaluate this on images of sinunasal tumors (SNT) from five patients and on images of the vocal folds (VF) from 11 patients using a cross-validation scheme. The best respective approach reached a median accuracy of 79.6\% on the rather homogeneous VF dataset, but only of 61.6\% for the highly diverse SNT dataset. Our results indicate that FSL on CLE images is viable, but strongly affected by the number of patients, as well as the diversity of anatomical patterns.}, language = {en} } @inproceedings{QiuWilmOettletal.2023, author = {Qiu, Jingna and Wilm, Frauke and {\"O}ttl, Mathias and Schlereth, Maja and Liu, Chang and Heimann, Tobias and Aubreville, Marc and Breininger, Katharina}, title = {Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation}, booktitle = {Medical Image Computing and Computer Assisted Intervention - MICCAI 2023: Proceedings, Part II}, editor = {Greenspan, Hayit and Madabhushi, Anant and Mousavi, Parvin and Salcudean, Septimiu and Duncan, James and Syeda-Mahmood, Tanveer and Taylor, Russell}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-43895-0}, issn = {1611-3349}, doi = {https://doi.org/10.1007/978-3-031-43895-0_9}, pages = {90 -- 100}, year = {2023}, language = {en} } @inproceedings{GanzLipnikAmmelingetal.2023, author = {Ganz, Jonathan and Lipnik, Karoline and Ammeling, Jonas and Richter, Barbara and Puget, Chlo{\´e} and Parlak, Eda and Diehl, Laura and Klopfleisch, Robert and Donovan, Taryn and Kiupel, Matti and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Deep Learning-based Automatic Assessment of AgNOR-scores in Histopathology Images}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, Braunschweig, July 2-4, 2023}, editor = {Deserno, Thomas Martin and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-41657-7}, doi = {https://doi.org/10.1007/978-3-658-41657-7_49}, pages = {226 -- 231}, year = {2023}, language = {en} } @inproceedings{WilmFragosoGarciaBertrametal.2023, author = {Wilm, Frauke and Fragoso-Garcia, Marco and Bertram, Christof and Stathonikos, Nikolas and {\"O}ttl, Mathias and Qiu, Jingna and Klopfleisch, Robert and Maier, Andreas and Aubreville, Marc and Breininger, Katharina}, title = {Mind the Gap: Scanner-Induced Domain Shifts Pose Challenges for Representation Learning in Histopathology}, booktitle = {2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-7358-3}, doi = {https://doi.org/10.1109/ISBI53787.2023.10230458}, 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} } @unpublished{QiuAubrevilleWilmetal.2024, author = {Qiu, Jingna and Aubreville, Marc and Wilm, Frauke and {\"O}ttl, Mathias and Utz, Jonas and Schlereth, Maja and Breininger, Katharina}, title = {Leveraging Image Captions for Selective Whole Slide Image Annotation}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2407.06363}, year = {2024}, 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} } @inproceedings{AmmelingHeckerGanzetal.2024, author = {Ammeling, Jonas and Hecker, Moritz and Ganz, Jonathan and Donovan, Taryn and Klopfleisch, Robert and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Automated Mitotic Index Calculation via Deep Learning and Immunohistochemistry}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Conference on Medical Image Computing, Erlangen, March 10-12, 2024}, editor = {Maier, Andreas and Deserno, Thomas Martin and Handels, Heinz and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-44037-4}, doi = {https://doi.org/10.1007/978-3-658-44037-4_37}, pages = {123 -- 128}, year = {2024}, language = {en} } @article{SievertAubrevilleMuelleretal.2024, author = {Sievert, Matti and Aubreville, Marc and Mueller, Sarina Katrin and Eckstein, Markus and Breininger, Katharina and Iro, Heinrich and Goncalves, Miguel}, title = {Diagnosis of malignancy in oropharyngeal confocal laser endomicroscopy using GPT 4.0 with vision}, volume = {281}, journal = {European Archives of Oto-Rhino-Laryngology}, number = {4}, publisher = {Springer}, address = {Berlin}, issn = {1434-4726}, doi = {https://doi.org/10.1007/s00405-024-08476-5}, pages = {2115 -- 2122}, year = {2024}, 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} } @inproceedings{AmmelingMangerKwakaetal.2023, author = {Ammeling, Jonas and Manger, Carina and Kwaka, Elias and Kr{\"u}gel, Sebastian and Uhl, Matthias and Kießig, Angelika and Fritz, Alexis and Ganz, Jonathan and Riener, Andreas and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Appealing but Potentially Biasing - Investigation of the Visual Representation of Segmentation Predictions by AI Recommender