用改进的Swin-UNet模型实现跨器官跨扫描仪腺癌分割，提升病理图像分析鲁棒性。
Adenocarcinoma Segmentation Using Pre-trained Swin-UNet with Parallel Cross-Attention for Multi-Domain Imaging
- 基于预训练Swin-UNet，引入并行交叉注意力模块增强特征融合能力
- 在跨器官和跨扫描仪数据上分别取得0.7469和0.7597的分割分数
- 适用于多源病理图像，尤其适合临床实际中设备与组织差异场景
计算机辅助病理分析已成为肿瘤诊断的标准方法，但组织学图像中存在显著的域偏移问题，由解剖结构差异、组织制备流程及成像过程变化引起，严重影响分割模型的鲁棒性。本文提出一种基于预训练编码器的Swin-UNet框架，通过引入并行交叉注意力模块，有效应对不同器官与扫描仪间的腺癌分割挑战，同时考虑形态学变化与扫描仪带来的域差异。在跨器官与跨扫描仪腺癌分割挑战赛数据集上的实验表明，该框架在最终测试集上分别达到0.7469（跨器官）和0.7597（跨扫描仪）的分割分数，能有效适应多样成像条件，显著提升跨域分割精度。
原文摘要 · Abstract (English)
Computer aided pathological analysis has been the gold standard for tumor diagnosis, however domain shift is a significant problem in histopathology. It may be caused by variability in anatomical structures, tissue preparation, and imaging processes challenges the robustness of segmentation models. In this work, we present a framework consist of pre-trained encoder with a Swin-UNet architecture enhanced by a parallel cross-attention module to tackle the problem of adenocarcinoma segmentation across different organs and scanners, considering both morphological changes and scanner-induced domain variations. Experiment conducted on Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation challenge dataset showed that our framework achieved segmentation scores of 0.7469 for the cross-organ track and 0.7597 for the cross-scanner track on the final challenge test sets, and effectively navigates diverse imaging conditions and improves segmentation accuracy across varying domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。