Exploring multi-instance learning in whole slide imaging: Current and future perspectives.

Journal: Pathology, research and practice
Published Date: May 13, 2025

Abstract

Whole slide images (WSI), due to their gigabyte-scale size and ultra-high resolution, play a significant role in diagnostic pathology. However, the enormous data size makes it difficult to directly input these images into image processing units (GPU) for computation, limiting the development of automated screening and diagnostic algorithms. As an effective computational framework, multi-instance learning (MIL) has provided strong support in addressing this challenge. This review systematically summarizes the research progress and applications of MIL in WSI analysis, based on over 90 articles retrieved from Web of Science, IEEE Xplore and PubMed. It briefly outlines the unique advantages and specific improvements in handling whole slide images, with a focus on analyzing the core characteristics and performance of mainstream techniques in tasks such as cancer detection and subtype classification. The results indicate that methods like data preprocessing, multi-scale feature fusion, representative instance selection, and Transformer-based models significantly enhance the ability of MIL in WSI processing. Furthermore, this paper also summarizes the characteristics of different technologies and proposes future research directions to promote the widespread application of MIL in pathological diagnosis.

Authors

  • Jikai Yu
    School of Information Engineering, Huzhou University, Huzhou, ZheJiang 313000, China.
  • Hongda Chen
    Department of Gastroenterology, the Third Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China.
  • Lianxin Hu
    School of Information Engineering, Huzhou University, Huzhou, ZheJiang 313000, China.
  • Boyuan Wu
    School of Information Engineering, Huzhou University, Huzhou, ZheJiang 313000, China.
  • Shicheng Zhou
    School of Information Engineering, Huzhou University, Huzhou, ZheJiang 313000, China.
  • Jiayun Zhu
    School of Information Engineering, Huzhou University, Huzhou, ZheJiang 313000, China.
  • Yizhen Jiang
    Huzhou Central Hospital, Affiliated Central Hospital Huzhou University, No.1558, North Third Ring Road, Huzhou, ZheJiang 313000, China.
  • Shuwen Han
    Huzhou Central Hospital, Affiliated Central Hospital Huzhou University, No.1558, North Third Ring Road, Huzhou, ZheJiang 313000, China; Key Laboratory of Multiomics Research and Clinical Transformation of Digestive Cancer of Huzhou, No.1558, North Third Ring Road, Huzhou, ZheJiang 313000, China.
  • Zefeng Wang
    CAS Key Laboratory of Computational Biology, CAS-MPG Partner Institute for Computational Biology, Shanghai Institute of Nutrition and Health, Shanghai Institutes for Biological Sciences, University of Chinese Academy of Sciences, CAS Center for Excellence in Molecular Cell Science, Chinese Academy of Sciences, Shanghai 200031, China. Electronic address: wangzefeng@picb.an.cn.

Keywords

External Resources

Popular Topics
Recent Journals