GCUNet: A GNN-Based Contextual Learning Network for Tertiary Lymphoid Structure Semantic Segmentation in Whole Slide Image
GCUNet is a Graph Neural Network approach designed to improve semantic segmentation of Tertiary Lymphoid Structures (TLS) in Whole Slide Images (WSIs). It addresses the limitation of patch-based methods by using GNNs to aggregate long-range and fine-grained contextual information outside the target area. This contextual learning helps distinguish TLS maturity levels, leading to significant performance improvements over existing state-of-the-art models.