Zhuang Yan, Suri Abhinav, Mathai Tejas Sudharshan, Khoury Brandon, Summers Ronald M
Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
J Imaging Inform Med. 2025 Apr 30. doi: 10.1007/s10278-025-01473-y.
CT-based imaging biomarkers can be derived from the pancreas for detecting pancreatic pathologies. However, current approaches using full pancreas segmentations are unable to provide region-specific biomarkers that are crucial in predicting disease severity for many conditions, such as pancreatic adenocarcinomas. This study aims to develop an automated 3D tool to detect and segment the pancreatic sub-regions (the head, body, and tail) on CT volumes. This retrospective study used a subset of 549 CT volumes from the publicly available TotalSegmentator (TS) dataset. The dataset was randomly split into training (n = 440) and testing (n = 109) subsets. Additionally, 30 CT volumes from the TCIA NIH Pancreas-CT dataset were used for external validation. A 3D full-resolution nnUNet model was trained with a custom loss function to detect the landmarks corresponding to the pancreas's head, body, and tail. Based on the detected landmarks, a post-processing algorithm generated the sub-region segmentations. We evaluated the predicted segmentation against the ground truth masks using the Dice similarity coefficient (DSC) and Normalized Surface Distance (NSD). The mean±std of DSC (%) and NSD (%) for the head, body, and tail were 90.8±4.1 and 94.5±4.6, 83.3±7.6 and 87.2±7.4, and 85.1±9.8 and 89.7±8.8, respectively. On the external dataset, the mean±std of DSC and NSD for the head, body, and tail were 83.4±2.6 and 89.7±4.1, 79.4±5.9 and 88.5±6.0, and 81.2±5.5 and 91.4±5.3, respectively. The proposed model can accurately segment three pancreas sub-regions and enables imaging biomarkers to be derived from each sub-region and the pancreas as a whole.
基于CT的成像生物标志物可源自胰腺以检测胰腺病变。然而，当前使用全胰腺分割的方法无法提供区域特异性生物标志物，而这些生物标志物对于预测许多病症（如胰腺腺癌）的疾病严重程度至关重要。本研究旨在开发一种自动化3D工具，用于在CT容积上检测和分割胰腺亚区域（头部、体部和尾部）。这项回顾性研究使用了公开可用的TotalSegmentator（TS）数据集中的549个CT容积子集。该数据集被随机分为训练子集（n = 440）和测试子集（n = 109）。此外，来自TCIA NIH胰腺CT数据集的30个CT容积用于外部验证。使用自定义损失函数训练3D全分辨率nnUNet模型，以检测与胰腺头部、体部和尾部相对应的地标。基于检测到的地标，后处理算法生成亚区域分割。我们使用Dice相似系数（DSC）和归一化表面距离（NSD）将预测的分割与真实掩码进行评估。头部、体部和尾部的DSC（%）和NSD（%）的平均值±标准差分别为90.8±4.1和94.5±4.6、83.3±7.6和87.2±7.4、85.1±9.8和89.7±8.8。在外部数据集上，头部、体部和尾部的DSC和NSD的平均值±标准差分别为83.4±2.6和89.7±4.1、79.4±5.9和88.5±6.0、81.2±5.5和91.4±5.3。所提出的模型可以准确分割三个胰腺亚区域，并能够从每个亚区域以及整个胰腺中得出成像生物标志物。
