LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules

TL;DR

LungNoduleAgent tackles the challenge of precise, interpretable lung nodule diagnosis from CT scans by deploying a collaborative multi-agent framework that mirrors clinical workflow. It decomposes the task into three specialized modules—Nodule Spotter, Simulated Radiologist, and Doctor Agent System—augmented by a Memory store and a medical knowledge graph via GraphRAG. The approach delivers state-of-the-art CT report generation and malignancy grading across private and public datasets, with ablation studies validating the contribution of each component and the optimal number of medical agents. The work advances clinically relevant diagnostic reasoning by enforcing region-level semantic alignment and structured evidence gathering, paving the way for robust, explainable AI support in radiology.

Abstract

Diagnosing lung cancer typically involves physicians identifying lung nodules in Computed tomography (CT) scans and generating diagnostic reports based on their morphological features and medical expertise. Although advancements have been made in using multimodal large language models for analyzing lung CT scans, challenges remain in accurately describing nodule morphology and incorporating medical expertise. These limitations affect the reliability and effectiveness of these models in clinical settings. Collaborative multi-agent systems offer a promising strategy for achieving a balance between generality and precision in medical applications, yet their potential in pathology has not been thoroughly explored. To bridge these gaps, we introduce LungNoduleAgent, an innovative collaborative multi-agent system specifically designed for analyzing lung CT scans. LungNoduleAgent streamlines the diagnostic process into sequential components, improving precision in describing nodules and grading malignancy through three primary modules. The first module, the Nodule Spotter, coordinates clinical detection models to accurately identify nodules. The second module, the Radiologist, integrates localized image description techniques to produce comprehensive CT reports. Finally, the Doctor Agent System performs malignancy reasoning by using images and CT reports, supported by a pathology knowledge base and a multi-agent system framework. Extensive testing on two private datasets and the public LIDC-IDRI dataset indicates that LungNoduleAgent surpasses mainstream vision-language models, agent systems, and advanced expert models. These results highlight the importance of region-level semantic alignment and multi-agent collaboration in diagnosing nodules. LungNoduleAgent stands out as a promising foundational tool for supporting clinical analyses of lung nodules.

Figures (7)

• Figure 1: Workflow Comparison of Traditional Methods vs. the Proposed LungNoduleAgent Framework.
• Figure 2: Overview of LungNoduleAgent for multi-modal lung nodule analysis with a nodule spotter for lung nodule detection, simulated radiologist for localized CT report generation, and Doctor Agent System for malignancy grading.
• Figure 3: Visualization of the DAS's Internal Collaboration. This figure illustrates how multiple agents leverage a medical knowledge graph and a collaborative conversational mechanism to infer and arrive at a final diagnosis for lung nodules based on the CT Report and Nodule Image.
• Figure 4: (a): Ablation study on the influence of nodule detection Acc on malignancy grading. (b): Ablation study on the impact of the number of medical agents in the DAS on nodule malignancy grading.
• Figure 5: Diagram of Measuring Lung Nodule Size.