Positive Semi-definite Latent Factor Grouping-Boosted Cluster-reasoning Instance Disentangled Learning for WSI Representation
This work addresses interpretability and performance limitations in medical image analysis for pathology, representing an incremental improvement over existing methods.
The paper tackles spatial, semantic, and decision entanglements in multiple instance learning for whole-slide pathology images by proposing a latent factor grouping-boosted cluster-reasoning instance disentangled learning framework, resulting in outperforming all state-of-the-art models on multicentre datasets and achieving pathologist-aligned interpretability.
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.