LRMR: LLM-Driven Relational Multi-node Ranking for Lymph Node Metastasis Assessment in Rectal Cancer

TL;DR

This paper introduces LRMR, a novel two-stage LLM-based framework that improves the interpretability and accuracy of lymph node metastasis assessment in rectal cancer by combining structured report generation and relational ranking.

Contribution

The paper presents a new LLM-driven approach that transforms lymph node assessment into a structured reasoning and ranking task, outperforming traditional deep learning models.

Findings

LRMR achieved an AUC of 0.7917, surpassing baseline models.

The two-stage framework significantly improves diagnostic performance.

Decoupling perception from reasoning enhances interpretability and accuracy.

Abstract

Accurate preoperative assessment of lymph node (LN) metastasis in rectal cancer guides treatment decisions, yet conventional MRI evaluation based on morphological criteria shows limited diagnostic performance. While some artificial intelligence models have been developed, they often operate as black boxes, lacking the interpretability needed for clinical trust. Moreover, these models typically evaluate nodes in isolation, overlooking the patient-level context. To address these limitations, we introduce LRMR, an LLM-Driven Relational Multi-node Ranking framework. This approach reframes the diagnostic task from a direct classification problem into a structured reasoning and ranking process. The LRMR framework operates in two stages. First, a multimodal large language model (LLM) analyzes a composite montage image of all LNs from a patient, generating a structured report that details ten distinct radiological features. Second, a text-based LLM performs pairwise comparisons of these reports between different patients, establishing a relative risk ranking based on the severity and number of adverse features. We evaluated our method on a retrospective cohort of 117 rectal cancer patients. LRMR achieved an area under the curve (AUC) of 0.7917 and an F1-score of 0.7200, outperforming a range of deep learning baselines, including ResNet50 (AUC 0.7708). Ablation studies confirmed the value of our two main contributions: removing the relational ranking stage or the structured prompting stage led to a significant performance drop, with AUCs falling to 0.6875 and 0.6458, respectively. Our work demonstrates that decoupling visual perception from cognitive reasoning through a two-stage LLM framework offers a powerful, interpretable, and effective new paradigm for assessing lymph node metastasis in rectal cancer.