arXiv 2606.255082026-06-25cs.CV

C2RM-Seg: 基于结构语义先验的因果反事实推理用于弱监督组织病理学组织分割

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

Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin University of Electronic Technology（广西图像图形智能处理重点实验室，桂林电子科技大学）；International Joint Research Laboratory of Spatio-temporal Information and Intelligent Location Services, Guilin University of Electronic Technology（时空信息与智能定位服务国际联合研究实验室，桂林电子科技大学）；School of Computer Science and Information Security, Guilin University of Electronic Technology（桂林电子科技大学计算机与信息安全学院）

Hualong Zhang, Siyang Feng, Zihan Huan, Yi Qian, Zhenbing Liu, Rushi Lan, Xipeng Pan

备注：: 11 pages, 3 figures. Code is available at https://github.com/OceanPetal/C2AM-Seg

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出C2RM-Seg框架，通过因果反事实推理模块生成形态对齐的CAM，结合双路径结构语义架构和不确定性门控边缘损失，解决弱监督组织分割中伪标签噪声问题，在公共数据集上达到最优性能。

摘要：

组织病理学组织分割对于计算机辅助诊断至关重要，但弱监督方法常受类激活映射（CAM）生成的噪声伪标签困扰。现有CAM方法倾向于关注染色驱动的外观线索而非真正的因果组织形态，导致虚假定位和结构一致性差。为解决此问题，我们提出C$^2$RM-Seg，一个两阶段框架，整合了因果伪标签精炼与结构感知语义增强。对于分类，我们引入因果反事实推理模块（C$^2$RM），将特征分解为潜在因子，并通过学习到的因果结构矩阵进行反事实干预，抑制混淆上下文并生成形态对齐的CAM。对于分割，我们设计了一个双路径结构语义架构，结合来自ResNeSt的细粒度结构特征和来自冻结DINOV3基础模型的全局语义先验。跨路径门控机制利用局部结构线索自适应调节语义注入以保持边界保真度。为进一步减轻残留伪标签噪声，我们提出不确定性门控边缘（UGM）损失，基于预测不确定性动态平衡边缘强制和置信度学习。在两个公共组织病理学组织数据集上的大量实验表明，C$^2$RM-Seg达到了最先进的性能。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。