TY - CHAP A1 - Rosbach, Emely A1 - Ammeling, Jonas A1 - Krügel, Sebastian A1 - Kießig, Angelika A1 - Fritz, Alexis A1 - Ganz, Jonathan A1 - Puget, Chloé A1 - Donovan, Taryn A1 - Klang, Andrea A1 - Köller, Maximilian C. A1 - Bolfa, Pompei A1 - Tecilla, Marco A1 - Denk, Daniela A1 - Kiupel, Matti A1 - Paraschou, Georgios A1 - Kok, Mun Keong A1 - Haake, Alexander F. H. A1 - de Krijger, Ronald R. A1 - Sonnen, Andreas F.-P. A1 - Kasantikul, Tanit A1 - Dorrestein, Gerry M. A1 - Smedley, Rebecca C. A1 - Stathonikos, Nikolas A1 - Uhl, Matthias A1 - Bertram, Christof A1 - Riener, Andreas A1 - Aubreville, Marc ED - Yamashita, Naomi ED - Evers, Vanessa ED - Yatani, Koji ED - Ding, Xianghua ED - Lee, Bongshin ED - Chetty, Marshini ED - Toups-Dugas, Phoebe T1 - "When Two Wrongs Don't Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology T2 - CHI'25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems N2 - Artificial intelligence (AI)-based decision support systems hold promise for enhancing diagnostic accuracy and efficiency in computational pathology. However, human-AI collaboration can introduce and amplify cognitive biases, like confirmation bias caused by false confirmation when erroneous human opinions are reinforced by inaccurate AI output. This bias may increase under time pressure, a ubiquitous factor in routine pathology, as it strains practitioners’ cognitive resources. We quantified confirmation bias triggered by AI-induced false confirmation and examined the role of time constraints in a web-based experiment, where trained pathology experts (n=28) estimated tumor cell percentages. Our results suggest that AI integration fuels confirmation bias, evidenced by a statistically significant positive linear-mixed-effects model coefficient linking AI recommendations mirroring flawed human judgment and alignment with system advice. Conversely, time pressure appeared to weaken this relationship. These findings highlight potential risks of AI in healthcare and aim to support the safe integration of clinical decision support systems. UR - https://doi.org/10.1145/3706598.3713319 Y1 - 2025 UR - https://doi.org/10.1145/3706598.3713319 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58797 SN - 979-8-4007-1394-1 PB - ACM CY - New York ER - TY - INPR A1 - Rosbach, Emely A1 - Ammeling, Jonas A1 - Krügel, Sebastian A1 - Kießig, Angelika A1 - Fritz, Alexis A1 - Ganz, Jonathan A1 - Puget, Chloé A1 - Donovan, Taryn A1 - Klang, Andrea A1 - Köller, Maximilian C. A1 - Bolfa, Pompei A1 - Tecilla, Marco A1 - Denk, Daniela A1 - Kiupel, Matti A1 - Paraschou, Georgios A1 - Kok, Mun Keong A1 - Haake, Alexander F. H. A1 - de Krijger, Ronald R. A1 - Sonnen, Andreas F.-P. A1 - Kasantikul, Tanit A1 - Dorrestein, Gerry M. A1 - Smedley, Rebecca C. A1 - Stathonikos, Nikolas A1 - Uhl, Matthias A1 - Bertram, Christof A1 - Riener, Andreas A1 - Aubreville, Marc T1 - "When TwoWrongs Don’t Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology UR - https://doi.org/10.48550/arXiv.2411.01007 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2411.01007 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Aubreville, Marc A1 - Stathonikos, Nikolas A1 - Donovan, Taryn A1 - Klopfleisch, Robert A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Wilm, Frauke A1 - Veta, Mitko A1 - Jabari, Samir A1 - Eckstein, Markus A1 - Annuscheit, Jonas A1 - Krumnow, Christian A1 - Bozaba, Engin A1 - Cayir, Sercan A1 - Gu, Hongyan A1 - Chen, Xiang A1 - Jahanifar, Mostafa A1 - Shephard, Adam A1 - Kondo, Satoshi A1 - Kasai, Satoshi A1 - Kotte, Sujatha A1 - Saipradeep, Vangala A1 - Lafarge, Maxime W. A1 - Koelzer, Viktor H. A1 - Wang, Ziyue A1 - Zhang, Yongbing A1 - Yang, Sen A1 - Wang, Xiyue A1 - Breininger, Katharina A1 - Bertram, Christof T1 - Domain generalization across tumor types, laboratories, and species – Insights from the 2022 edition of the Mitosis Domain Generalization Challenge N2 - Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert consensus and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an F1 score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, but with only minor changes in the order of participants in the ranking. UR - https://doi.org/10.48550/arXiv.2309.15589 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2309.15589 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41514 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Haghofer, Andreas A1 - Parlak, Eda A1 - Bartel, Alexander A1 - Donovan, Taryn A1 - Assenmacher, Charles-Antoine A1 - Bolfa, Pompei A1 - Dark, Michael A1 - Fuchs-Baumgartinger, Andrea A1 - Klang, Andrea A1 - Jäger, Kathrin A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Richter, Barbara A1 - Schulman, F. Yvonne A1 - Ganz, Jonathan A1 - Scharinger, Josef A1 - Aubreville, Marc A1 - Winkler, Stephan M. A1 - Kiupel, Matti A1 - Bertram, Christof T1 - Nuclear Morphometry using a Deep Learning-based Algorithm has Prognostic Relevance for Canine Cutaneous Mast Cell Tumors N2 - Variation in nuclear size and shape is an important criterion of malignancy for many tumor types; however, categorical estimates by pathologists have poor reproducibility. Measurements of nuclear characteristics (morphometry) can improve reproducibility, but manual methods are time consuming. In this study, we evaluated fully automated morphometry using a deep learning-based algorithm in 96 canine cutaneous mast cell tumors with information on patient survival. Algorithmic morphometry was compared with karyomegaly estimates by 11 pathologists, manual nuclear morphometry of 12 cells by 9 pathologists, and the mitotic count as a benchmark. The prognostic value of automated morphometry was high with an area under the ROC curve regarding the tumor-specific survival of 0.943 (95% CI: 0.889 - 0.996) for the standard deviation (SD) of nuclear area, which was higher than manual morphometry of all pathologists combined (0.868, 95% CI: 0.737 - 0.991) and the mitotic count (0.885, 95% CI: 0.765 - 1.00). At the proposed thresholds, the hazard ratio for algorithmic morphometry (SD of nuclear area ≥9.0μm2) was 18.3 (95% CI: 5.0 - 67.1), for manual morphometry (SD of nuclear area ≥10.9μm2) 9.0 (95% CI: 6.0 - 13.4), for karyomegaly estimates 7.6 (95% CI: 5.7 - 10.1), and for the mitotic count 30.5 (95% CI: 7.8 - 118.0). Inter-rater reproducibility for karyomegaly estimates was fair (κ = 0.226) with highly variable sensitivity/specificity values for the individual pathologists. Reproducibility for manual morphometry (SD of nuclear area) was good (ICC = 0.654). This study supports the use of algorithmic morphometry as a prognostic test to overcome the limitations of estimates and manual measurements. UR - https://doi.org/10.48550/arXiv.2309.15031 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2309.15031 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41401 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Ganz, Jonathan A1 - Marzahl, Christian A1 - Ammeling, Jonas A1 - Richter, Barbara A1 - Puget, Chloé A1 - Denk, Daniela A1 - Demeter, Elena A. A1 - Tabaran, Flaviu A. A1 - Wasinger, Gabriel A1 - Lipnik, Karoline A1 - Tecilla, Marco A1 - Valentine, Matthew J. A1 - Dark, Michael A1 - Abele, Niklas A1 - Bolfa, Pompei A1 - Erber, Ramona A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Donovan, Taryn A1 - Jabari, Samir A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - On the Value of PHH3 for Mitotic Figure Detection on H&E-stained Images N2 - The count of mitotic figures (MFs) observed in hematoxylin and eosin (H&E)-stained slides is an important prognostic marker as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. Deep learning algorithms can standardize this task, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithm's performance. Unlike