C2RM-Seg: Causal Counterfactual Reasoning with Structural-Semantic Priors for Weakly Supervised Histopathological Tissue Segmentation

2026-06-24

AI Summary

This work addresses the challenge of weakly supervised histopathological image segmentation, where conventional Class Activation Maps (CAMs) are highly susceptible to staining artifacts, resulting in noisy pseudo-labels and poor structural consistency. To mitigate this, the study introduces causal counterfactual reasoning for the first time to disentangle confounding factors and generate morphology-aligned CAMs. It further proposes a structure–semantics dual-path network that fuses ResNeSt and DINOv2 features, coupled with an Uncertainty-Gated Boundary Loss (UGM) to suppress noise while preserving boundary fidelity. Evaluated on two public histopathology datasets, the method achieves state-of-the-art performance, significantly improving both segmentation accuracy and structural coherence.

Abstract

Histopathological tissue segmentation is essential for computer-aided diagnosis, yet weakly supervised methods often suffer from noisy pseudo-labels generated by Class Activation Mapping (CAM). Existing CAM approaches tend to focus on staining-driven appearance cues rather than true causal tissue morphology, resulting in spurious localization and poor structural consistency. To address this issue, we propose C$^2$RM-Seg, a two-stage framework that integrates causal pseudo-label refinement with structure-aware semantic enhancement. For classification, we introduce a Causal Counterfactual Reasoning Module (C$^2$RM) that decomposes features into latent factors and performs counterfactual intervention via a learned causal structure matrix, suppressing confounding context and producing morphology-aligned CAMs. For segmentation, we design a Dual-Path Structural-Semantic Architecture that combines fine-grained structural features from ResNeSt with global semantic priors from a frozen DINOV3 foundation model. A cross-path gating mechanism adaptively regulates semantic injection using local structural cues to preserve boundary fidelity. To further mitigate residual pseudo-label noise, we propose an Uncertainty-Gated Margin (UGM) loss, which dynamically balances margin enforcement and confidence learning based on prediction uncertainty. Extensive experiments on two public histopathological tissue datasets show that C$^2$RM-Seg achieves state-of-the-art performance.

Problem

• weakly supervised segmentation
• histopathological tissue
• pseudo-label noise
• class activation mapping
• structural consistency

Innovation

• Causal Counterfactual Reasoning
• Structural-Semantic Priors
• Weakly Supervised Segmentation
• Pseudo-label Refinement
• Uncertainty-Gated Margin Loss