@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} } @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} } @article{BertramMarzahlBarteletal.2022, author = {Bertram, Christof and Marzahl, Christian and Bartel, Alexander and Stayt, Jason and Bonsembiante, Federico and Beeler-Marfisi, Janet and Barton, Ann K. and Brocca, Ginevra and Gelain, Maria Elena and Gl{\"a}sel, Agnes C. and du Preez, Kelly and Weiler, Kristina and Weissenbacher-Lang, Christiane and Breininger, Katharina and Aubreville, Marc and Maier, Andreas and Klopfleisch, Robert and Hill, Jenny}, title = {Cytologic scoring of equine exercise-induced pulmonary hemorrhage: Performance of human experts and a deep learning-based algorithm}, volume = {60}, journal = {Veterinary Pathology}, number = {1}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858221137582}, pages = {75 -- 85}, year = {2022}, abstract = {Exercise-induced pulmonary hemorrhage (EIPH) is a relevant respiratory disease in sport horses, which can be diagnosed by examination of bronchoalveolar lavage fluid (BALF) cells using the total hemosiderin score (THS). The aim of this study was to evaluate the diagnostic accuracy and reproducibility of annotators and to validate a deep learning-based algorithm for the THS. Digitized cytological specimens stained for iron were prepared from 52 equine BALF samples. Ten annotators produced a THS for each slide according to published methods. The reference methods for comparing annotator's and algorithmic performance included a ground truth dataset, the mean annotators' THSs, and chemical iron measurements. Results of the study showed that annotators had marked interobserver variability of the THS, which was mostly due to a systematic error between annotators in grading the intracytoplasmatic hemosiderin content of individual macrophages. Regarding overall measurement error between the annotators, 87.7\% of the variance could be reduced by using standardized grades based on the ground truth. The algorithm was highly consistent with the ground truth in assigning hemosiderin grades. Compared with the ground truth THS, annotators had an accuracy of diagnosing EIPH (THS of < or ≥ 75) of 75.7\%, whereas, the algorithm had an accuracy of 92.3\% with no relevant differences in correlation with chemical iron measurements. The results show that deep learning-based algorithms are useful for improving reproducibility and routine applicability of the THS. For THS by experts, a diagnostic uncertainty interval of 40 to 110 is proposed. THSs within this interval have insufficient reproducibility regarding the EIPH diagnosis.}, language = {en} } @article{MarzahlAubrevilleBertrametal.2021, author = {Marzahl, Christian and Aubreville, Marc and Bertram, Christof and Maier, Jennifer and Bergler, Christian and Kr{\"o}ger, Christine and Voigt, J{\"o}rn and Breininger, Katharina and Klopfleisch, Robert and Maier, Andreas}, title = {EXACT: a collaboration toolset for algorithm-aided annotation of images with annotation version control}, volume = {11}, pages = {4343}, journal = {Scientific Reports}, publisher = {Springer Nature}, address = {London}, issn = {2045-2322}, doi = {https://doi.org/10.1038/s41598-021-83827-4}, year = {2021}, abstract = {In many research areas, scientific progress is accelerated by multidisciplinary access to image data and their interdisciplinary annotation. However, keeping track of these annotations to ensure a high-quality multi-purpose data set is a challenging and labour intensive task. We developed the open-source online platform EXACT (EXpert Algorithm Collaboration Tool) that enables the collaborative interdisciplinary analysis of images from different domains online and offline. EXACT supports multi-gigapixel medical whole slide images as well as image series with thousands of images. The software utilises a flexible plugin system that can be adapted to diverse applications such as counting mitotic figures with a screening mode, finding false annotations on a novel validation view, or using the latest deep learning image analysis technologies. This is combined with a version control system which makes it possible to keep track of changes in the data sets and, for example, to link the results of deep learning experiments to specific data set versions. EXACT is freely available and has already been successfully applied to a broad range of annotation tasks, including highly diverse applications like deep learning supported cytology scoring, interdisciplinary multi-centre whole slide image tumour annotation, and highly specialised whale sound spectroscopy clustering.}, language = {en} } @article{MeutenMooreDonovanetal.2021, author = {Meuten, Donald J. and Moore, Frances M. and Donovan, Taryn and Bertram, Christof and Klopfleisch, Robert and Foster, Robert A. and Smedley, Rebecca C. and Dark, Michael and Milovancev, Milan and Stromberg, Paul and Williams, Bruce H. and Aubreville, Marc and Avallone, Giancarlo and Bolfa, Pompei and Cullen, John and Dennis, Michelle M. and Goldschmidt, Michael and Luong, Richard and Miller, Andrew D. and Miller, Margaret A. and Munday, John S. and Roccabianca, Paola and Salas, Elisa N. and Schulman, F. Yvonne and Laufer-Amorim, Renee and Asakawa, Midori G. and Craig, Linden and Dervisis, Nick and Esplin, D. Glen and George, Jeanne W. and Hauck, Marlene and Kagawa, Yumiko and Kiupel, Matti and Linder, Keith and Meichner, Kristina and Marconato, Laura and Oblak, Michelle L. and Santos, Renato L. and Simpson, R. Mark and Tvedten, Harold and Whitley, Derick}, title = {International Guidelines for Veterinary Tumor Pathology: A Call to Action}, volume = {58}, journal = {Veterinary Pathology}, number = {5}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858211013712}, pages = {766 -- 794}, year = {2021}, 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{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{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} } @article{RosbachAmmelingGanzetal.2026, author = {Rosbach, Emely and Ammeling, Jonas and Ganz, Jonathan and Bertram, Christof and Conrad, Thomas and Riener, Andreas and Aubreville, Marc}, title = {Stuck on Suggestions: Automation Bias, the Anchoring Effect, and the Factors That Shape Them in Computational Pathology}, volume = {3}, pages = {2026:007}, 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.2026-87b1}, pages = {126 -- 147}, year = {2026}, abstract = {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.