A deep learning framework deploying segment anything to detect pan-cancer mitotic figures from haematoxylin and eosin-stained slides

Shen, Zhuoyan; Simard, Mikaël; Brand, Douglas; Andrei, Vanghelita; Al-Khader, Ali; Oumlil, Fatine; Trevers, Katherine; Butters, Thomas; Haefliger, Simon; Kara, Eleanna; Amary, Fernanda; Tirabosco, Roberto; Cool, Paul; Royle, Gary; Hawkins, Maria A.; Flanagan, Adrienne M.; Collins-Fekete, Charles-Antoine

Abstract

Mitotic activity is an important feature for grading several cancer types. However, counting mitotic figures (cells in division) is a time-consuming and laborious task prone to inter-observer variation. Inaccurate recognition of MFs can lead to incorrect grading and hence potential suboptimal treatment. This study presents an artificial intelligence-based approach to detect mitotic figures in digitised whole-slide images stained with haematoxylin and eosin. Advances in this area are hampered by the small size and variety of datasets available. To address this, we create the largest dataset of mitotic figures (N = 74,620), combining an in-house dataset of soft tissue tumours with five open-source datasets. We then employ a two-stage framework, named the Optimised Mitoses Generator Network (OMG-Net), to identify mitotic figures. This framework first deploys the Segment Anything Model to automatically outline cells, followed by an adapted ResNet18 that distinguishes mitotic figures. OMG-Net achieves an F1 score of 0.84 in detecting pan-cancer mitotic figures, including human breast carcinoma, neuroendocrine tumours, and melanoma. It outperforms previous state-of-the-art models in hold-out test sets. To summarise, our study introduces a generalisable data creation and curation pipeline and a high-performance detection model, which can largely contribute to the field of computer-aided mitotic figure detection.

Citation

Shen, Z., Simard, M., Brand, D., Andrei, V., Al-Khader, A., Oumlil, F., Trevers, K., Butters, T., Haefliger, S., Kara, E., Amary, F., Tirabosco, R., Cool, P., Royle, G., Hawkins, M. A., Flanagan, A. M., & Collins-Fekete, C.-A. (in press). A deep learning framework deploying segment anything to detect pan-cancer mitotic figures from haematoxylin and eosin-stained slides. Communications Biology, 7(1), 1674. https://doi.org/10.1038/s42003-024-07398-6

• Journal Article Type: Article
• Acceptance Date: Dec 12, 2024
• Online Publication Date: Dec 19, 2024
• Deposit Date: Jan 8, 2025
• Publicly Available Date: Jan 8, 2025
• Journal: Communications Biology
• Print ISSN: 2399-3642
• Electronic ISSN: 2399-3642
• Publisher: Nature Research
• Peer Reviewed: Peer Reviewed
• Volume: 7
• Issue: 1
• Pages: 1674
• DOI: https://doi.org/10.1038/s42003-024-07398-6
• Public URL: https://keele-repository.worktribe.com/output/1020489