An interpretable deep learning model for detecting pathogenic variants of breast cancer from hematoxylin and eosin-stained pathological images.

Journal: PeerJ
PMID: 39484212

Abstract

BACKGROUND: Determining the status of breast cancer susceptibility genes () is crucial for guiding breast cancer treatment. Nevertheless, the need for genetic testing among breast cancer patients remains unmet due to high costs and limited resources. This study aimed to develop a Bi-directional Self-Attention Multiple Instance Learning (BiAMIL) algorithm to detect status from hematoxylin and eosin (H&E) pathological images.

Authors

  • Yi Li
    Wuhan Zoncare Bio-Medical Electronics Co., Ltd, Wuhan, China.
  • Xiaomin Xiong
    School of Medicine, Chongqing University, Chongqing, China.
  • Xiaohua Liu
    Bioengineering College of Chongqing University, Chongqing, China.
  • Yihan Wu
    Center for Magnetic Resonance Research(CMRR), Department of Radiology, University of Minnesota, Minneapolis, Minnesota, USA.
  • Xiaoju Li
    Department of Pathology, Honghui Hospital, Xi'an Jiaotong University College of Medicine, Xi'an, Shaanxi, China.
  • Bo Liu
    Wuhan United Imaging Healthcare Surgical Technology Co., Ltd., Wuhan, China.
  • Bo Lin
    b Pharmaceutical Department , The Second Affiliated Hospital of Hainan Medical University , Haikou , P.R. China.
  • Yu Li
    Department of Public Health, Shihezi University School of Medicine, 832000, China.
  • Bo Xu
    State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100037, China.

Keywords

External Resources

Popular Topics
Recent Journals