}, 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{AubrevilleBertramDonovanetal.2020, author = {Aubreville, Marc and Bertram, Christof and Donovan, Taryn and Marzahl, Christian and Maier, Andreas and Klopfleisch, Robert}, title = {A completely annotated whole slide image dataset of canine breast cancer to aid human breast cancer research}, volume = {7}, pages = {417}, journal = {Scientific data}, publisher = {Springer}, address = {London}, issn = {2052-4463}, doi = {https://doi.org/10.1038/s41597-020-00756-z}, year = {2020}, abstract = {Canine mammary carcinoma (CMC) has been used as a model to investigate the pathogenesis of human breast cancer and the same grading scheme is commonly used to assess tumor malignancy in both. One key component of this grading scheme is the density of mitotic figures (MF). Current publicly available datasets on human breast cancer only provide annotations for small subsets of whole slide images (WSIs). We present a novel dataset of 21 WSIs of CMC completely annotated for MF. For this, a pathologist screened all WSIs for potential MF and structures with a similar appearance. A second expert blindly assigned labels, and for non-matching labels, a third expert assigned the final labels. Additionally, we used machine learning to identify previously undetected MF. Finally, we performed representation learning and two-dimensional projection to further increase the consistency of the annotations. Our dataset consists of 13,907 MF and 36,379 hard negatives. We achieved a mean F1-score of 0.791 on the test set and of up to 0.696 on a human breast cancer dataset.}, 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} } @article{BertramAubrevilleMarzahletal.2019, author = {Bertram, Christof and Aubreville, Marc and Marzahl, Christian and Maier, Andreas and Klopfleisch, Robert}, title = {A large-scale dataset for mitotic figure assessment on whole slide images of canine cutaneous mast cell tumor}, volume = {6}, pages = {274}, journal = {Scientific data}, publisher = {Springer}, address = {London}, issn = {2052-4463}, doi = {https://doi.org/10.1038/s41597-019-0290-4}, year = {2019}, abstract = {We introduce a novel, large-scale dataset for microscopy cell annotations. The dataset includes 32 whole slide images (WSI) of canine cutaneous mast cell tumors, selected to include both low grade cases as well as high grade cases. The slides have been completely annotated for mitotic figures and we provide secondary annotations for neoplastic mast cells, inflammatory granulocytes, and mitotic figure look-alikes. Additionally to a blinded two-expert manual annotation with consensus, we provide an algorithm-aided dataset, where potentially missed mitotic figures were detected by a deep neural network and subsequently assessed by two human experts. We included 262,481 annotations in total, out of which 44,880 represent mitotic figures. For algorithmic validation, we used a customized RetinaNet approach, followed by a cell classification network. We find F1-Scores of 0.786 and 0.820 for the manually labelled and the algorithm-aided dataset, respectively. The dataset provides, for the first time, WSIs completely annotated for mitotic figures and thus enables assessment of mitosis detection algorithms on complete WSIs as well as region of interest detection algorithms.}, language = {en} } @inproceedings{BertramWeissDonovanetal.2025, author = {Bertram, Christof and Weiss, Viktoria and Donovan, Taryn and Banerjee, Sweta and Conrad, Thomas and Ammeling, Jonas and Klopfleisch, Robert and Kaltenecker, Christopher and Aubreville, Marc}, title = {Histologic Dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br)}, 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_25}, pages = {113 -- 118}, year = {2025}, language = {en} } @unpublished{AubrevilleGanzAmmelingetal.2024, author = {Aubreville, Marc and Ganz, Jonathan and Ammeling, Jonas and Kaltenecker, Christopher and Bertram, Christof}, title = {Model-based Cleaning of the QUILT-1M Pathology Dataset for Text-Conditional Image Synthesis}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2404.07676}, year = {2024}, abstract = {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.}, 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} } @unpublished{MarzahlBertramAubrevilleetal.2020, author = {Marzahl, Christian and Bertram, Christof and Aubreville, Marc and Petrick, Anne and Weiler, Kristina and Gl{\"a}sel, Agnes C. and Fragoso-Garcia, Marco and Merz, Sophie and Bartenschlager, Florian and Hoppe, Judith and Langenhagen, Alina and Jasensky, Anne-Katherine and Voigt, J{\"o}rn and Klopfleisch, Robert and Maier, Andreas}, title = {Are Fast Labeling Methods Reliable? A Case Study of Computer-Aided Expert Annotations on Microscopy Slides}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2004.05838}, year = {2020}, language = {en} } @unpublished{BertramVetaMarzahletal.2020, author = {Bertram, Christof and Veta, Mitko and Marzahl, Christian and Stathonikos, Nikolas and Maier, Andreas and Klopfleisch, Robert and Aubreville, Marc}, title = {Are pathologist-defined labels reproducible? Comparison of the TUPAC16 mitotic figure dataset with an alternative set of labels}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2007.05351}, year = {2020}, language = {en} }