Self-HER2Net: A generative self-supervised framework for HER2 classification in IHC histopathology of breast cancer.

Journal: Pathology, research and practice
Published Date:

Abstract

Breast cancer is a significant global health concern, where precise identification of proteins like Human Epidermal Growth Factor Receptor 2 (HER2) in cancer cells via Immunohistochemistry (IHC) is pivotal for treatment decisions. HER2 overexpression is evaluated through HER2 scoring on a scale from 0 to 3 + based on staining patterns and intensity. Recent efforts have been made to automate HER2 scoring using image processing and AI techniques. However, existing methods require large manually annotated datasets as these follow supervised learning paradigms. Therefore, we proposed a generative self-supervised learning (SSL) framework "Self-HER2Net" for the classification of HER2 scoring, to reduce dependence on large manually annotated data by leveraging one of best performing four novel generative self-supervised tasks, that we proposed. The first two SSL tasks HER2 and HER2 are domain-agnostic and the other two HER2 and HER2 are domain-specific SSL tasks focusing on domain-agnostic and domain-specific staining patterns and intensity representation. Our approach is evaluated under different budget scenarios (2 %, 15 %, & 100 % labeled datasets) and also out distribution test. For tile-level assessment, HER2 achieved the best performance with AUC-ROC of 0.965 ± 0.037. Our self-supervised learning approach shows potential for application in scenarios with limited annotated data for HER2 analysis.

Authors

  • Genevieve Chyrmang
    Research Scholar, Department of Computer Science and IT, Cotton University, Guwahati, Assam, India.
  • Barun Barua
    Research Scholar, Department of Computer Science and IT, Cotton University, Guwahati, Assam, India.
  • Kangkana Bora
    The Department of Centre for Computational and Numerical Sciences, Institute of Advanced Study in Science and Technology, Guwahati 781035, Assam, India. Electronic address: kangkana.bora89@gmail.com.
  • Gazi N Ahmed
    North East Cancer Hospital and Research Institute, Jorabat, Guwahati, Assam, 781023, India.
  • Anup Kr Das
    Arya Wellness Centre, Guwahati, Assam, India.
  • Lopamudra Kakoti
    Dr. B Borooah Cancer Institute, Guwahati, Assam, 781016, India.
  • Bernardo Lemos
    Department of Environmental Health, Harvard T H Chan School of Public Health, Boston, MA 02115, USA; Department of Pharmacology & Toxicology, University of Arizona, AZ 85721, USA. Electronic address: blemos@hsph.harvard.edu.
  • Saurav Mallik
    Center for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center, Houston.