SAGE: Agentic Framework for Interpretable and Clinically Translatable Computational Pathology Biomarker Discovery

📅 2026-02-01
📈 Citations: 0
Influential: 0
📄 PDF

career value

223K/year
🤖 AI Summary
This study addresses the limited clinical translatability of AI models in computational pathology, which stems from insufficient interpretability and biological validation. To bridge this gap, the authors propose SAGE, an intelligent agent system that uniquely integrates literature-anchored reasoning with multi-agent collaboration to establish a closed-loop framework spanning hypothesis generation to empirical validation. By jointly modeling histopathology images, gene expression profiles, and clinical data through multimodal association, SAGE automatically discovers interpretable imaging biomarkers grounded in clear biological mechanisms and significantly associated with clinical outcomes. Experimental results demonstrate that SAGE substantially enhances the transparency, credibility, and clinical translatability of identified biomarkers, thereby advancing computational pathology models toward real-world clinical deployment.

Technology Category

Application Category

📝 Abstract
Despite significant progress in computational pathology, many AI models remain black-box and difficult to interpret, posing a major barrier to clinical adoption due to limited transparency and explainability. This has motivated continued interest in engineered image-based biomarkers, which offer greater interpretability but are often proposed based on anecdotal evidence or fragmented prior literature rather than systematic biological validation. We introduce SAGE (Structured Agentic system for hypothesis Generation and Evaluation), an agentic AI system designed to identify interpretable, engineered pathology biomarkers by grounding them in biological evidence. SAGE integrates literature-anchored reasoning with multimodal data analysis to correlate image-derived features with molecular biomarkers, such as gene expression, and clinically relevant outcomes. By coordinating specialized agents for biological contextualization and empirical hypothesis validation, SAGE prioritizes transparent, biologically supported biomarkers and advances the clinical translation of computational pathology.
Problem

Research questions and friction points this paper is trying to address.

computational pathology
interpretable AI
biomarker discovery
clinical translation
explainability
Innovation

Methods, ideas, or system contributions that make the work stand out.

agentic AI
computational pathology
interpretable biomarkers
biological grounding
multimodal data integration
🔎 Similar Papers
No similar papers found.
S
Sahar Almahfouz Nasser
Department of Biomedical Engineering, Emory University, Atlanta, GA, USA
J
Juan Francisco Pesantez Borja
Georgia Institute of Technology, Atlanta, GA, USA
J
Jincheng Liu
Georgia Institute of Technology, Atlanta, GA, USA
T
Tanvir Hasan
University of Arkansas at Little Rock, Little Rock, AR, USA
Z
Zenghan Wang
Georgia Institute of Technology, Atlanta, GA, USA
S
Suman Ghosh
Georgia Institute of Technology, Atlanta, GA, USA
S
Sandeep Manandhar
Department of Biomedical Engineering, Emory University, Atlanta, GA, USA
S
Shikhar Shiromani
Georgia Institute of Technology, Atlanta, GA, USA
T
Twisha Shah
Georgia Institute of Technology, Atlanta, GA, USA
N
Naoto Tokuyama
Department of Biomedical Engineering, Emory University, Atlanta, GA, USA
A
Anant Madabhushi
Department of Biomedical Engineering, Emory University, Atlanta, GA, USA