Systems for Medical Decision Making}, booktitle = {Mensch und Computer 2023: Building Bridges: Tagungsband (Proceedings)}, editor = {Stolze, Markus and Loch, Frieder and Baldauf, Matthias and Alt, Florian and Schneegass, Christina and Kosch, Thomas and Hirzle, Teresa and Sadeghian, Shadan and Draxler, Fiona and Bektas, Kenan and Lohan, Katrin and Knierim, Pascal}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-0771-1}, doi = {https://doi.org/10.1145/3603555.3608561}, pages = {330 -- 335}, year = {2023}, language = {en} } @inproceedings{AmmelingWilmGanzetal.2023, author = {Ammeling, Jonas and Wilm, Frauke and Ganz, Jonathan and Breininger, Katharina and Aubreville, Marc}, title = {Reference Algorithms for the Mitosis Domain Generalization (MIDOG) 2022 Challenge}, booktitle = {Mitosis Domain Generalization and Diabetic Retinopathy Analysis}, editor = {Sheng, Bin and Aubreville, Marc}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-33658-4}, doi = {https://doi.org/10.1007/978-3-031-33658-4_19}, pages = {201 -- 205}, year = {2023}, language = {en} } @inproceedings{AubrevilleGanzAmmelingetal.2023, author = {Aubreville, Marc and Ganz, Jonathan and Ammeling, Jonas and Donovan, Taryn and Fick, Rutger H. J. and Breininger, Katharina and Bertram, Christof}, title = {Deep Learning-based Subtyping of Atypical and Normal Mitoses using a Hierarchical Anchor-free Object Detector}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, Braunschweig, July 2-4, 2023}, editor = {Deserno, Thomas Martin and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-41657-7}, doi = {https://doi.org/10.1007/978-3-658-41657-7_40}, pages = {189 -- 195}, year = {2023}, language = {en} } @article{AubrevilleStathonikosBertrametal.2022, author = {Aubreville, Marc and Stathonikos, Nikolas and Bertram, Christof and Klopfleisch, Robert and Hoeve, Natalie ter and Ciompi, Francesco and Wilm, Frauke and Marzahl, Christian and Donovan, Taryn and Maier, Andreas and Breen, Jack and Ravikumar, Nishant and Chung, Youjin and Park, Jinah and Nateghi, Ramin and Pourakpour, Fattaneh and Fick, Rutger H. J. and Ben Hadj, Saima and Jahanifar, Mostafa and Shepard, Adam and Dexl, Jakob and Wittenberg, Thomas and Kondo, Satoshi and Lafarge, Maxime W. and Kolezer, Viktor H. and Liang, Jingtang and Wang, Yubo and Long, Xi and Liu, Jingxin and Razavi, Salar and Khademi, April and Yang, Sen and Wang, Xiyue and Erber, Ramona and Klang, Andrea and Lipnik, Karoline and Bolfa, Pompei and Dark, Michael and Wasinger, Gabriel and Veta, Mitko and Breininger, Katharina}, title = {Mitosis domain generalization in histopathology images — The MIDOG challenge}, volume = {2023}, pages = {102699}, journal = {Medical Image Analysis}, number = {84}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1361-8415}, doi = {https://doi.org/10.1016/j.media.2022.102699}, year = {2022}, language = {en} } @article{PanBreiningerAubrevilleetal.2022, author = {Pan, Zhaoya and Breininger, Katharina and Aubreville, Marc and Stelzle, Florian and Oetter, Nicolai and Maier, Andreas and Mantsopoulos, Konstantinos and Iro, Heinrich and Goncalves, Miguel and Sievert, Matti}, title = {Defining a baseline identification of artifacts in confocal laser endomicroscopy in head and neck cancer imaging}, volume = {44}, pages = {103779}, journal = {American Journal of Otolaryngology}, number = {2}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1532-818X}, doi = {https://doi.org/10.1016/j.amjoto.2022.103779}, year = {2022}, language = {en} } @inproceedings{TheelkeWilmMarzahletal.2021, author = {Theelke, Luisa and Wilm, Frauke and Marzahl, Christian and Bertram, Christof and Klopfleisch, Robert and Maier, Andreas and Aubreville, Marc and Breininger, Katharina}, title = {Iterative Cross-Scanner Registration for Whole Slide Images}, booktitle = {2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-0191-3}, issn = {2473-9944}, doi = {https://doi.org/10.1109/ICCVW54120.2021.00071}, pages = {582 -- 590}, year = {2021}, language = {en} } @inproceedings{AubrevilleBertramStathonikosetal.2021, author = {Aubreville, Marc and Bertram, Christof and Stathonikos, Nikolas and ter Hoeve, Natalie and Ciompi, Francesco and Klopfleisch, Robert and Veta, Mitko and Donovan, Taryn and Marzahl, Christian and Wilm, Frauke and Breininger, Katharina and Maier, Andreas}, title = {Quantifying the Scanner-Induced Domain Gap in Mitosis Detection}, booktitle = {MIDL: Medical Imaging with Deep Learning 2021}, publisher = {MIDL Foundation}, address = {Nijmegen}, url = {https://2021.midl.io/papers/i6}, year = {2021}, language = {en} } @inproceedings{WilmMarzahlBreiningeretal.2022, author = {Wilm, Frauke and Marzahl, Christian and Breininger, Katharina and Aubreville, Marc}, title = {Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge}, booktitle = {Biomedical Image Registration, Domain Generalisation and Out-of-Distribution Analysis : MICCAI 2021 Challenges}, editor = {Aubreville, Marc and Zimmerer, David and Heinrich, Mattias}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-97281-3}, doi = {https://doi.org/10.1007/978-3-030-97281-3_1}, pages = {5 -- 13}, year = {2022}, 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} } @inproceedings{WilmBertramMarzahletal.2021, author = {Wilm, Frauke and Bertram, Christof and Marzahl, Christian and Bartel, Alexander and Donovan, Taryn and Assenmacher, Charles-Antoine and Becker, Kathrin and Bennett, Mark and Corner, Sarah M. and Cossic, Brieuc and Denk, Daniela and Dettwiler, Martina and Garcia Gonzalez, Beatriz and Gurtner, Corinne and Heier, Annabelle and Lehmbecker, Annika and Merz, Sophie and Plog, Stephanie and Schmidt, Anja and Sebastian, Franziska and Smedley, Rebecca C. and Tecilla, Marco and Thaiwong, Tuddow and Breininger, Katharina and Kiupel, Matti and Maier, Andreas and Klopfleisch, Robert and Aubreville, Marc}, title = {Influence of inter-annotator variability on automatic mitotic figure assessment}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2021}, publisher = {Springer}, address = {Wiesbaden}, isbn = {978-3-658-33198-6}, doi = {https://doi.org/10.1007/978-3-658-33198-6_56}, pages = {241 -- 246}, year = {2021}, language = {en} } @inproceedings{BertramDonovanTecillaetal.2021, author = {Bertram, Christof and Donovan, Taryn and Tecilla, Marco and Bartenschlager, Florian and Fragoso-Garcia, Marco and Wilm, Frauke and Marzahl, Christian and Breininger, Katharina and Maier, Andreas and Klopfleisch, Robert and Aubreville, Marc}, title = {Dataset on bi- and multi-nucleated tumor cells in canine cutaneous mast cell tumors}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2021: Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-33197-9}, issn = {1431-472X}, doi = {https://doi.org/10.1007/978-3-658-33198-6_33}, pages = {134 -- 139}, year = {2021}, language = {en} } @inproceedings{MarzahlBertramWilmetal.2021, author = {Marzahl, Christian and Bertram, Christof and Wilm, Frauke and Voigt, J{\"o}rn and Barton, Ann K. and Klopfleisch, Robert and Breininger, Katharina and Maier, Andreas and Aubreville, Marc}, title = {Cell detection for asthma on partially annotated whole slide images}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2021: Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, subtitle = {learning to be EXACT}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-33197-9}, issn = {1431-472X}, doi = {https://doi.org/10.1007/978-3-658-33198-6_36}, pages = {147 -- 152}, year = {2021}, language = {en} } @article{AmmelingGanzWilmetal.2025, author = {Ammeling, Jonas and Ganz, Jonathan and Wilm, Frauke and Breininger, Katharina and Aubreville, Marc}, title = {Investigation of Class Separability within Object Detection Models in Histopathology}, volume = {44}, journal = {IEEE Transactions on Medical Imaging}, number = {8}, publisher = {IEEE}, address = {New York}, issn = {0278-0062}, doi = {https://doi.org/10.1109/TMI.2025.3560134}, pages = {3162 -- 3174}, year = {2025}, language = {en} } @article{OetterProellSievertetal.2024, author = {Oetter, Nicolai and Pr{\"o}ll, Jonas and Sievert, Matti and Goncalves, Miguel and Rohde, Maximilian and Nobis, Christopher-Philipp and Knipfer, Christian and Aubreville, Marc and Pan, Zhaoya and Breininger, Katharina and Maier, Andreas and Kesting, Marco and Stelzle, Florian}, title = {Oral mucosa - an examination map for confocal laser endomicroscopy within the oral cavity: an experimental clinical study}, volume = {28}, pages = {266}, journal = {Clinical Oral Investigations}, number = {5}, publisher = {Springer}, address = {Berlin}, issn = {1436-3771}, doi = {https://doi.org/10.1007/s00784-024-05664-9}, year = {2024}, abstract = {Objectives Confocal laser endomicroscopy (CLE) is an optical method that enables microscopic visualization of oral mucosa. Previous studies have shown that it is possible to differentiate between physiological and malignant oral mucosa. However, differences in mucosal architecture were not taken into account. The objective was to map the different oral mucosal morphologies and to establish a "CLE map" of physiological mucosa as baseline for further application of this powerful technology. Materials and methods The CLE database consisted of 27 patients. The following spots were examined: (1) upper lip (intraoral) (2) alveolar ridge (3) lateral tongue (4) floor of the mouth (5) hard palate (6) intercalary line. All sequences were examined by two CLE experts for morphological differences and video quality. Results Analysis revealed clear differences in image quality and possibility of depicting tissue morphologies between the various localizations of oral mucosa: imaging of the alveolar ridge and hard palate showed visually most discriminative tissue morphology. Labial mucosa was also visualized well using CLE. Here, typical morphological features such as uniform cells with regular intercellular gaps and vessels could be clearly depicted. Image generation and evaluation was particularly difficult in the area of the buccal mucosa, the lateral tongue and the floor of the mouth. Conclusion A physiological "CLE map" for the entire oral cavity could be created for the first time. Clinical relevance This will make it possible to take into account the existing physiological morphological features when differentiating between normal mucosa and oral squamous cell carcinoma in future work.}, language = {en} } @article{AmmelingGanzRosbachetal.2026, author = {Ammeling, Jonas and Ganz, Jonathan and Rosbach, Emely and Lausser, Ludwig and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Benchmarking Foundation Models for Mitotic Figure Classification}, volume = {3}, pages = {2026:003}, journal = {Machine Learning for Biomedical Imaging}, number = {MELBA-BVM 2025 Special Issue}, publisher = {Melba editors}, address = {[s. l.]}, issn = {2766-905X}, doi = {https://doi.org/10.59275/j.melba.2026-a3eb}, pages = {38 -- 55}, year = {2026}, abstract = {The performance of deep learning models is known to scale with data quantity and diversity. In pathology, as in many other medical imaging domains, the availability of labeled images for a specific task is often limited. Self-supervised learning techniques have enabled the use of vast amounts of unlabeled data to train large-scale neural networks, i.e., foundation models, that can address the limited data problem by providing semantically rich feature vectors that can generalize well to new tasks with minimal training effort increasing model performance and robustness. In this work, we investigate the use of foundation models for mitotic figure classification. The mitotic count, which can be derived from this classification task, is an independent prognostic marker for specific tumors and part of certain tumor grading systems. In particular, we investigate the data scaling laws on multiple current foundation models and evaluate their robustness to unseen tumor domains. Next to the commonly used linear probing paradigm, we also adapt the models using low-rank adaptation (LoRA) of their attention mechanisms. We compare all models against end-to-end-trained baselines, both CNNs and Vision Transformers. Our results demonstrate that LoRA-adapted foundation models provide superior performance to those adapted with standard linear probing, reaching performance levels close to 100 \% data availability with only 10 \% of training data. Furthermore, LoRA-adaptation of the most recent foundation models almost closes the out-of-domain performance gap when evaluated on unseen tumor domains. However, full fine-tuning of traditional architectures still yields competitive performance.}, language = {en} } @inproceedings{GanzAmmelingRosbachetal.2025, 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?}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, subtitle = {Benchmarking Foundation Models Against End-to-end Training for Mitotic Figure Classification}, editor = {Palm, Christoph and Breininger, Katharina and Deserno, Thomas Martin and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-47422-5}, doi = {https://doi.org/10.1007/978-3-658-47422-5_15}, pages = {63 -- 68}, year = {2025}, language = {en} } @unpublished{AmmelingGanzRosbachetal.2025, author = {Ammeling, Jonas and Ganz, Jonathan and Rosbach, Emely and Lausser, Ludwig and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Benchmarking Foundation Models for Mitotic Figure Classification}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2508.04441}, year = {2025}, language = {en} } @article{PugetGanzOstermaieretal.2024, author = {Puget, Chlo{\´e} and Ganz, Jonathan and Ostermaier, Julian and Conrad, Thomas and Parlak, Eda and