基于多类Transformer的胰腺导管腺癌及周围结构CT图像分割:多中心评估
这项回顾性多中心研究纳入六家机构3265例患者,比较UNet、nnU-Net、UNETR和Swin-UNet在CT上对胰腺导管腺癌及五个周围结构的多类分割性能,Swin-UNet平均验证DSC为92.4%、测试DSC为90.8%,统计确认其最优(p < 0.001),作者认为该框架有潜力用于临床诊断、分期和治疗计划。
要点
- Swin-UNet对PDAC及周围结构分割最优,平均验证DSC 92.4%、测试DSC 90.8%。
- Swin-UNet在交叉验证中dHD最低(4.3 mm)、ASSD最低(1.2 mm)、VOE最低(6.0%)。
- 各解剖目标中胰管DSC 91.0%、胆总管DSC 91.8%,显示对挑战性结构的分割能力。
核心结论
- 基于Transformer的架构(尤其是Swin-UNet)能对胰腺导管腺癌及周围解剖结构进行精确且可泛化的多类分割,作者认为该框架有潜力用于胰腺导管腺癌诊断、分期和治疗计划的临床整合。
研究设计与样本
- 回顾性多中心研究,纳入六家机构3265例患者,四类深度学习模型(UNet、nnU-Net、UNETR、Swin-UNet)在五家中心数据上采用五折交叉验证训练,并在第六家中心(n = 569)独立测试。
关键影像表现/征象
- 分割目标包括胰腺导管腺癌病灶、胰腺、静脉、动脉、胰管和胆总管共六类结构。
- 预处理包括强度归一化、体素重采样和标准化标注。
- Swin-UNet在交叉验证中dHD为4.3 mm、ASSD为1.2 mm、VOE为6.0%。
诊断标准与关键数值
- Swin-UNet平均验证DSC为92.4%,测试DSC为90.8%。
- Swin-UNet各解剖目标DSC中,胰管为91.0%,胆总管为91.8%。
- 统计比较采用Wilcoxon符号秩检验并行Bonferroni校正,确认Swin-UNet的优越性(p < 0.001)。
临床应用与阅片要点
- 作者认为基于Transformer的架构(尤其Swin-UNet)有潜力用于胰腺导管腺癌诊断、分期和治疗计划的临床整合。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: Accurate segmentation of pancreatic ductal adenocarcinoma (PDAC) and surrounding anatomical structures is critical for diagnosis, treatment planning, and outcome assessment. This study proposes a deep learning-based framework to automate multi-class segmentation in CT images, comparing the performance of four state-of-the-art architectures.
MATERIALS AND METHODS: This retrospective multi-center study included 3265 patients from six institutions. Four deep learning models-UNet, nnU-Net, UNETR, and Swin-UNet-were trained using five-fold cross-validation on data from five centers and tested independently on a sixth center (n = 569). Preprocessing included intensity normalization, voxel resampling, and standardized annotation for six structures: PDAC lesion, pancreas, veins, arteries, pancreatic duct, and common bile duct. Evaluation metrics included Dice Similarity Coefficient (DSC), Intersection over Union (IoU), directed Hausdorff Distance (dHD), Average Symmetric Surface Distance (ASSD), and Volume Overlap Error (VOE). Statistical comparisons were made using Wilcoxon signed-rank tests with Bonferroni correction.
RESULTS: Swin-UNet outperformed all models with a mean validation DSC of 92.4% and test DSC of 90.8%, showing minimal overfitting. It also achieved the lowest dHD (4.3 mm), ASSD (1.2 mm), and VOE (6.0%) in cross-validation. Per-class DSCs for Swin-UNet were consistently higher across all anatomical targets, including challenging structures like the pancreatic duct (91.0%) and bile duct (91.8%). Statistical analysis confirmed the superiority of Swin-UNet (p < 0.001). All models showed generalization capability, but Swin-UNet provided the most accurate and robust segmentation across datasets.
CONCLUSIONS: Transformer-based architectures, particularly Swin-UNet, enable precise and generalizable multi-class segmentation of PDAC and surrounding anatomy. This framework has potential for clinical integration in PDAC diagnosis, staging, and therapy planning.
引用
- Wen S, Xiao X. Multi-class transformer-based segmentation of pancreatic ductal adenocarcinoma and surrounding structures in CT imaging: a multi-center evaluation. Abdom Radiol (NY). 2025. PMID: 40514460. doi:10.1007/s00261-025-05061-0
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。