H&E, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H&E stain alone, the use of this ground truth could potentially introduce noise into the H&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. We found that the annotators' object-level agreement increased when using PHH3-assisted labeling. Subsequently, MF detectors were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models' performance. Additionally, a novel dual-stain MF detector was developed to investigate the interpretation-shift of PHH3-assisted labels used in H&E, which clearly outperformed single-stain detectors. However, the PHH3-assisted labels did not have a positive effect on solely H&E-based models. The high performance of our dual-input detector reveals an information mismatch between the H&E and PHH3-stained images as the cause of this effect. UR - https://doi.org/10.48550/arXiv.2406.19899 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2406.19899 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-50155 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification N2 - Foundation models (FMs), i.e., models trained on a vast amount of typically unlabeled data, have become popular and available recently for the domain of histopathology. The key idea is to extract semantically rich vectors from any input patch, allowing for the use of simple subsequent classification networks potentially reducing the required amounts of labeled data, and increasing domain robustness. In this work, we investigate to which degree this also holds for mitotic figure classification. Utilizing two popular public mitotic figure datasets, we compared linear probing of five publicly available FMs against models trained on ImageNet and a simple ResNet50 end-to-end-trained baseline. We found that the end-to-end-trained baseline outperformed all FM-based classifiers, regardless of the amount of data provided. Additionally, we did not observe the FM-based classifiers to be more robust against domain shifts, rendering both of the above assumptions incorrect. UR - https://doi.org/10.48550/arXiv.2412.06365 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2412.06365 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59672 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Bertram, Christof A1 - Aubreville, Marc A1 - Gurtner, Corinne A1 - Bartel, Alexander A1 - Corner, Sarah M. A1 - Dettwiler, Martina A1 - Kershaw, Olivia A1 - Noland, Erica L. A1 - Schmidt, Anja A1 - Sledge, Dodd G. A1 - Smedley, Rebecca C. A1 - Thaiwong, Tuddow A1 - Kiupel, Matti A1 - Maier, Andreas A1 - Klopfleisch, Robert T1 - Computerized Calculation of Mitotic Count Distribution in Canine Cutaneous Mast Cell Tumor Sections: Mitotic Count Is Area Dependent JF - Veterinary Pathology UR - https://doi.org/10.1177/0300985819890686 KW - area selection KW - high-power field KW - mitotic activity KW - mitotic figure distribution KW - tumor grading KW - tumor periphery Y1 - 2020 UR - https://doi.org/10.1177/0300985819890686 SN - 1544-2217 VL - 57 IS - 2 SP - 214 EP - 226 PB - Sage CY - London ER - TY - CHAP A1 - Marzahl, Christian A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Gerlach, Stefan A1 - Maier, Jennifer A1 - Voigt, Jörn A1 - Hill, Jenny A1 - Klopfleisch, Robert A1 - Maier, Andreas ED - Tolxdorff, Thomas ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Palm, Christoph T1 - Is crowd-algorithm collaboration an advanced alternative to crowd-sourcing on cytology slides? T2 - Bildverarbeitung für die Medizin 2020, Algorithmen – Systeme – Anwendungen. Proceedings des Workshops vom 15. bis 17. März 2020 in Berlin UR - https://doi.org/10.1007/978-3-658-29267-6_5 Y1 - 2020 UR - https://doi.org/10.1007/978-3-658-29267-6_5 SN - 978-3-658-29266-9 SN - 978-3-658-29267-6 N1 - Access to this content is enabled by Nationallizenz Ebooks Medicine SP - 26 EP - 31 PB - Springer Vieweg CY - Wiesbaden ER - TY - CHAP A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Jabari, Samir A1 - Marzahl, Christian A1 - Klopfleisch, Robert A1 - Maier, Andreas ED - Tolxdorff, Thomas ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Palm, Christoph T1 - Inter-species, inter-tissue domain adaptation for mitotic figure assessment BT - learning new tricks from old dogs T2 - Bildverarbeitung für die Medizin 2020, Algorithmen – Systeme – Anwendungen. Proceedings des Workshops vom 15. bis 17. März 2020 in Berlin UR - https://doi.org/10.1007/978-3-658-29267-6_1 Y1 - 2020 UR - https://doi.org/10.1007/978-3-658-29267-6_1 SN - 978-3-658-29266-9 SN - 978-3-658-29267-6 N1 - Access to this content is enabled by Nationallizenz Ebooks Medicine SP - 1 EP - 7 PB - Springer Vieweg CY - Wiesbaden ER - TY - CHAP A1 - Ganz, Jonathan A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Jabari, Samir A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Classification of visibility in multi-stain microscopy images T2 - Medical Imaging with Deep Learning: MIDL 2022 Short Papers KW - mitotic figure classification KW - digital pathology KW - deep learning KW - dual input networks KW - attention KW - immunohistochemical staining Y1 - 2022 UR - https://openreview.net/forum?id=-GsA-mUVmm ER - TY - INPR A1 - Puget, Chloé A1 - Ganz, Jonathan A1 - Ostermaier, Julian A1 - Konrad, Thomas A1 - Parlak, Eda A1 - Bertram, Christof A1 - Kiupel, Matti A1 - Breininger, Katharina A1 - Aubreville, Marc A1 - Klopfleisch, Robert T1 - Deep Learning model predicts the c-Kit-11 mutational status of canine cutaneous mast cell tumors by HE stained histological slides N2 - Numerous prognostic factors are currently assessed histopathologically in biopsies of canine mast cell tumors to evaluate clinical behavior. In addition, PCR analysis of the c-Kit exon 11 mutational status is often performed to evaluate the potential success of a tyrosine kinase inhibitor therapy. This project aimed at training deep learning models (DLMs) to identify the c-Kit-11 mutational status of MCTs solely based on morphology without additional molecular analysis. HE slides of 195 mutated and 173 non-mutated tumors were stained consecutively in two different laboratories and scanned with three different slide scanners. This resulted in six different datasets (stain-scanner variations) of whole slide images. DLMs were trained with single and mixed datasets and their performances was assessed under scanner and staining domain shifts. The DLMs correctly classified HE slides according to their c-Kit 11 mutation status in, on average, 87% of cases for the best-suited stain-scanner variant. A relevant performance drop could be observed when the stain-scanner combination of the training and test dataset differed. Multi-variant datasets improved the average accuracy but did not reach the maximum accuracy of algorithms trained and tested on the same stain-scanner variant. In summary, DLM-assisted morphological examination of MCTs can predict c-Kit-exon 11 mutational status of MCTs with high accuracy. However, the recognition performance is impeded by a change of scanner or staining protocol. Larger data sets with higher numbers of scans originating from different laboratories and scanners may lead to more robust DLMs to identify c-Kit mutations in HE slides. UR - https://doi.org/10.48550/arXiv.2401.06169 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2401.06169 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-46020 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - Field of Interest Proposal for Augmented Mitotic Cell Count BT - Comparison of Two Convolutional Networks T2 - Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOIMAGING UR - https://doi.org/10.5220/0007365700300037 KW - Mitotic Figure KW - Cell Segmentation KW - Digital Histopathology KW - Tumor Grading Y1 - 2019 UR - https://doi.org/10.5220/0007365700300037 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-19248 SN - 978-989-758-353-7 SN - 2184-4305 VL - 2 SP - 30 EP - 37 PB - SciTePress CY - Setúbal ER - TY - JOUR A1 - Bertram, Christof A1 - Aubreville, Marc A1 - Donovan, Taryn A1 - Bartel, Alexander A1 - Wilm, Frauke A1 - Marzahl, Christian A1 - Assenmacher, Charles-Antoine A1 - Becker, Kathrin A1 - Bennett, Mark A1 - Corner, Sarah M. A1 - Cossic, Brieuc A1 - Denk, Daniela A1 - Dettwiler, Martina A1 - Garcia Gonzalez, Beatriz A1 - Gurtner, Corinne A1 - Haverkamp, Ann-Kathrin A1 - Heier, Annabelle A1 - Lehmbecker, Annika A1 - Merz, Sophie A1 - Noland, Erica L. A1 - Plog, Stephanie A1 - Schmidt, Anja A1 - Sebastian, Franziska A1 - Sledge, Dodd G. A1 - Smedley, Rebecca C. A1 - Tecilla, Marco A1 - Thaiwong, Tuddow A1 - Fuchs-Baumgartinger, Andrea A1 - Meuten, Donald J. A1 - Breininger, Katharina A1 - Kiupel, Matti A1 - Maier, Andreas A1 - Klopfleisch, Robert T1 - Computer-assisted mitotic count using a deep learning–based algorithm improves interobserver reproducibility and accuracy JF - Veterinary Pathology N2 - 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. UR - https://doi.org/10.1177/03009858211067478 KW - canine cutaneous mast cell tumors KW - artificial intelligence KW - digital pathology KW - deep learning KW - mitotic figures KW - mitotic count KW - automated image analysis KW - computer assistance Y1 - 2021 UR - https://doi.org/10.1177/03009858211067478 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-13141 SN - 1544-2217 VL - 59 IS - 2 SP - 211 EP - 226 PB - Sage CY - London ER - TY - JOUR A1 - Marzahl, Christian A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Stayt, Jason A1 - Jasensky, Anne-Katherine A1 - Bartenschlager, Florian A1 - Fragoso-Garcia, Marco A1 - Barton, Ann K. A1 - Elsemann, Svenja A1 - Jabari, Samir A1 - Krauth, Jens A1 - Madhu, Prathmesh A1 - Voigt, Jörn A1 - Hill, Jenny A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - Deep Learning-based quantification of pulmonary hemosiderophages in cytology slides JF - Scientific Reports N2 - Exercise-induced pulmonary hemorrhage (EIPH) is a common condition in sport horses with negative impact on performance. Cytology of bronchoalveolar lavage fluid by use of a scoring system is considered the most sensitive diagnostic method. Macrophages are classified depending on the degree of cytoplasmic hemosiderin content. The current gold standard is manual grading, which is however monotonous and time-consuming. We evaluated state-of-the-art deep learning-based methods for single cell macrophage classification and compared them against the performance of nine cytology experts and evaluated inter- and intra-observer variability. Additionally, we evaluated object detection methods on a novel data set of 17 completely annotated cytology whole slide images (WSI) containing 78,047 hemosiderophages. Our deep learning-based approach reached a concordance of 0.85, partially exceeding human expert concordance (0.68 to 0.86, mean of 0.73, SD of 0.04). Intra-observer variability was high (0.68 to 0.88) and inter-observer concordance was moderate (Fleiss’ kappa = 0.67). Our object detection approach has a mean average precision of 0.66 over the five classes from the whole slide gigapixel image and a computation time of below two minutes. To mitigate the high inter- and intra-rater variability, we propose our automated object detection pipeline, enabling accurate, reproducible and quick EIPH scoring in WSI. UR - https://doi.org/10.1038/s41598-020-65958-2 Y1 - 2020 UR - https://doi.org/10.1038/s41598-020-65958-2 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-11783 SN - 2045-2322 VL - 10 PB - Springer Nature CY - London ER - TY - JOUR A1 - Donovan, Taryn A1 - Moore, Frances M. A1 - Bertram, Christof A1 - Luong, Richard A1 - Bolfa, Pompei A1 - Klopfleisch, Robert A1 - Tvedten, Harold A1 - Salas, Elisa N. A1 - Whitley, Derick A1 - Aubreville, Marc A1 - Meuten, Donald J. T1 - Mitotic Figures - Normal, Atypical, and Imposters: A Guide to Identification JF - Veterinary pathology UR - https://doi.org/10.1177/0300985820980049 KW - mitotic figure KW - mitotic count KW - MC KW - prophase KW - prometaphase KW - metaphase KW - anaphase KW - telophase KW - computational pathology KW - CPATH KW - artificial intelligence KW - AI KW - whole slide image KW - WSI KW - pathology KW - oncology Y1 - 2021 UR - https://doi.org/10.1177/0300985820980049 SN - 1544-2217 VL - 58 IS - 2 SP - 243 EP - 257 PB - Sage CY - London ER - TY - CHAP A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Maier, Andreas ED - Handels, Heinz ED - Deserno, Thomas Martin ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Augmented mitotic cell count using field of interest proposal T2 - Bildverarbeitung für die Medizin 2019, Algorithmen – Systeme – Anwendungen, Proceedings des Workshops vom 17. bis 19. März 2019 in Lübeck UR - https://doi.org/10.1007/978-3-658-25326-4_71 Y1 - 2019 UR - https://doi.org/10.1007/978-3-658-25326-4_71 SN - 978-3-658-25325-7 SN - 978-3-658-25326-4 N1 - Access to this content is enabled by Nationallizenz Ebooks Medicine SP - 321 EP - 326 PB - Springer Vieweg CY - Wiesbaden ER - TY - INPR A1 - Ganz, Jonathan A1 - Marzahl, Christian A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Richter, Barbara A1 - Puget, Chloé A1 - Denk, Daniela A1 - Demeter, Elena A. A1 - Tabaran, Flaviu A. A1 - Wasinger, Gabriel A1 - Lipnik, Karoline A1 - Tecilla, Marco A1 - Valentine, Matthew J. A1 - Dark, Michael A1 - Abele, Niklas A1 - Bolfa, Pompei A1 - Erber, Ramona A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Donovan, Taryn A1 - Jabari, Samir A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Information Mismatch in PHH3-Assisted Mitosis Annotation Leads to Interpretation Shifts in H&E Slide Analysis T2 - Research Square N2 - The count of mitotic figures (MFs) observed in hematoxylin and eosin (H&E)-stained slides is an important prognostic marker, as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. In a computer-aided setting, deep learning algorithms can help to mitigate this, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithms' performance. Unlike H&E, where identification of MFs is based mainly on morphological features, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H&E staining alone, the use of this ground truth could potentially introduce an interpretation shift and even label noise into the H&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. Subsequently, MF detectors, including a novel dual-stain detector, were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models' performance. We found that the annotators' object-level agreement significantly increased when using PHH3-assisted labeling (F1: 0.53 to 0.74). However, this enhancement in label consistency did not translate to improved performance for H&E-based detectors, neither during the training phase nor the evaluation phase. Conversely, the dual-stain detector was able to benefit from the higher consistency. This reveals an information mismatch between the H&E and PHH3-stained images as the cause of this effect, which renders PHH3-assisted annotations not well-aligned for use with H&E-based detectors. Based on our findings, we propose an improved PHH3-assisted labeling procedure. UR - https://doi.org/10.21203/rs.3.rs-4900505/v1 Y1 - 2024 UR - https://doi.org/10.21203/rs.3.rs-4900505/v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-57630 SN - 2693-5015 PB - Research Square CY - Durham ER - TY - JOUR A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Marzahl, Christian A1 - Gurtner, Corinne A1 - Dettwiler, Martina A1 - Schmidt, Anja A1 - Bartenschlager, Florian A1 - Merz, Sophie A1 - Fragoso-Garcia, Marco A1 - Kershaw, Olivia A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - Deep learning algorithms out-perform veterinary pathologists in detecting the mitotically most active tumor region JF - Scientific reports N2 - Manual count of mitotic figures, which is determined in the tumor region with the highest mitotic activity, is a key parameter of most tumor grading schemes. It can be, however, strongly dependent on the area selection due to uneven mitotic figure distribution in the tumor section. We aimed to assess the question, how significantly the area selection could impact the mitotic count, which has a known high inter-rater disagreement. On a data set of 32 whole slide images of H&E-stained canine cutaneous mast cell tumor, fully annotated for mitotic figures, we asked eight veterinary pathologists (five board-certified, three in training) to select a field of interest for the mitotic count. To assess the potential difference on the mitotic count, we compared the mitotic count of the selected regions to the overall distribution on the slide. Additionally, we evaluated three deep learning-based methods for the assessment of highest mitotic density: In one approach, the model would directly try to predict the mitotic count for the presented image patches as a regression task. The second method aims at deriving a segmentation mask for mitotic figures, which is then used to obtain a mitotic density. Finally, we evaluated a two-stage object-detection pipeline based on state-of-the-art architectures to identify individual mitotic figures. We found that the predictions by all models were, on average, better than those of the experts. The two-stage object detector performed best and outperformed most of the human pathologists on the majority of tumor cases. The correlation between the predicted and the ground truth mitotic count was also best for this approach (0.963–0.979). Further, we found considerable differences in position selection between pathologists, which could partially explain the high variance that has been reported for the manual mitotic count. To achieve better inter-rater agreement, we propose to use a computer-based area selection for support of the pathologist in the manual mitotic count. UR - https://doi.org/10.1038/s41598-020-73246-2 Y1 - 2020 UR - https://doi.org/10.1038/s41598-020-73246-2 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-11794 SN - 2045-2322 VL - 10 PB - Springer Nature CY - London ER - TY - INPR A1 - Ammeling, Jonas A1 - Hecker, Moritz A1 - Ganz, Jonathan A1 - Donovan, Taryn A1 - Klopfleisch, Robert A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Automated Volume Corrected Mitotic Index Calculation Through Annotation-Free Deep Learning using Immunohistochemistry as Reference Standard N2 - The volume-corrected mitotic index (M/V-Index) was shown to provide prognostic value in invasive breast carcinomas. However, despite its prognostic significance, it is not established as the standard method for assessing aggressive biological behaviour, due to the high additional workload associated with determining the epithelial proportion. In this work, we show that using a deep learning pipeline solely trained with an annotation-free, immunohistochemistry-based approach, provides accurate estimations of epithelial segmentation in canine breast carcinomas. We compare our automatic framework with the manually annotated M/V-Index in a study with three board-certified pathologists. Our results indicate that the deep learning-based pipeline shows expert-level performance, while providing time efficiency and reproducibility. UR - https://doi.org/10.48550/arXiv.2311.08949 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2311.08949 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41549 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Bertram, Christof A1 - Aubreville, Marc A1 - Gurtner, Corinne A1 - Bartel, Alexander A1 - Corner, Sarah M. A1 - Dettwiler, Martina A1 - Kershaw, Olivia A1 - Noland, Erica L. A1 - Schmidt, Anja A1 - Sledge, Dodd G. A1 - Smedley, Rebecca C. A1 - Thaiwong, Tuddow A1 - Kiupel, Matti A1 - Maier, Andreas A1 - Klopfleisch, Robert T1 - Mitotic count in canine cutaneous mast cell tumours BT - not accurate but reproducible JF - Journal of Comparative Pathology UR - https://doi.org/10.1016/j.jcpa.2019.10.015 Y1 - 2020 UR - https://doi.org/10.1016/j.jcpa.2019.10.015 SN - 1532-3129 VL - 2020 IS - 174 SP - 143 PB - Elsevier CY - London ER - TY - INPR A1 - Wilm, Frauke A1 - Fragoso-Garcia, Marco A1 - Bertram, Christof A1 - Stathonikos, Nikolas A1 - Öttl, Mathias A1 - Qiu, Jingna A1 - Klopfleisch, Robert A1 - Maier, Andreas A1 - Aubreville, Marc A1 - Breininger, Katharina T1 - Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology UR - https://doi.org/10.48550/arXiv.2211.16141 KW - Histopathology KW - Domain Shift KW - Representation Learning KW - Barlow Twins Y1 - 2022 UR - https://doi.org/10.48550/arXiv.2211.16141 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Aubreville, Marc A1 - Krappmann, Maximilian A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - A Guided Spatial Transformer Network for Histology Cell Differentiation T2 - VCBM '17: Proceedings of the Eurographics Workshop on Visual Computing for Biology and Medicine UR - https://doi.org/10.2312/vcbm.20171233 Y1 - 2017 UR - https://doi.org/10.2312/vcbm.20171233 SN - 978-3-03868-036-9 SP - 21 EP - 25 PB - Eurographics Association CY - Goslar ER - TY - CHAP A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - SlideRunner BT - a tool for massive cell annotations in whole slide images T2 - Bildverarbeitung für die Medizin 2018: Algorithmen - Systeme - Anwendungen N2 - Large-scale image data such as digital whole-slide histology images pose a challenging task at annotation software solutions. Today, a number of good solutions with varying scopes exist. For cell annotation, however, we find that many do not match the prerequisites for fast annotations. Especially in the field of mitosis detection, it is assumed that detection accuracy could significantly benefit from larger annotation databases that are currently however very troublesome to produce. Further, multiple independent (blind) expert labels are a big asset for such databases, yet there is currently no tool for this kind of annotation available. To ease this tedious process of expert annotation and grading, we introduce SlideRunner, an open source annotation and visualization tool for digital histopathology, developed in close cooperation with two pathologists. SlideRunner is capable of setting annotations like object centers (for e.g. cells) as well as object boundaries (e.g. for tumor outlines). It provides single-click annotations as well as a blind mode for multi-annotations, where the expert is directly shown the microscopy image containing the cells that he has not yet rated. UR - https://doi.org/10.1007/978-3-662-56537-7_81 Y1 - 2018 UR - https://doi.org/10.1007/978-3-662-56537-7_81 SN - 978-3-662-56537-7 SP - 309 EP - 314 PB - Springer Vieweg CY - Berlin ER - TY - CHAP A1 - Marzahl, Christian A1 - Bertram, Christof A1 - Aubreville, Marc A1 - Petrick, Anne A1 - Weiler, Kristina A1 - Gläsel, Agnes C. A1 - Fragoso-Garcia, Marco A1 - Merz, Sophie A1 - Bartenschlager, Florian A1 - Hoppe, Judith A1 - Langenhagen, Alina A1 - Jasensky, Anne-Katherine A1 - Voigt, Jörn A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - Are Fast Labeling Methods Reliable? A Case Study of Computer-Aided Expert Annotations on Microscopy Slides T2 - Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 UR - https://doi.org/10.1007/978-3-030-59710-8_3 KW - Pathology KW - Microscopy KW - Computer-aided labelling KW - Expert-algorithm collaboration Y1 - 2020 UR - https://doi.org/10.1007/978-3-030-59710-8_3 SN - 978-3-030-59710-8 SN - 1611-3349 SP - 24 EP - 32 PB - Springer CY - Cham ER - TY - CHAP A1 - Bertram, Christof A1 - Veta, Mitko A1 - Marzahl, Christian A1 - Stathonikos, Nikolas A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Aubreville, Marc T1 - Are Pathologist-Defined Labels Reproducible? Comparison of the TUPAC16 Mitotic Figure Dataset with an Alternative Set of Labels T2 - Interpretable and Annotation-Efficient Learning for Medical Image Computing UR - https://doi.org/10.1007/978-3-030-61166-8_22 KW - Breast cancer KW - Mitotic figures KW - Computer-aided annotation KW - Deep learning Y1 - 2020 UR - https://doi.org/10.1007/978-3-030-61166-8_22 SN - 978-3-030-61166-8 SN - 1611-3349 SP - 204 EP - 213 PB - Springer CY - Cham ER - TY - CHAP A1 - Krappmann, Maximilian A1 - Aubreville, Marc A1 - Maier, Andreas A1 - Bertram, Christof A1 - Klopfleisch, Robert ED - Maier, Andreas ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Classification of Mitotic Cells BT - Potentials Beyond the Limits of Small Data Sets T2 - Bildverarbeitung für die Medizin 2018 UR - https://doi.org/10.1007/978-3-662-56537-7_66 Y1 - 2018 UR - https://doi.org/10.1007/978-3-662-56537-7_66 SN - 978-3-662-56536-0 SP - 245 EP - 250 PB - Springer CY - Berlin ER - TY - INPR A1 - Aubreville, Marc A1 - Krappmann, Maximilian A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - A Guided Spatial Transformer Network for Histology Cell Differentiation UR - https://doi.org/10.48550/arXiv.1707.08525 Y1 - 2017 UR - https://doi.org/10.48550/arXiv.1707.08525 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Haghofer, Andreas A1 - Fuchs-Baumgartinger, Andrea A1 - Lipnik, Karoline A1 - Klopfleisch, Robert A1 - Aubreville, Marc A1 - Scharinger, Josef A1 - Weissenböck, Herbert A1 - Winkler, Stephan M. A1 - Bertram, Christof T1 - Histological classification of canine and feline lymphoma using a modular approach based on deep learning and advanced image processing JF - Scientific Reports N2 - AbstractHistopathological examination of tissue samples is essential for identifying tumor malignancy and the diagnosis of different types of tumor. In the case of lymphoma classification, nuclear size of the neoplastic lymphocytes is one of the key features to differentiate the different subtypes. Based on the combination of artificial intelligence and advanced image processing, we provide a workflow for the classification of lymphoma with regards to their nuclear size (small, intermediate, and large). As the baseline for our workflow testing, we use a Unet++ model trained on histological images of canine lymphoma with individually labeled nuclei. As an alternative to the Unet++, we also used a publicly available pre-trained and unmodified instance segmentation model called Stardist to demonstrate that our modular classification workflow can be combined with different types of segmentation models if they can provide proper nuclei segmentation. Subsequent to nuclear segmentation, we optimize algorithmic parameters for accurate classification of nuclear size using a newly derived reference size and final image classification based on a pathologists-derived ground truth. Our image classification module achieves a classification accuracy of up to 92% on canine lymphoma data. Compared to the accuracy ranging from 66.67 to 84% achieved using measurements provided by three individual pathologists, our algorithm provides a higher accuracy level and reproducible results. Our workflow also demonstrates a high transferability to feline lymphoma, as shown by its accuracy of up to 84.21%, even though our workflow was not optimized for feline lymphoma images. By determining the nuclear size distribution in tumor areas, our workflow can assist pathologists in subtyping lymphoma based on the nuclei size and potentially improve reproducibility. Our proposed approach is modular and comprehensible, thus allowing adaptation for specific tasks and increasing the users’ trust in computer-assisted image classification. UR - https://doi.org/10.1038/s41598-023-46607-w Y1 - 2023 UR - https://doi.org/10.1038/s41598-023-46607-w UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41415 SN - 2045-2322 VL - 13 PB - Springer Nature CY - London ER - TY - CHAP A1 - Ganz, Jonathan A1 - Lipnik, Karoline A1 - Ammeling, Jonas A1 - Richter, Barbara A1 - Puget, Chloé A1 - Parlak, Eda A1 - Diehl, Laura A1 - Klopfleisch, Robert A1 - Donovan, Taryn A1 - Kiupel, Matti A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Deep Learning-based Automatic Assessment of AgNOR-scores in Histopathology Images T2 - Bildverarbeitung für die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, Braunschweig, July 2-4, 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_49 Y1 - 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_49 SN - 978-3-658-41657-7 SN - 978-3-658-41656-0 SP - 226 EP - 231 PB - Springer Vieweg CY - Wiesbaden ER - TY - CHAP A1 - Wilm, Frauke A1 - Fragoso-Garcia, Marco A1 - Bertram, Christof A1 - Stathonikos, Nikolas A1 - Öttl, Mathias A1 - Qiu, Jingna A1 - Klopfleisch, Robert A1 - Maier, Andreas A1 - Aubreville, Marc A1 - Breininger, Katharina T1 - Mind the Gap: Scanner-Induced Domain Shifts Pose Challenges for Representation Learning in Histopathology T2 - 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI) UR - https://doi.org/10.1109/ISBI53787.2023.10230458 KW - Histopathology KW - Domain Shift KW - Representation Learning KW - Barlow Twins Y1 - 2023 UR - https://doi.org/10.1109/ISBI53787.2023.10230458 SN - 978-1-6654-7358-3 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Aubreville, Marc A1 - Stathonikos, Nikolas A1 - Donovan, Taryn A1 - Klopfleisch, Robert A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Wilm, Frauke A1 - Veta, Mitko A1 - Jabari, Samir A1 - Eckstein, Markus A1 - Annuscheit, Jonas A1 - Krumnow, Christian A1 - Bozaba, Engin A1 - Cayir, Sercan A1 - Gu, Hongyan A1 - Chen, Xiang A1 - Jahanifar, Mostafa A1 - Shephard, Adam A1 - Kondo, Satoshi A1 - Kasai, Satoshi A1 - Kotte, Sujatha A1 - Saipradeep, Vangala A1 - Lafarge, Maxime W. A1 - Koelzer, Viktor H. A1 - Wang, Ziyue A1 - Zhang, Yongbing A1 - Yang, Sen A1 - Wang, Xiyue A1 - Breininger, Katharina A1 - Bertram, Christof T1 - Domain generalization across tumor types, laboratories, and species — Insights from the 2022 edition of the Mitosis Domain Generalization Challenge JF - Medical Image Analysis N2 - Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert majority vote and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today’s deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, with only minor changes in the order of participants in the ranking. UR - https://doi.org/10.1016/j.media.2024.103155 Y1 - 2024 UR - https://doi.org/10.1016/j.media.2024.103155 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58479 SN - 1361-8423 VL - 2024 IS - 94 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Ganz, Jonathan A1 - Marzahl, Christian A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Richter, Barbara A1 - Puget, Chloé A1 - Denk, Daniela A1 - Demeter, Elena A. A1 - Tabaran, Flaviu A. A1 - Wasinger, Gabriel A1 - Lipnik, Karoline A1 - Tecilla, Marco A1 - Valentine, Matthew J. A1 - Dark, Michael A1 - Abele, Niklas A1 - Bolfa, Pompei A1 - Erber, Ramona A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Donovan, Taryn A1 - Jabari, Samir A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Information mismatch in PHH3-assisted mitosis annotation leads to interpretation shifts in H&E slide analysis JF - Scientific Reports N2 - The count of mitotic figures (MFs) observed in hematoxylin and eosin (H&E)-stained slides is an important prognostic