mlsanityData to 7 Oct 2026

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

arXiv 2606.21174 ↗First posted 19 Jun 2026cs.CV q-bio.GNcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 19 Jun 2026.

Builds on

18 of 27 references.

References · 18

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2025Qwen2.5-VL Technical Reportcited by 5,418
  3. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  4. 2017Self-Normalizing Neural Networkscited by 591
  5. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  6. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 311
  7. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 162
  8. 2024Multimodal Whole Slide Foundation Model for Pathologycited by 156
  9. 2024MMedAgent: Learning to Use Medical Tools with Multi-modal Agentcited by 108
  10. 2023Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Predictioncited by 92
  11. 2023Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Predictioncited by 86
  12. 2025MedRAX: Medical Reasoning Agent for Chest X-raycited by 68
6 more
  1. 2024SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understandingcited by 54
  2. 2024WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Imagecited by 37
  3. 2024Cohort-Individual Cooperative Learning for Multimodal Cancer Survival Analysiscited by 13
  4. 2023hist2RNA: An efficient deep learning architecture to predict gene expression from breast cancer histopathology imagescited by 10
  5. 2024Screen Them All: High-Throughput Pan-Cancer Genetic and Phenotypic Biomarker Screening from H&E Whole Slide Imagescited by 8
  6. 2026Prototype-driven fusion of pathology and spatial transcriptomics for interpretable survival predictioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DoGMA: A Central-Dogma-Guided Foundation Model for Multi-Omics Alignment and Multi-Task Learning in Oncology
  2. 2026OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning
  3. 2025Patient-specific Biomolecular Instruction Tuning
  4. 2025Generative vector search to improve pathology foundation models across multimodal vision-language tasks
  5. 2026BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine
  6. 2026OmicSync: Reliability-Aware Spatial Multi-Omics Clustering with Evidence-Constrained LLM Reasoning
  7. 2026Tool-Augmented On-Policy Distillation for LLM Domain Adaptation in Sequence-Based Omics Tasks
  8. 2026ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction