Enhanced hierarchical attention mechanism for mixed MIL in automatic Gleason grading and scoring.

Journal: Scientific reports
PMID:

Abstract

Segmenting histological images and analyzing relevant regions are crucial for supporting pathologists in diagnosing various diseases. In prostate cancer diagnosis, Gleason grading and scoring relies on the recognition of different patterns in tissue samples. However, annotating large histological datasets is laborious, expensive, and often limited to slide-level or limited instance-level labels. To address this, we propose an enhanced hierarchical attention mechanism within a mixed multiple instance learning (MIL) model that effectively integrates slide-level and instance-level labels. Our hierarchical attention mechanism dynamically suppresses noisy instance-level labels while adaptively amplifying discriminative features, achieving a synergistic integration of global slide-level context and local superpixel patterns. This design significantly improves label utilization efficiency, leading to state-of-the-art performance in Gleason grading. Experimental results on the SICAPv2 and TMAs datasets demonstrate the superior performance of our model, achieving AUC scores of 0.9597 and 0.8889, respectively. Our work not only advances the state-of-the-art in Gleason grading but also highlights the potential of hierarchical attention mechanisms in mixed MIL models for medical image analysis.

Authors

  • Meili Ren
    Hainan Provincial Key Laboratory of Big Data and Smart Service, Hainan University, Haikou, 570228, China. renml@sxufe.edu.cn.
  • Mengxing Huang
    State Key Laboratory of Marine Resource Utilization in South China Sea, College of Information and Communication Engineering, Hainan University, Haikou 570288, China. Electronic address: huangmx09@hainanu.edu.cn.
  • Yu Zhang
    College of Marine Electrical Engineering, Dalian Maritime University, Dalian, China.
  • Zhijun Zhang
  • Meiyan Ren
    School of Medical, Shanxi Datong University, Datong, 037009, China.