Positive Semi-definite Latent Factor Grouping-Boosted Cluster-reasoning Instance Disentangled Learning for WSI Representation

2025-11-03

AI Summary

To address the entanglement of instances across spatial, semantic, and decision dimensions in whole-slide image (WSI) multiple-instance learning (MIL), this paper proposes a latent factor grouping-enhanced clustering-based inference disentanglement framework. It innovatively introduces positive semi-definite latent factor grouping to mitigate spatial dependencies; integrates counterfactual instance probability inference with clustering-guided semantic disentanglement to separate heterogeneous semantic features; and achieves interpretable decision-making via instance-effect reweighting. Evaluated on multi-center pathological datasets, the method significantly outperforms state-of-the-art approaches—achieving, for instance, a 3.2% improvement in C-index—while generating heatmaps and instance attributions that align closely with pathologists’ clinical interpretations. The framework thus delivers both high predictive performance and clinically grounded interpretability, establishing a novel paradigm for trustworthy AI-assisted diagnosis.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Multi-instance/Multi-view Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Multiple instance learning (MIL) has been widely used for representing whole-slide pathology images. However, spatial, semantic, and decision entanglements among instances limit its representation and interpretability. To address these challenges, we propose a latent factor grouping-boosted cluster-reasoning instance disentangled learning framework for whole-slide image (WSI) interpretable representation in three phases. First, we introduce a novel positive semi-definite latent factor grouping that maps instances into a latent subspace, effectively mitigating spatial entanglement in MIL. To alleviate semantic entanglement, we employs instance probability counterfactual inference and optimization via cluster-reasoning instance disentangling. Finally, we employ a generalized linear weighted decision via instance effect re-weighting to address decision entanglement. Extensive experiments on multicentre datasets demonstrate that our model outperforms all state-of-the-art models. Moreover, it attains pathologist-aligned interpretability through disentangled representations and a transparent decision-making process.

Problem

• Address spatial entanglement in multiple instance learning
• Alleviate semantic entanglement via cluster-reasoning disentangling
• Resolve decision entanglement through instance effect re-weighting

Innovation

• Positive semi-definite latent factor grouping for spatial disentanglement
• Cluster-reasoning instance disentangling via counterfactual inference
• Generalized linear weighted decision using instance effect re-weighting