Saved in:
Bibliographic Details
Main Authors: Chen, Wenting, Dong, Yi, Ding, Zhaojun, Shi, Yucheng, Zhou, Yifan, Zeng, Fang, Luo, Yijun, Lin, Tianyu, Su, Yihang, Wu, Yichen, Zhang, Kai, Xiang, Zhen, Liu, Tianming, Liu, Ninghao, Sun, Lichao, Yuan, Yixuan, Li, Xiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.14142
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916796697673728
author Chen, Wenting
Dong, Yi
Ding, Zhaojun
Shi, Yucheng
Zhou, Yifan
Zeng, Fang
Luo, Yijun
Lin, Tianyu
Su, Yihang
Wu, Yichen
Zhang, Kai
Xiang, Zhen
Liu, Tianming
Liu, Ninghao
Sun, Lichao
Yuan, Yixuan
Li, Xiang
author_facet Chen, Wenting
Dong, Yi
Ding, Zhaojun
Shi, Yucheng
Zhou, Yifan
Zeng, Fang
Luo, Yijun
Lin, Tianyu
Su, Yihang
Wu, Yichen
Zhang, Kai
Xiang, Zhen
Liu, Tianming
Liu, Ninghao
Sun, Lichao
Yuan, Yixuan
Li, Xiang
contents Chest X ray (CXR) imaging remains a critical diagnostic tool for thoracic conditions, but current automated systems face limitations in pathology coverage, diagnostic accuracy, and integration of visual and textual reasoning. To address these gaps, we propose RadFabric, a multi agent, multimodal reasoning framework that unifies visual and textual analysis for comprehensive CXR interpretation. RadFabric is built on the Model Context Protocol (MCP), enabling modularity, interoperability, and scalability for seamless integration of new diagnostic agents. The system employs specialized CXR agents for pathology detection, an Anatomical Interpretation Agent to map visual findings to precise anatomical structures, and a Reasoning Agent powered by large multimodal reasoning models to synthesize visual, anatomical, and clinical data into transparent and evidence based diagnoses. RadFabric achieves significant performance improvements, with near-perfect detection of challenging pathologies like fractures (1.000 accuracy) and superior overall diagnostic accuracy (0.799) compared to traditional systems (0.229 to 0.527). By integrating cross modal feature alignment and preference-driven reasoning, RadFabric advances AI-driven radiology toward transparent, anatomically precise, and clinically actionable CXR analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14142
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RadFabric: Agentic AI System with Reasoning Capability for Radiology
Chen, Wenting
Dong, Yi
Ding, Zhaojun
Shi, Yucheng
Zhou, Yifan
Zeng, Fang
Luo, Yijun
Lin, Tianyu
Su, Yihang
Wu, Yichen
Zhang, Kai
Xiang, Zhen
Liu, Tianming
Liu, Ninghao
Sun, Lichao
Yuan, Yixuan
Li, Xiang
Computer Vision and Pattern Recognition
Computation and Language
Chest X ray (CXR) imaging remains a critical diagnostic tool for thoracic conditions, but current automated systems face limitations in pathology coverage, diagnostic accuracy, and integration of visual and textual reasoning. To address these gaps, we propose RadFabric, a multi agent, multimodal reasoning framework that unifies visual and textual analysis for comprehensive CXR interpretation. RadFabric is built on the Model Context Protocol (MCP), enabling modularity, interoperability, and scalability for seamless integration of new diagnostic agents. The system employs specialized CXR agents for pathology detection, an Anatomical Interpretation Agent to map visual findings to precise anatomical structures, and a Reasoning Agent powered by large multimodal reasoning models to synthesize visual, anatomical, and clinical data into transparent and evidence based diagnoses. RadFabric achieves significant performance improvements, with near-perfect detection of challenging pathologies like fractures (1.000 accuracy) and superior overall diagnostic accuracy (0.799) compared to traditional systems (0.229 to 0.527). By integrating cross modal feature alignment and preference-driven reasoning, RadFabric advances AI-driven radiology toward transparent, anatomically precise, and clinically actionable CXR analysis.
title RadFabric: Agentic AI System with Reasoning Capability for Radiology
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2506.14142