Improving CNN-Based Mitosis Detection through Rescanning Annotated Glass Slides and Atypical Mitosis Subtyping

Rutger RH Fick, Christof Bertram, Marc Aubreville
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:452-464, 2024.

Abstract

The identification of mitotic figures (MFs) is a routine task in the histopathological assessment of tumor malignancy with known limitations for human observers. For a machine learning pipeline to robustly detect MFs, it must overcome a variety of conditions such as different scanners, staining protocols, tissue configurations, and organ types. In order to develop a deep learning-based algorithm that can cope with these challenges, there are two obstacles that need to be overcome: obtaining a large-scale dataset of MF annotations spread across different domains of interest, including whole slide images (WSIs) exhaustively annotated for MFs, and using the annotated MFs in an efficient training process to extract the most relevant features for classification.Our work attempts to address both of these challenges and establishes an MF detection pipeline trained solely on animal data, yet competitive on the mixed human/animal MIDOG22 dataset, and, in particular, on human breast cancer.First, we propose a processing pipeline that allows us to strengthen the true scanner robustness of our dataset by physically rescanning the glass slides of annotated WSIs and registering MF positions. To enable the use of such rescans for training, we propose a novel learning paradigm tailored for labels that match partially, which allows to account for ambiguous MF positions in the rescans caused by spurious, suboptimal fine-focus on potential MFs by the scanner. Second, we demonstrate how a multi-task learning approach for MF subtypes, including the prediction of atypical mitotic figures (AMFs), can significantly enhance a modelś ability to distinguish MFs from imposters. Our algorithm, using a standard object detection pipeline, performs very competitively with an average test set F1 value across five runs of 0.80 on the MIDOG22 training set. We also demonstrate its ability to stratify overall survival on the TCGA-BRCA dataset based on mitotic density, though it falls short of reaching significance in stratifying survival based on AMFs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-fick24a, title = {Improving CNN-Based Mitosis Detection through Rescanning Annotated Glass Slides and Atypical Mitosis Subtyping}, author = {Fick, Rutger RH and Bertram, Christof and Aubreville, Marc}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {452--464}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/fick24a/fick24a.pdf}, url = {https://proceedings.mlr.press/v250/fick24a.html}, abstract = {The identification of mitotic figures (MFs) is a routine task in the histopathological assessment of tumor malignancy with known limitations for human observers. For a machine learning pipeline to robustly detect MFs, it must overcome a variety of conditions such as different scanners, staining protocols, tissue configurations, and organ types. In order to develop a deep learning-based algorithm that can cope with these challenges, there are two obstacles that need to be overcome: obtaining a large-scale dataset of MF annotations spread across different domains of interest, including whole slide images (WSIs) exhaustively annotated for MFs, and using the annotated MFs in an efficient training process to extract the most relevant features for classification.Our work attempts to address both of these challenges and establishes an MF detection pipeline trained solely on animal data, yet competitive on the mixed human/animal MIDOG22 dataset, and, in particular, on human breast cancer.First, we propose a processing pipeline that allows us to strengthen the true scanner robustness of our dataset by physically rescanning the glass slides of annotated WSIs and registering MF positions. To enable the use of such rescans for training, we propose a novel learning paradigm tailored for labels that match partially, which allows to account for ambiguous MF positions in the rescans caused by spurious, suboptimal fine-focus on potential MFs by the scanner. Second, we demonstrate how a multi-task learning approach for MF subtypes, including the prediction of atypical mitotic figures (AMFs), can significantly enhance a modelś ability to distinguish MFs from imposters. Our algorithm, using a standard object detection pipeline, performs very competitively with an average test set F1 value across five runs of 0.80 on the MIDOG22 training set. We also demonstrate its ability to stratify overall survival on the TCGA-BRCA dataset based on mitotic density, though it falls short of reaching significance in stratifying survival based on AMFs.} }
Endnote
%0 Conference Paper %T Improving CNN-Based Mitosis Detection through Rescanning Annotated Glass Slides and Atypical Mitosis Subtyping %A Rutger RH Fick %A Christof Bertram %A Marc Aubreville %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-fick24a %I PMLR %P 452--464 %U https://proceedings.mlr.press/v250/fick24a.html %V 250 %X The identification of mitotic figures (MFs) is a routine task in the histopathological assessment of tumor malignancy with known limitations for human observers. For a machine learning pipeline to robustly detect MFs, it must overcome a variety of conditions such as different scanners, staining protocols, tissue configurations, and organ types. In order to develop a deep learning-based algorithm that can cope with these challenges, there are two obstacles that need to be overcome: obtaining a large-scale dataset of MF annotations spread across different domains of interest, including whole slide images (WSIs) exhaustively annotated for MFs, and using the annotated MFs in an efficient training process to extract the most relevant features for classification.Our work attempts to address both of these challenges and establishes an MF detection pipeline trained solely on animal data, yet competitive on the mixed human/animal MIDOG22 dataset, and, in particular, on human breast cancer.First, we propose a processing pipeline that allows us to strengthen the true scanner robustness of our dataset by physically rescanning the glass slides of annotated WSIs and registering MF positions. To enable the use of such rescans for training, we propose a novel learning paradigm tailored for labels that match partially, which allows to account for ambiguous MF positions in the rescans caused by spurious, suboptimal fine-focus on potential MFs by the scanner. Second, we demonstrate how a multi-task learning approach for MF subtypes, including the prediction of atypical mitotic figures (AMFs), can significantly enhance a modelś ability to distinguish MFs from imposters. Our algorithm, using a standard object detection pipeline, performs very competitively with an average test set F1 value across five runs of 0.80 on the MIDOG22 training set. We also demonstrate its ability to stratify overall survival on the TCGA-BRCA dataset based on mitotic density, though it falls short of reaching significance in stratifying survival based on AMFs.
APA
Fick, R.R., Bertram, C. & Aubreville, M.. (2024). Improving CNN-Based Mitosis Detection through Rescanning Annotated Glass Slides and Atypical Mitosis Subtyping. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:452-464 Available from https://proceedings.mlr.press/v250/fick24a.html.

Related Material