MacNet: An End-to-End Manifold-Constrained Adaptive Clustering Network for Interpretable Whole Slide Image Classification

TL;DR

This paper introduces MacNet, an end-to-end manifold-constrained clustering network for interpretable whole slide image classification, improving accuracy and interpretability by integrating geometric structure and prior knowledge.

Contribution

The paper proposes a novel end-to-end MIL framework with Grassmann re-embedding and manifold adaptive clustering for better interpretability and performance in WSI classification.

Findings

Achieves superior grading accuracy on multicentre datasets

Provides more interpretable decision-making process

Requires acceptable computational resources

Abstract

Whole slide images (WSIs) are the gold standard for pathological diagnosis and sub-typing. Current main-stream two-step frameworks employ offline feature encoders trained without domain-specific knowledge. Among them, attention-based multiple instance learning (MIL) methods are outcome-oriented and offer limited interpretability. Clustering-based approaches can provide explainable decision-making process but suffer from high dimension features and semantically ambiguous centroids. To this end, we propose an end-to-end MIL framework that integrates Grassmann re-embedding and manifold adaptive clustering, where the manifold geometric structure facilitates robust clustering results. Furthermore, we design a prior knowledge guiding proxy instance labeling and aggregation strategy to approximate patch labels and focus on pathologically relevant tumor regions. Experiments on multicentre WSI datasets demonstrate that: 1) our cluster-incorporated model achieves superior performance in both grading accuracy and interpretability; 2) end-to-end learning refines better feature representations and it requires acceptable computation resources.