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

arXiv: https://arxiv.org/abs/2606.21174 · HTML: https://mlsanity.com/paper/2606.21174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [Multimodal Whole Slide Foundation Model for Pathology](https://mlsanity.com/paper/2411.19666/) (2024)
- [MMedAgent: Learning to Use Medical Tools with Multi-modal Agent](https://mlsanity.com/paper/2407.02483/) (2024)
- [Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction](https://mlsanity.com/paper/2304.06819/) (2023)
- [Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction](https://mlsanity.com/paper/2306.08330/) (2023)
- [MedRAX: Medical Reasoning Agent for Chest X-ray](https://mlsanity.com/paper/2502.02673/) (2025)
- [SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding](https://mlsanity.com/paper/2410.11761/) (2024)
- [WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image](https://mlsanity.com/paper/2412.02141/) (2024)
- [Cohort-Individual Cooperative Learning for Multimodal Cancer Survival Analysis](https://mlsanity.com/paper/2404.02394/) (2024)
- [hist2RNA: An efficient deep learning architecture to predict gene expression from breast cancer histopathology images](https://mlsanity.com/paper/2304.04507/) (2023)
- [Screen Them All: High-Throughput Pan-Cancer Genetic and Phenotypic Biomarker Screening from H&E Whole Slide Images](https://mlsanity.com/paper/2408.09554/) (2024)
- [Prototype-driven fusion of pathology and spatial transcriptomics for interpretable survival prediction](https://mlsanity.com/paper/2602.12441/) (2026)

## Abstract (arXiv)

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.