arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.24399cs.AI
收藏

ConceptM$^3$oE:面向可解释计算病理学的概念引导多模态专家混合模型

ConceptM$^3$oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology

University of Texas at Austin(德克萨斯大学奥斯汀分校);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Dell Children’s Medical Center(德尔儿童医疗中心);The University of Texas MD Anderson Cancer Center(德克萨斯大学MD安德森癌症中心);University of Nevada, Reno(内华达大学里诺分校)
Xuan Wang, Zhongling Xu, Gopi Kannedhara, Joakim Nguyen, Jian Yu, Jinrui Fang, Abdurrahmaan Baghdadi, Tianlong Chen, Awais Naeem, Chandra Krishnan, Edward Casti… 展开作者

Xuan Wang, Zhongling Xu, Gopi Kannedhara, Joakim Nguyen, Jian Yu, Jinrui Fang, Abdurrahmaan Baghdadi, Tianlong Chen, Awais Naeem, Chandra Krishnan, Edward Castillo, Andrew H. Song, Ankita Shukla, Ying Ding, Nicholas Konz, Hairong Wang

AI总结:

提出ConceptM$^3$oE框架,通过概念引导的多模态专家混合路径嵌入概念形成,并利用残差路径保持性能与可解释性,在脑肿瘤分类中优于基线并提升小样本性能。

摘要:

医疗模型正从单模态预测转向对异构诊断输入的多模态推理。在计算病理学中,对于仅凭形态学难以区分的复杂肿瘤亚型,病理报告和分子测量可提供额外的诊断证据,但现有模型往往无法阐明不同信号如何组合成可识别的诊断概念。我们提出ConceptM$^3$oE(概念多模态MoE),将概念形成直接嵌入交互感知的专家混合(MoE)路径中。该架构将证据分解为模态特定、冗余和协同专家,然后将其投影到结构化概念瓶颈中,将潜在特征映射到形态学和生物标志物概念层次结构。为防止可解释瓶颈典型的信息损失,我们在每个专家内利用残差路径,使任务相关信号既通过概念流动,也直接流向最终任务预测,从而在保持可解释性的同时维持高性能。在机构性儿童脑肿瘤队列和公共胶质瘤队列上,该框架实现了与无约束模型相竞争的性能,同时产生由独立神经病理学家验证的推理轨迹。在数据有限的情况下,ConceptM$^3$oE提升了小数据性能,在较小训练规模下,与非概念信息基线相比,宏F1从56.41%提升至66.70%,同时显示出更快的训练收敛速度,这与概念学习的正则化效应一致。这项工作为高性能、内在可验证且更符合临床实践复杂决策的医疗AI提供了一条可扩展的路径。

英文摘要:

Healthcare models are transitioning from unimodal prediction toward multimodal reasoning over heterogeneous diagnostic inputs. In computational pathology, for complex tumor subtypes where morphology alone can be challenging to distinguish, pathology reports and molecular measurements may provide additional diagnostic evidence alongside whole-slide images, yet existing models often fail to clarify how diverse signals assemble into recognizable diagnostic concepts. We propose ConceptM$^3$oE (Concept Multimodal MoE), which embeds concept formation directly within interaction-aware mixture-of-experts (MoE) pathways. The architecture decomposes evidence into modality-specific, redundant, and synergistic experts, which are then projected into structured concept bottlenecks mapping latent features to a hierarchy of morphology and biomarker concepts. To prevent the information loss typical of interpretable bottlenecks, we utilize residual pathways within each expert to allow task-relevant signals to flow both through the concepts and directly to the final task prediction, so that high performance is maintained alongside interpretability. Across an institutional pediatric brain tumor cohort and a public glioma cohort, the framework delivers competitive performance to unconstrained models while producing reasoning traces validated by an independent neuropathologist. In data-limited regimes, ConceptM$^3$oE improves limited-data performance, increasing macro-F1 from 56.41% to 66.70% at small training sizes compared to non-concept-informed baselines, while also showing faster training convergence consistent with the regularizing effect of concept learning. This work offers a scalable path toward high-performance medical AI that is inherently verifiable and better aligned with the complex decision-making of clinical practice.

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。

↑