CT-Flow: Orchestrating CT Interpretation Workflow with Model Context Protocol Servers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gu, Yannian, Zhang, Xizhuo, Mu, Linjie, Yu, Yongrui, Huang, Zhongzhen, Zhang, Shaoting, Zhang, Xiaofan
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915824257728512
author Gu, Yannian
Zhang, Xizhuo
Mu, Linjie
Yu, Yongrui
Huang, Zhongzhen
Zhang, Shaoting
Zhang, Xiaofan
author_facet Gu, Yannian
Zhang, Xizhuo
Mu, Linjie
Yu, Yongrui
Huang, Zhongzhen
Zhang, Shaoting
Zhang, Xiaofan
contents Recent advances in Large Vision-Language Models (LVLMs) have shown strong potential for multi-modal radiological reasoning, particularly in tasks like diagnostic visual question answering (VQA) and radiology report generation. However, most existing approaches for 3D CT analysis largely rely on static, single-pass inference. In practice, clinical interpretation is a dynamic, tool-mediated workflow where radiologists iteratively review slices and use measurement, radiomics, and segmentation tools to refine findings. To bridge this gap, we propose CT-Flow, an agentic framework designed for interoperable volumetric interpretation. By leveraging the Model Context Protocol (MCP), CT-Flow shifts from closed-box inference to an open, tool-aware paradigm. We curate CT-FlowBench, the first large-scale instruction-tuning benchmark tailored for 3D CT tool-use and multi-step reasoning. Built upon this, CT-Flow functions as a clinical orchestrator capable of decomposing complex natural language queries into automated tool-use sequences. Experimental evaluations on CT-FlowBench and standard 3D VQA datasets demonstrate that CT-Flow achieves state-of-the-art performance, surpassing baseline models by 41% in diagnostic accuracy and achieving a 95% success rate in autonomous tool invocation. This work provides a scalable foundation for integrating autonomous, agentic intelligence into real-world clinical radiology.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00123
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CT-Flow: Orchestrating CT Interpretation Workflow with Model Context Protocol Servers
Gu, Yannian
Zhang, Xizhuo
Mu, Linjie
Yu, Yongrui
Huang, Zhongzhen
Zhang, Shaoting
Zhang, Xiaofan
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent advances in Large Vision-Language Models (LVLMs) have shown strong potential for multi-modal radiological reasoning, particularly in tasks like diagnostic visual question answering (VQA) and radiology report generation. However, most existing approaches for 3D CT analysis largely rely on static, single-pass inference. In practice, clinical interpretation is a dynamic, tool-mediated workflow where radiologists iteratively review slices and use measurement, radiomics, and segmentation tools to refine findings. To bridge this gap, we propose CT-Flow, an agentic framework designed for interoperable volumetric interpretation. By leveraging the Model Context Protocol (MCP), CT-Flow shifts from closed-box inference to an open, tool-aware paradigm. We curate CT-FlowBench, the first large-scale instruction-tuning benchmark tailored for 3D CT tool-use and multi-step reasoning. Built upon this, CT-Flow functions as a clinical orchestrator capable of decomposing complex natural language queries into automated tool-use sequences. Experimental evaluations on CT-FlowBench and standard 3D VQA datasets demonstrate that CT-Flow achieves state-of-the-art performance, surpassing baseline models by 41% in diagnostic accuracy and achieving a 95% success rate in autonomous tool invocation. This work provides a scalable foundation for integrating autonomous, agentic intelligence into real-world clinical radiology.
title CT-Flow: Orchestrating CT Interpretation Workflow with Model Context Protocol Servers
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.00123