marker, as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. In a computer-aided setting, deep learning algorithms can help to mitigate this, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithms’ performance. Unlike H&E, where identification of MFs is based mainly on morphological features, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H&E staining alone, the use of this ground truth could potentially introduce an interpretation shift and even label noise into the H&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. Subsequently, MF detectors, including a novel dual-stain detector, were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models’ performance. We found that the annotators’ object-level agreement significantly increased when using PHH3-assisted labeling (F1: 0.53 to 0.74). However, this enhancement in label consistency did not translate to improved performance for H&E-based detectors, neither during the training phase nor the evaluation phase. Conversely, the dual-stain detector was able to benefit from the higher consistency. This reveals an information mismatch between the H&E and PHH3-stained images as the cause of this effect, which renders PHH3-assisted annotations not well-aligned for use with H&E-based detectors. Based on our findings, we propose an improved PHH3-assisted labeling procedure. UR - https://doi.org/10.1038/s41598-024-77244-6 Y1 - 2024 UR - https://doi.org/10.1038/s41598-024-77244-6 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53559 SN - 2045-2322 VL - 14 IS - 1 PB - Springer Nature CY - London ER - TY - JOUR A1 - Haghofer, Andreas A1 - Parlak, Eda A1 - Bartel, Alexander A1 - Donovan, Taryn A1 - Assenmacher, Charles-Antoine A1 - Bolfa, Pompei A1 - Dark, Michael A1 - Fuchs-Baumgartinger, Andrea A1 - Klang, Andrea A1 - Jäger, Kathrin A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Richter, Barbara A1 - Schulman, F. Yvonne A1 - Janout, Hannah A1 - Ganz, Jonathan A1 - Scharinger, Josef A1 - Aubreville, Marc A1 - Winkler, Stephan M. A1 - Kiupel, Matti A1 - Bertram, Christof T1 - Nuclear pleomorphism in canine cutaneous mast cell tumors: Comparison of reproducibility and prognostic relevance between estimates, manual morphometry, and algorithmic morphometry JF - Veterinary Pathology N2 - Variation in nuclear size and shape is an important criterion of malignancy for many tumor types; however, categorical estimates by pathologists have poor reproducibility. Measurements of nuclear characteristics can improve reproducibility, but current manual methods are time-consuming. The aim of this study was to explore the limitations of estimates and develop alternative morphometric solutions for canine cutaneous mast cell tumors (ccMCTs). We assessed the following nuclear evaluation methods for accuracy, reproducibility, and prognostic utility: (1) anisokaryosis estimates by 11 pathologists; (2) gold standard manual morphometry of at least 100 nuclei; (3) practicable manual morphometry with stratified sampling of 12 nuclei by 9 pathologists; and (4) automated morphometry using deep learning–based segmentation. The study included 96 ccMCTs with available outcome information. Inter-rater reproducibility of anisokaryosis estimates was low (k = 0.226), whereas it was good (intraclass correlation = 0.654) for practicable morphometry of the standard deviation (SD) of nuclear size. As compared with gold standard manual morphometry (area under the ROC curve [AUC] = 0.839, 95% confidence interval [CI] = 0.701–0.977), the prognostic value (tumor-specific survival) of SDs of nuclear area for practicable manual morphometry and automated morphometry were high with an AUC of 0.868 (95% CI = 0.737–0.991) and 0.943 (95% CI = 0.889–0.996), respectively. This study supports the use of manual morphometry with stratified sampling of 12 nuclei and algorithmic morphometry to overcome the poor reproducibility of estimates. Further studies are needed to validate our findings, determine inter-algorithmic reproducibility and algorithmic robustness, and explore tumor heterogeneity of nuclear features in entire tumor sections. UR - https://doi.org/10.1177/03009858241295399 Y1 - 2024 UR - https://doi.org/10.1177/03009858241295399 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53661 SN - 1544-2217 SN - 0300-9858 VL - 62 IS - 2 SP - 161 EP - 177 PB - Sage CY - London ER - TY - JOUR A1 - Stathonikos, Nikolas A1 - Aubreville, Marc A1 - de Vries, Sjoerd A1 - Wilm, Frauke A1 - Bertram, Christof A1 - Veta, Mitko A1 - van Diest, Paul J T1 - Breast cancer survival prediction using an automated mitosis detection pipeline JF - The Journal of Pathology: Clinical Research N2 - AbstractMitotic count (MC) is the most common measure to assess tumor proliferation in breast cancer patients and is highly predictive of patient outcomes. It is, however, subject to inter‐ and intraobserver variation and reproducibility challenges that may hamper its clinical utility. In past studies, artificial intelligence (AI)‐supported MC has been shown to correlate well with traditional MC on glass slides. Considering the potential of AI to improve reproducibility of MC between pathologists, we undertook the next validation step by evaluating the prognostic value of a fully automatic method to detect and count mitoses on whole slide images using a deep learning model. The model was developed in the context of the Mitosis Domain Generalization Challenge 2021 (MIDOG21) grand challenge and was expanded by a novel automatic area selector method to find the optimal mitotic hotspot and calculate the MC per 2 mm2. We employed this method on a breast cancer cohort with long‐term follow‐up from the University Medical Centre Utrecht (N = 912) and compared predictive values for overall survival of AI‐based MC and light‐microscopic MC, previously assessed during routine diagnostics. The MIDOG21 model was prognostically comparable to the original MC from the pathology report in uni‐ and multivariate survival analysis. In conclusion, a fully automated MC AI algorithm was validated in a large cohort of breast cancer with regard to retained prognostic value compared with traditional light‐microscopic MC. UR - https://doi.org/10.1002/2056-4538.70008 Y1 - 2024 UR - https://doi.org/10.1002/2056-4538.70008 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53087 SN - 2056-4538 VL - 10 IS - 6 PB - Wiley CY - Chichester ER - TY - JOUR A1 - Glahn, Imaine A1 - Haghofer, Andreas A1 - Donovan, Taryn A1 - Degasperi, Brigitte A1 - Bartel, Alexander A1 - Kreilmeier-Berger, Theresa A1 - Hyndman, Philip S. A1 - Janout, Hannah A1 - Assenmacher, Charles-Antoine A1 - Bartenschlager, Florian A1 - Bolfa, Pompei A1 - Dark, Michael A1 - Klang, Andrea A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Richter, Barbara A1 - Schulman, F. Yvonne A1 - Ganz, Jonathan A1 - Scharinger, Josef A1 - Aubreville, Marc A1 - Winkler, Stephan M. A1 - Bertram, Christof T1 - Automated Nuclear Morphometry: A Deep Learning Approach for Prognostication in Canine Pulmonary Carcinoma to Enhance Reproducibility JF - Veterinary Sciences N2 - The integration of deep learning-based tools into diagnostic workflows is increasingly prevalent due to their efficiency and reproducibility in various settings. We investigated the utility of automated nuclear morphometry for assessing nuclear pleomorphism (NP), a criterion of malignancy in the current grading system in canine pulmonary carcinoma (cPC), and its prognostic implications. We developed a deep learning-based algorithm for evaluating NP (variation in size, i.e., anisokaryosis and/or shape) using a segmentation model. Its performance was evaluated on 46 cPC cases with comprehensive follow-up data regarding its accuracy in nuclear segmentation and its prognostic