Bertram, Christof and Kiupel, Matti and Breininger, Katharina and Aubreville, Marc and Klopfleisch, Robert}, title = {Artificial intelligence can be trained to predict c-KIT-11 mutational status of canine mast cell tumors from hematoxylin and eosin-stained histological slides}, volume = {62}, journal = {Veterinary Pathology}, number = {2}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858241286806}, pages = {152 -- 160}, year = {2024}, abstract = {Numerous prognostic factors are currently assessed histologically and immunohistochemically in canine mast cell tumors (MCTs) to evaluate clinical behavior. In addition, polymerase chain reaction (PCR) is often performed to detect internal tandem duplication (ITD) mutations in exon 11 of the c-KIT gene ( c-KIT-11-ITD) to predict the therapeutic response to tyrosine kinase inhibitors. This project aimed at training deep learning models (DLMs) to identify MCTs with c-KIT-11-ITD solely based on morphology. Hematoxylin and eosin (HE) stained slides of 368 cutaneous, subcutaneous, and mucocutaneous MCTs (195 with ITD and 173 without) were stained consecutively in 2 different laboratories and scanned with 3 different slide scanners. This resulted in 6 data sets (stain-scanner variations representing diagnostic institutions) of whole-slide images. DLMs were trained with single and mixed data sets and their performances were assessed under stain-scanner variations (domain shifts). The DLM correctly classified HE slides according to their c-KIT-11-ITD status in up to 87\% of cases with a 0.90 sensitivity and a 0.83 specificity. A relevant performance drop could be observed when the stain-scanner combination of training and test data set differed. Multi-institutional data sets improved the average accuracy but did not reach the maximum accuracy of algorithms trained and tested on the same stain-scanner variant (ie, intra-institutional). In summary, DLM-based morphological examination can predict c-KIT-11-ITD with high accuracy in canine MCTs in HE slides. However, staining protocol and scanner type influence accuracy. Larger data sets of scans from different laboratories and scanners may lead to more robust DLMs to identify c- KIT mutations in HE slides.}, language = {en} } @article{WilmFragosoGarciaMarzahletal.2022, author = {Wilm, Frauke and Fragoso-Garcia, Marco and Marzahl, Christian and Qiu, Jingna and Puget, Chlo{\´e} and Diehl, Laura and Bertram, Christof and Klopfleisch, Robert and Maier, Andreas and Breininger, Katharina and Aubreville, Marc}, title = {Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset}, volume = {9}, pages = {588}, journal = {Scientific Data}, publisher = {Springer}, address = {London}, issn = {2052-4463}, doi = {https://doi.org/10.1038/s41597-022-01692-w}, year = {2022}, abstract = {Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging. Recently, deep learning-based approaches have proven their potential for supporting pathologists in this regard. However, many of these supervised algorithms require a large amount of annotated data for robust development. We present a publicly available dataset of 350 whole slide images of seven different canine cutaneous tumors complemented by 12,424 polygon annotations for 13 histologic classes, including seven cutaneous tumor subtypes. In inter-rater experiments, we show a high consistency of the provided labels, especially for tumor annotations. We further validate the dataset by training a deep neural network for the task of tissue segmentation and tumor subtype classification. We achieve a class-averaged Jaccard coefficient of 0.7047, and 0.9044 for tumor in particular. For classification, we achieve a slide-level accuracy of 0.9857. Since canine cutaneous tumors possess various histologic homologies to human tumors the added value of this dataset is not limited to veterinary pathology but extends to more general fields of application.