NCI Data Jamboree (Project Abstract Submission): Submission #43

Presenter Information
---------------------
First Name: Ying
Middle Initial: {Empty}
Last Name: Ding
Degree(s): Ph.D.
Position/Title/Career Status: {Empty}
Organization: University of Texas at Austin
Organization Address:
Austin

Email: ying.ding@austin.utexas.edu

Additional Authors
------------------
List of Additional Authors:
- First Name: Hairong
  Last Name: Wang
  Affiliation: University of Texas at Austin


Abstract Information
--------------------
Abstract Category: Developing, refining, or validating tools, methods, algorithms, and pipelines
Abstract Keywords: {Empty}
Abstract Title: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology
Abstract:
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
5 evidence alongside whole-slide images, yet existing models often fail to clarify how diverse signals assemble into recognizable diagnostic concepts. We propose ConceptM3oE (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 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.