用轻量模型实现胰腺癌自动分割，为临床诊疗提供新工具
Lightweight MRI-Based Automated Segmentation of Pancreatic Cancer with Auto3DSeg
- 基于Auto3DSeg框架，结合5折交叉验证与STAPLE集成，聚焦解剖关键区域
- 在诊断MRI上达到0.56的Dice系数，在MR-Linac上降至0.33，受序列差异影响大
- 适合医学影像算法研究者参考，尤其关注小样本下模型泛化能力
准确勾画胰腺肿瘤对诊断、治疗规划和预后评估至关重要，但因解剖变异和数据集有限，自动化分割仍具挑战。本研究将SegResNet模型作为Auto3DSeg架构的一部分，参与2025年PANTHER挑战的两项基于MRI的胰腺肿瘤分割任务。任务1使用91例增强T1加权MRI，任务2使用50例T2加权MR-Linac图像，均含专家标注的胰腺与肿瘤标签。采用5折交叉验证并结合STAPLE集成方法，以解剖相关区域为焦点。性能评估指标包括骰子相似系数（DSC）、5 mm DSC、95%分位数豪斯多夫距离（HD95）、平均表面距离（MASD）和均方根误差（RMSE）。任务1结果：DSC为0.56，5 mm DSC为0.73，HD95为41.1 mm，MASD为26.0 mm，RMSE为5164 mm；任务2性能下降：DSC为0.33，5 mm DSC为0.50，HD95为20.1 mm，MASD为7.2 mm，RMSE为17,203 mm。结果表明，小样本下基于MRI的胰腺肿瘤分割面临显著挑战，不同成像序列引入的变异性是主要因素。尽管表现有限，但仍展示出自动化勾画的潜力，并强调构建更大、标准化的MRI数据集以提升模型鲁棒性和临床可用性的重要性。
原文摘要 · Abstract (English)
Accurate delineation of pancreatic tumors is critical for diagnosis, treatment planning, and outcome assessment, yet automated segmentation remains challenging due to anatomical variability and limited dataset availability. In this study, SegResNet models, as part of the Auto3DSeg architecture, were trained and evaluated on two MRI-based pancreatic tumor segmentation tasks as part of the 2025 PANTHER Challenge. Algorithm methodology included 5-fold cross-validation with STAPLE ensembling after focusing on an anatomically relevant region-of-interest. The Pancreatic Tumor Segmentation on Diagnostic MRI task 1 training set included 91 T1-weighted arterial contrast-enhanced MRI with expert annotated pancreas and tumor labels. The Pancreatic Tumor Segmentation on MR-Linac task 2 training set used 50 T2-weighted MR-Linac cases with expert annotated pancreas and tumor labels. Algorithm-automated segmentation performance of pancreatic tumor was assessed using Dice Similarity Coefficient (DSC), 5 mm DSC, 95th percentile Hausdorff Distance (HD95), Mean Average Surface Distance (MASD), and Root Mean Square Error (RMSE). For Task 1, the algorithm achieved a DSC of 0.56, 5 mm DSC of 0.73, HD95 of 41.1 mm, MASD of 26.0 mm, and RMSE of 5164 mm. For Task 2, performance decreased, with a DSC of 0.33, 5 mm DSC of 0.50, HD95 of 20.1 mm, MASD of 7.2 mm, and RMSE of 17,203 mm. These findings illustrate the challenges of MRI-based pancreatic tumor segmentation with small datasets, highlighting variability introduced by different MRI sequences. Despite modest performance, the results demonstrate potential for automated delineation and emphasize the need for larger, standardized MRI datasets to improve model robustness and clinical utility.
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。