LungCURE: Benchmarking Multimodal Real-World Clinical Reasoning for Precision Lung Cancer Diagnosis and Treatment

TL;DR

LungCURE introduces a standardized multimodal benchmark and a multi-agent framework to improve clinical reasoning and decision-making in lung cancer diagnosis and treatment, addressing limitations of existing models.

Contribution

The paper presents LungCURE, the first benchmark for multimodal lung cancer decision support, and LCAgent, a multi-agent system that enhances guideline-compliant reasoning in LLMs.

Findings

Large differences in LLMs' medical reasoning capabilities.

LCAgent improves reasoning performance in real-world scenarios.

Benchmark built from 1,000 clinician-labeled cases across hospitals.

Abstract

Lung cancer clinical decision support demands precise reasoning across complex, multi-stage oncological workflows. Existing multimodal large language models (MLLMs) fail to handle guideline-constrained staging and treatment reasoning. We formalize three oncological precision treatment (OPT) tasks for lung cancer, spanning TNM staging, treatment recommendation, and end-to-end clinical decision support. We introduce LungCURE, the first standardized multimodal benchmark built from 1,000 real-world, clinician-labeled cases across more than 10 hospitals. We further propose LCAgent, a multi-agent framework that ensures guideline-compliant lung cancer clinical decision-making by suppressing cascading reasoning errors across the clinical pathway. Experiments reveal large differences across various large language models (LLMs) in their capabilities for complex medical reasoning, when given precise treatment requirements. We further verify that LCAgent, as a simple yet effective plugin, enhances the reasoning performance of LLMs in real-world medical scenarios.