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

Journal: Communications biology
PMID: 39702417

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.

Authors

  • Zhuoyan Shen
    Department of Medical Physics and Biomedical Engineering, University College London, London, UK. zhuoyan.shen.18@ucl.ac.uk.
  • Mikaël Simard
  • Douglas Brand
    Department of Medical Physics and Biomedical Engineering, University College London, London, UK.
  • Vanghelita Andrei
    Research Department of Pathology, University College London Cancer Institute, London, UK.
  • Ali Al-Khader
    Research Department of Pathology, University College London Cancer Institute, London, UK.
  • Fatine Oumlil
    Cellular and Molecular Pathology, Royal National Orthopaedic Hospital NHS Foundation Trust, Middlesex, UK.
  • Katherine Trevers
    Research Department of Pathology, University College London Cancer Institute, London, UK.
  • Thomas Butters
    Research Department of Pathology, University College London Cancer Institute, London, UK.
  • Simon Haefliger
    Research Department of Pathology, University College London Cancer Institute, London, UK.
  • Eleanna Kara
    Department of Neurology, Rutgers Biomedical and Health Sciences, Rutgers University, NJ, USA.
  • Fernanda Amary
    Research Department of Pathology, University College London Cancer Institute, London, UK.
  • Roberto Tirabosco
    Research Department of Pathology, University College London Cancer Institute, London, UK.
  • Paul Cool
    Department of Orthopaedics, The Robert Jones and Agnes Hunt Orthopaedic Hospital, Oswestry, UK.
  • Gary Royle
    Department of Medical Physics and Biomedical Engineering, University College London, London, UK.
  • Maria A Hawkins
    Department of Medical Physics and Biomedical Engineering, University College London, London, UK.
  • Adrienne M Flanagan
    Research Department of Pathology, University College London Cancer Institute, London, UK.
  • Charles-Antoine Collins-Fekete
    Department of Medical Physics and Biomedical Engineering, University College London, London, UK.

Keywords

External Resources

Popular Topics
Recent Journals