}, language = {en} } @article{AubrevilleWilmStathonikosetal.2023, author = {Aubreville, Marc and Wilm, Frauke and Stathonikos, Nikolas and Breininger, Katharina and Donovan, Taryn and Jabari, Samir and Veta, Mitko and Ganz, Jonathan and Ammeling, Jonas and van Diest, Paul J and Klopfleisch, Robert and Bertram, Christof}, title = {A comprehensive multi-domain dataset for mitotic figure detection}, volume = {10}, pages = {484}, journal = {Scientific Data}, publisher = {Springer}, address = {London}, issn = {2052-4463}, doi = {https://doi.org/10.1038/s41597-023-02327-4}, year = {2023}, abstract = {The prognostic value of mitotic figures in tumor tissue is well-established for many tumor types and automating this task is of high research interest. However, especially deep learning-based methods face performance deterioration in the presence of domain shifts, which may arise from different tumor types, slide preparation and digitization devices. We introduce the MIDOG++ dataset, an extension of the MIDOG 2021 and 2022 challenge datasets. We provide region of interest images from 503 histological specimens of seven different tumor types with variable morphology with in total labels for 11,937 mitotic figures: breast carcinoma, lung carcinoma, lymphosarcoma, neuroendocrine tumor, cutaneous mast cell tumor, cutaneous melanoma, and (sub)cutaneous soft tissue sarcoma. The specimens were processed in several laboratories utilizing diverse scanners. We evaluated the extent of the domain shift by using state-of-the-art approaches, observing notable differences in single-domain training. In a leave-one-domain-out setting, generalizability improved considerably. This mitotic figure dataset is the first that incorporates a wide domain shift based on different tumor types, laboratories, whole slide image scanners, and species.}, language = {en} } @article{MarzahlHillStaytetal.2022, author = {Marzahl, Christian and Hill, Jenny and Stayt, Jason and Bienzle, Dorothee and Welker, Lutz and Wilm, Frauke and Voigt, J{\"o}rn and Aubreville, Marc and Maier, Andreas and Klopfleisch, Robert and Breininger, Katharina and Bertram, Christof}, title = {Inter-species cell detection - datasets on pulmonary hemosiderophages in equine, human and feline specimens}, volume = {9}, pages = {269}, journal = {Scientific Data}, publisher = {Springer}, address = {London}, issn = {2052-4463}, doi = {https://doi.org/10.1038/s41597-022-01389-0}, year = {2022}, abstract = {Pulmonary hemorrhage (P-Hem) occurs among multiple species and can have various causes. Cytology of bronchoalveolar lavage fluid (BALF) using a 5-tier scoring system of alveolar macrophages based on their hemosiderin content is considered the most sensitive diagnostic method. We introduce a novel, fully annotated multi-species P-Hem dataset, which consists of 74 cytology whole slide images (WSIs) with equine, feline and human samples. To create this high-quality and high-quantity dataset, we developed an annotation pipeline combining human expertise with deep learning and data visualisation techniques. We applied a deep learning-based object detection approach trained on 17 expertly annotated equine WSIs, to the remaining 39 equine, 12 human and 7 feline WSIs. The resulting annotations were semi-automatically screened for errors on multiple types of specialised annotation maps and finally reviewed by a trained pathologist. Our dataset contains a total of 297,383 hemosiderophages classified into five grades. It is one of the largest publicly available WSIs datasets with respect to the number of annotations, the scanned area and the number of species covered.}, language = {en} } @inproceedings{BanerjeeGoschHesteretal.2026, author = {Banerjee, Sweta and Gosch, Timo and Hester, Sara and Weiss, Viktoria and Conrad, Thomas and Donovan, Taryn and Porsche, Nils and Ammeling, Jonas and Stroblberger, Christoph and Klopfleisch, Robert and Kaltenecker, Christopher and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Enabling Fast and Mobile Histopathology Image Annotation through Swipeable Interfaces SWAN}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2026: Proceedings, German Conference on Medical Image Computing, L{\"u}beck, March 15-17, 2026}, editor = {Handels, Heinz and Breininger, Katharina and Deserno, Thomas Martin and Maier, Andreas and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-51100-5}, doi = {https://doi.org/10.1007/978-3-658-51100-5_42}, pages = {203 -- 209}, year = {2026}, language = {en} } @inproceedings{BanerjeeBertramAmmelingetal.2025, author = {Banerjee, Sweta and Bertram, Christof and Ammeling, Jonas and Weiss, Viktoria and Conrad, Thomas and Klopfleisch, Robert and Kaltenecker, Christopher and Breininger, Katharina and Aubreville, Marc}, title = {Comprehensive Dataset of Coarse Tumor Annotations for The Cancer Genome Atlas Breast Invasive Carcinoma}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, editor = {Palm, Christoph and Breininger, Katharina and Deserno, Thomas Martin and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-47422-5}, doi = {https://doi.org/10.1007/978-3-658-47422-5_56}, pages = {260 -- 265}, year = {2025}, language = {en} }