WeGA: Weakly-Supervised Global-Local Affinity Learning Framework for Lymph Node Metastasis Prediction in Rectal Cancer

TL;DR

WeGA introduces a weakly-supervised framework that models global and local lymph node relationships to improve metastasis prediction accuracy in rectal cancer MRI scans.

Contribution

It proposes a novel dual-branch architecture with global-local affinity learning and structural coherence enforcement, addressing the lack of node-level annotations.

Findings

Achieved AUCs of 0.750, 0.822, and 0.802 on different test centers.

Outperformed existing methods in lymph node metastasis prediction.

Effectively models spatial and contextual relationships between lymph nodes.

Abstract

Accurate lymph node metastasis (LNM) assessment in rectal cancer is essential for treatment planning, yet current MRI-based evaluation shows unsatisfactory accuracy, leading to suboptimal clinical decisions. Developing automated systems also faces significant obstacles, primarily the lack of node-level annotations. Previous methods treat lymph nodes as isolated entities rather than as an interconnected system, overlooking valuable spatial and contextual information. To solve this problem, we present WeGA, a novel weakly-supervised global-local affinity learning framework that addresses these challenges through three key innovations: 1) a dual-branch architecture with DINOv2 backbone for global context and residual encoder for local node details; 2) a global-local affinity extractor that aligns features across scales through cross-attention fusion; and 3) a regional affinity loss that enforces structural coherence between classification maps and anatomical regions. Experiments across one internal and two external test centers demonstrate that WeGA outperforms existing methods, achieving AUCs of 0.750, 0.822, and 0.802 respectively. By effectively modeling the relationships between individual lymph nodes and their collective context, WeGA provides a more accurate and generalizable approach for lymph node metastasis prediction, potentially enhancing diagnostic precision and treatment selection for rectal cancer patients.