HERO: Hypothesis-Driven Evidence Retrieval from Omics for Multi-Task Breast Cancer Analysis

2026-06-19

AI Summary

This study addresses the lack of existing multimodal integration methods that translate omics data into testable morphological hypotheses to guide evidence retrieval from histopathology images. The authors propose a closed-loop framework that, for the first time, maps DNA methylation and miRNA features into morphological intent vectors, retrieves relevant pathological regions from structured text via TF-IDF, and employs a cosine similarity gating mechanism to trigger a vision-language model for deterministic refinement. This approach establishes a lexically auditable retrieval-and-verification pipeline, reducing reliance on implicit semantic matching in embedding spaces. Evaluated on the TCGA-BRCA dataset, the method achieves new state-of-the-art performance across multiple clinical tasks—including ER, PR, and HER2 status prediction, molecular subtyping, and risk stratification—significantly outperforming current multimodal fusion and vision-language model baselines.

Abstract

Matched multi-omics can improve WSI-based biomarker and prognosis prediction, but most existing pipelines use omics as a paral lel feature stream or textual context rather than as an explicit retrieval constraint. HERO asks whether observed omics can be a testable mor phology hypothesis: a sparse pathway-to-morphology prior maps DNA methylation and miRNA into a K-dimensional intent vector m (K=16), TF-IDF retrieval over structured 10 captions selects endpoint-relevant regions, and a cosine gate c=cos(m,v) triggers deterministic deficit driven repair when c<τc. This closed-loop design bounds VLM calls, reduces reliance on embedding-based semantic matching, and makes every retrieval and verification step lexically auditable. On TCGA-BRCA (930WSIs, patient-level 5-fold CV), HERO sets new state-of-the-art across ER, PR, HER2, subtype, and risk prediction, outperforming both multimodal fusion and VLM-based baselines.

Problem

• multi-omics
• breast cancer
• evidence retrieval
• morphology hypothesis
• biomarker prediction

Innovation

• hypothesis-driven retrieval
• multi-omics integration
• visual-language model gating
• morphology hypothesis
• auditable multimodal reasoning