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 - 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 -