GCUNet：一种用于全视野数字切片中三级淋巴结构语义分割的基于GNN的上下文学习网络
GCUNet: A GNN-Based Contextual Learning Network for Tertiary Lymphoid Structure Semantic Segmentation in Whole Slide Image
AI总结：
针对全视野数字切片中基于图像块的三级淋巴结构语义分割无法获取块外上下文的问题，提出基于GNN的GCUNet网络，通过聚合长程上下文并融合细节特征提升性能，构建并公开3个数据集，mF1较SOTA至少提升7.41%。
摘要：
我们聚焦于全视野数字切片（WSI）中的三级淋巴结构（TLS）语义分割任务。与TLS二值分割不同，TLS语义分割可识别结构边界与成熟度，需整合上下文信息以发现具有判别力的特征。由于WSI尺寸极大（例如100,000×100,000像素），TLS分割通常采用基于图像块（patch）的策略，但这会导致模型无法获取图像块外的信息，限制了分割性能。为解决该问题，我们提出GCUNet，一种基于图神经网络（GNN）的上下文学习网络，用于TLS语义分割。给定待分割的目标图像块，GCUNet首先逐步聚合目标外部的长程细粒度上下文信息；随后设计细节与上下文融合模块（DCFusion），整合目标的细节特征与上下文信息以预测分割掩码。我们构建了四个TLS语义分割数据集，分别为TCGA-COAD、TCGA-LUSC、TCGA-BLCA和INHOUSE-PAAD，并公开前三个数据集（包含826张WSI和15,276个TLS）以推动TLS语义分割领域发展。在这些数据集上的实验验证了GCUNet的优越性，其mF1指标较当前最优方法（SOTA）至少提升7.41%。
英文摘要：
We focus on tertiary lymphoid structure (TLS) semantic segmentation in whole slide image (WSI). Unlike TLS binary segmentation, TLS semantic segmentation identifies boundaries and maturity, which requires integrating contextual information to discover discriminative features. Due to the extensive scale of WSI (e.g., 100,000 \times 100,000 pixels), the segmentation of TLS is usually carried out through a patch-based strategy. However, this prevents the model from accessing information outside of the patches, limiting the performance. To address this issue, we propose GCUNet, a GNN-based contextual learning network for TLS semantic segmentation. Given an image patch (target) to be segmented, GCUNet first progressively aggregates long-range and fine-grained context outside the target. Then, a Detail and Context Fusion block (DCFusion) is designed to integrate the context and detail of the target to predict the segmentation mask. We build four TLS semantic segmentation datasets, called TCGA-COAD, TCGA-LUSC, TCGA-BLCA and INHOUSE-PAAD, and make the former three datasets (comprising 826 WSIs and 15,276 TLSs) publicly available to promote the TLS semantic segmentation. Experiments on these datasets demonstrate the superiority of GCUNet, achieving at least 7.41% improvement in mF1 compared with SOTA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