ability. Its assessment of NP was compared to manual morphometry and established prognostic tests (pathologists’ NP estimates (n = 11), mitotic count, histological grading, and TNM-stage). The standard deviation (SD) of the nuclear area, indicative of anisokaryosis, exhibited good discriminatory ability for tumor-specific survival, with an area under the curve (AUC) of 0.80 and a hazard ratio (HR) of 3.38. The algorithm achieved values comparable to manual morphometry. In contrast, the pathologists’ estimates of anisokaryosis resulted in HR values ranging from 0.86 to 34.8, with slight inter-observer reproducibility (k = 0.204). Other conventional tests had no significant prognostic value in our study cohort. Fully automated morphometry promises a time-efficient and reproducible assessment of NP with a high prognostic value. Further refinement of the algorithm, particularly to address undersegmentation, and application to a larger study population are required. UR - https://doi.org/10.3390/vetsci11060278 Y1 - 2024 UR - https://doi.org/10.3390/vetsci11060278 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-48612 SN - 2306-7381 VL - 11 IS - 6 PB - MDPI CY - Basel ER - TY - CHAP A1 - Ammeling, Jonas A1 - Hecker, Moritz A1 - Ganz, Jonathan A1 - Donovan, Taryn A1 - Klopfleisch, Robert A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Maier, Andreas ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Automated Mitotic Index Calculation via Deep Learning and Immunohistochemistry T2 - Bildverarbeitung für die Medizin 2024: Proceedings, German Conference on Medical Image Computing, Erlangen, March 10–12, 2024 UR - https://doi.org/10.1007/978-3-658-44037-4_37 Y1 - 2024 UR - https://doi.org/10.1007/978-3-658-44037-4_37 SN - 978-3-658-44037-4 SP - 123 EP - 128 PB - Springer Vieweg CY - Wiesbaden ER - TY - JOUR A1 - Fragoso-Garcia, Marco A1 - Wilm, Frauke A1 - Bertram, Christof A1 - Merz, Sophie A1 - Schmidt, Anja A1 - Donovan, Taryn A1 - Fuchs-Baumgartinger, Andrea A1 - Bartel, Alexander A1 - Marzahl, Christian A1 - Diehl, Laura A1 - Puget, Chloe A1 - Maier, Andreas A1 - Aubreville, Marc A1 - Breininger, Katharina A1 - Klopfleisch, Robert T1 - Automated diagnosis of 7 canine skin tumors using machine learning on H&E-stained whole slide images JF - Veterinary Pathology N2 - 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. UR - https://doi.org/10.1177/03009858231189205 KW - computer-aided diagnosis KW - computational pathology KW - digital pathology KW - dog KW - machine learning KW - skin KW - veterinary oncology Y1 - 2023 UR - https://doi.org/10.1177/03009858231189205 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-38321 SN - 0300-9858 VL - 60 IS - 6 SP - 865 EP - 875 PB - Sage CY - London ER - TY - CHAP A1 - Ammeling, Jonas A1 - Manger, Carina A1 - Kwaka, Elias A1 - Krügel, Sebastian A1 - Uhl, Matthias A1 - Kießig, Angelika A1 - Fritz, Alexis A1 - Ganz, Jonathan A1 - Riener, Andreas A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Stolze, Markus ED - Loch, Frieder ED - Baldauf, Matthias ED - Alt, Florian ED - Schneegass, Christina ED - Kosch, Thomas ED - Hirzle, Teresa ED - Sadeghian, Shadan ED - Draxler, Fiona ED - Bektas, Kenan ED - Lohan, Katrin ED - Knierim, Pascal T1 - Appealing but Potentially Biasing - Investigation of the Visual Representation of Segmentation Predictions by AI Recommender Systems for Medical Decision Making T2 - Mensch und Computer 2023: Building Bridges: Tagungsband (Proceedings) UR - https://doi.org/10.1145/3603555.3608561 Y1 - 2023 UR - https://doi.org/10.1145/3603555.3608561 SN - 979-8-4007-0771-1 SP - 330 EP - 335 PB - ACM CY - New York ER - TY - CHAP A1 - Aubreville, Marc A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Donovan, Taryn A1 - Fick, Rutger H. J. A1 - Breininger, Katharina A1 - Bertram, Christof ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Deep Learning-based Subtyping of Atypical and Normal Mitoses using a Hierarchical Anchor-free Object Detector T2 - Bildverarbeitung für die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, Braunschweig, July 2-4, 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_40 Y1 - 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_40 SN - 978-3-658-41657-7 SN - 978-3-658-41656-0 SP - 189 EP - 195 PB - Springer Vieweg CY - Wiesbaden ER - TY - CHAP A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Aubreville, Marc ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Limits of Human Expert Ensembles in Mitosis Multi-expert Ground Truth Generation T2 - Bildverarbeitung für die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, Braunschweig, July 2-4, 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_27 Y1 - 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_27 SN - 978-3-658-41657-7 SN - 978-3-658-41656-0 SP - 116 EP - 121 PB - Springer Vieweg CY - Wiesbaden ER - TY - JOUR A1 - Aubreville, Marc A1 - Stathonikos, Nikolas A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Hoeve, Natalie ter A1 - Ciompi, Francesco A1 - Wilm, Frauke A1 - Marzahl, Christian A1 - Donovan, Taryn A1 - Maier, Andreas A1 - Breen, Jack A1 - Ravikumar, Nishant A1 - Chung, Youjin A1 - Park, Jinah A1 - Nateghi, Ramin A1 - Pourakpour, Fattaneh A1 - Fick, Rutger H. J. A1 - Ben Hadj, Saima A1 - Jahanifar, Mostafa A1 - Shepard, Adam A1 - Dexl, Jakob A1 - Wittenberg, Thomas A1 - Kondo, Satoshi A1 - Lafarge, Maxime W. A1 - Kolezer, Viktor H. A1 - Liang, Jingtang A1 - Wang, Yubo A1 - Long, Xi A1 - Liu, Jingxin A1 - Razavi, Salar A1 - Khademi, April A1 - Yang, Sen A1 - Wang, Xiyue A1 - Erber, Ramona A1 - Klang, Andrea A1 - Lipnik, Karoline A1 - Bolfa, Pompei A1 - Dark, Michael A1 - Wasinger, Gabriel A1 - Veta, Mitko A1 - Breininger, Katharina T1 - Mitosis domain generalization in histopathology images — The MIDOG challenge JF - Medical Image Analysis UR - https://doi.org/10.1016/j.media.2022.102699 KW - Domain generalization KW - Histopathology KW - Challenge KW - Deep Learning KW - Mitosis Y1 - 2022 UR - https://doi.org/10.1016/j.media.2022.102699 SN - 1361-8423 SN - 1361-8415 VL - 2023 IS - 84 PB - Elsevier CY - Amsterdam ER - TY - CHAP A1 - Theelke, Luisa A1 - Wilm, Frauke A1 - Marzahl, Christian A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Maier, Andreas A1 - Aubreville, Marc A1 - Breininger, Katharina T1 - Iterative Cross-Scanner Registration for Whole Slide Images T2 - 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) UR - https://doi.org/10.1109/ICCVW54120.2021.00071 KW - Pathology KW - Computer vision KW - Image resolution KW - Microscopy KW - Conferences KW - Estimation KW - Registers Y1 - 2021 UR - https://doi.org/10.1109/ICCVW54120.2021.00071 SN - 978-1-6654-0191-3 SN - 2473-9944 N1 - Eine frei zugängliche Version ist veröffentlicht unter: https://openaccess.thecvf.com/content/ICCV2021W/CDPath/html/Theelke_Iterative_Cross-Scanner_Registration_for_Whole_Slide_Images_ICCVW_2021_paper.html SP - 582 EP - 590 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Stathonikos, Nikolas A1 - ter Hoeve, Natalie A1 - Ciompi, Francesco A1 - Klopfleisch, Robert A1 - Veta, Mitko A1 - Donovan, Taryn A1 - Marzahl, Christian A1 - Wilm, Frauke A1 - Breininger, Katharina A1 - Maier, Andreas T1 - Quantifying the Scanner-Induced Domain Gap in Mitosis Detection T2 - MIDL: Medical Imaging with Deep Learning 2021 Y1 - 2021 UR - https://2021.midl.io/papers/i6 PB - MIDL Foundation CY - Nijmegen ER - TY - JOUR A1 - Bertram, Christof A1 - Marzahl, Christian A1 - Bartel, Alexander A1 - Stayt, Jason A1 - Bonsembiante, Federico A1 - Beeler-Marfisi, Janet A1 - Barton, Ann K. A1 - Brocca, Ginevra A1 - Gelain, Maria Elena A1 - Gläsel, Agnes C. A1 - du Preez, Kelly A1 - Weiler, Kristina A1 - Weissenbacher-Lang, Christiane A1 - Breininger, Katharina A1 - Aubreville, Marc A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Hill, Jenny T1 - Cytologic scoring of equine exercise-induced pulmonary hemorrhage: Performance of human experts and a deep learning-based algorithm JF - Veterinary Pathology N2 - 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. UR - https://doi.org/10.1177/03009858221137582 KW - artificial intelligence KW - automated image analysis KW - bronchoalveolar lavage fluid KW - computational pathology KW - digital pathology KW - equine KW - pulmonary hemorrhage KW - respiratory disease KW - total hemosiderin score Y1 - 2022 UR - https://doi.org/10.1177/03009858221137582 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-35196 SN - 1544-2217 VL - 60 IS - 1 SP - 75 EP - 85 PB - Sage CY - London ER - TY - JOUR A1 - Marzahl, Christian A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Maier, Jennifer A1 - Bergler, Christian A1 - Kröger, Christine A1 - Voigt, Jörn A1 - Breininger, Katharina A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - EXACT: a collaboration toolset for algorithm-aided annotation of images with annotation version control JF - Scientific Reports N2 - 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. UR - https://doi.org/10.1038/s41598-021-83827-4 Y1 - 2021 UR - https://doi.org/10.1038/s41598-021-83827-4 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-10943 SN - 2045-2322 VL - 11 PB - Springer Nature CY - London ER - TY - JOUR A1 - Meuten, Donald J. A1 - Moore, Frances M. A1 - Donovan, Taryn A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Foster, Robert A. A1 - Smedley, Rebecca C. A1 - Dark, Michael A1 - Milovancev, Milan A1 - Stromberg, Paul A1 - Williams, Bruce H. A1 - Aubreville, Marc A1 - Avallone, Giancarlo A1 - Bolfa, Pompei A1 - Cullen, John A1 - Dennis, Michelle M. A1 - Goldschmidt, Michael A1 - Luong, Richard A1 - Miller, Andrew D. A1 - Miller, Margaret A. A1 - Munday, John S. A1 - Roccabianca, Paola A1 - Salas, Elisa N. A1 - Schulman, F. Yvonne A1 - Laufer-Amorim, Renee A1 - Asakawa, Midori G. A1 - Craig, Linden A1 - Dervisis, Nick A1 - Esplin, D. Glen A1 - George, Jeanne W. A1 - Hauck, Marlene A1 - Kagawa, Yumiko A1 - Kiupel, Matti A1 - Linder, Keith A1 - Meichner, Kristina A1 - Marconato, Laura A1 - Oblak, Michelle L. A1 - Santos, Renato L. A1 - Simpson, R. Mark A1 - Tvedten, Harold A1 - Whitley, Derick T1 - International Guidelines for Veterinary Tumor Pathology: A Call to Action JF - Veterinary Pathology UR - https://doi.org/10.1177/03009858211013712 KW - standardization KW - oncology KW - guidelines KW - protocols KW - validation Y1 - 2021 UR - https://doi.org/10.1177/03009858211013712 SN - 1544-2217 VL - 58 IS - 5 SP - 766 EP - 794 PB - Sage CY - London ER - TY - CHAP A1 - Wilm, Frauke A1 - Bertram, Christof A1 - Marzahl, Christian A1 - Bartel, Alexander A1 - Donovan, Taryn A1 - Assenmacher, Charles-Antoine A1 - Becker, Kathrin A1 - Bennett, Mark A1 - Corner, Sarah M. A1 - Cossic, Brieuc A1 - Denk, Daniela A1 - Dettwiler, Martina A1 - Garcia Gonzalez, Beatriz A1 - Gurtner, Corinne A1 - Heier, Annabelle A1 - Lehmbecker, Annika A1 - Merz, Sophie A1 - Plog, Stephanie A1 - Schmidt, Anja A1 - Sebastian, Franziska A1 - Smedley, Rebecca C. A1 - Tecilla, Marco A1 - Thaiwong, Tuddow A1 - Breininger, Katharina A1 - Kiupel, Matti A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Aubreville, Marc T1 - Influence of inter-annotator variability on automatic mitotic figure assessment T2 - Bildverarbeitung für die Medizin 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_56 Y1 - 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_56 SN - 978-3-658-33198-6 SP - 241 EP - 246 PB - Springer CY - Wiesbaden ER - TY - CHAP A1 - Bertram, Christof A1 - Donovan, Taryn A1 - Tecilla, Marco A1 - Bartenschlager, Florian A1 - Fragoso-Garcia, Marco A1 - Wilm, Frauke A1 - Marzahl, Christian A1 - Breininger, Katharina A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Aubreville, Marc T1 - Dataset on bi- and multi-nucleated tumor cells in canine cutaneous mast cell tumors T2 - Bildverarbeitung für die Medizin 2021: Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7–9, 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_33 Y1 - 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_33 SN - 978-3-658-33197-9 SN - 978-3-658-33198-6 SN - 1431-472X SP - 134 EP - 139 PB - Springer Vieweg CY - Wiesbaden ER - TY - CHAP A1 - Marzahl, Christian A1 - Bertram, Christof A1 - Wilm, Frauke A1 - Voigt, Jörn A1 - Barton, Ann K. A1 - Klopfleisch, Robert A1 - Breininger, Katharina A1 - Maier, Andreas A1 - Aubreville, Marc T1 - Cell detection for asthma on partially annotated whole slide images BT - learning to be EXACT T2 - Bildverarbeitung für die Medizin 2021: Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7–9, 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_36 Y1 - 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_36 SN - 978-3-658-33197-9 SN - 978-3-658-33198-6 SN - 1431-472X SP - 147 EP - 152 PB - Springer Vieweg CY - Wiesbaden ER - TY - JOUR A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Benchmarking Foundation Models for Mitotic Figure Classification JF - Machine Learning for Biomedical Imaging N2 - The performance of deep learning models is known to scale with data quantity and diversity. In pathology, as in many other medical imaging domains, the availability of labeled images for a specific task is often limited. Self-supervised learning techniques have enabled the use of vast amounts of unlabeled data to train large-scale neural networks, i.e., foundation models, that can address the limited data problem by providing semantically rich feature vectors that can generalize well to new tasks with minimal training effort increasing model performance and robustness. In this work, we investigate the use of foundation models for mitotic figure classification. The mitotic count, which can be derived from this classification task, is an independent prognostic marker for specific tumors and part of certain tumor grading systems. In particular, we investigate the data scaling laws on multiple current foundation models and evaluate their robustness to unseen tumor domains. Next to the commonly used linear probing paradigm, we also adapt the models using low-rank adaptation (LoRA) of their attention mechanisms. We compare all models against end-to-end-trained baselines, both CNNs and Vision Transformers. Our results demonstrate that LoRA-adapted foundation models provide superior performance to those adapted with standard linear probing, reaching performance levels close to 100 % data availability with only 10 % of training data. Furthermore, LoRA-adaptation of the most recent foundation models almost closes the out-of-domain performance gap when evaluated on unseen tumor domains. However, full fine-tuning of traditional architectures still yields competitive performance. UR - https://doi.org/10.59275/j.melba.2026-a3eb Y1 - 2026 UR - https://doi.org/10.59275/j.melba.2026-a3eb UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-66220 SN - 2766-905X VL - 3 IS - MELBA–BVM 2025 Special Issue SP - 38 EP - 55 PB - Melba editors CY - [s. l.] ER - TY - CHAP A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Palm, Christoph ED - Breininger, Katharina ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Tolxdorff, Thomas T1 - Is Self-supervision Enough? BT - Benchmarking Foundation Models Against End-to-end Training for Mitotic Figure Classification T2 - Bildverarbeitung für die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09–11, 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_15 Y1 - 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_15 SN - 978-3-658-47422-5 SP - 63 EP - 68 PB - Springer Vieweg CY - Wiesbaden ER -