文献速递腹部胸部泌尿生殖CT

基于3D V-Net的肾上腺分割模型的多中心验证研究:从腹部CT到胸部CT的跨协议泛化

A multicentre validation study of 3D V-net-based segmentation model for adrenal glands: cross-protocol generalization from abdominal CT to chest CT.
PubMed 文献 · Br J Radiol · 2026-01-01

本研究基于腹部CT建立3D V-Net肾上腺分割模型,在内部测试集及两个健康筛查队列(同机构与外部机构)的胸部CT上验证,左右肾上腺DSC在测试集为0.920与0.910,验证队列1为0.816与0.819,验证队列2为0.752与0.747,显示从腹部CT到胸部CT的泛化性,作者认为其有潜力作为辅助诊断的「标记」系统。

要点

  • 模型在内部测试集左右肾上腺DSC分别为0.920与0.910。
  • 同机构验证队列胸部CT左右肾上腺DSC为0.816与0.819。
  • 外部机构验证队列胸部CT左右肾上腺DSC为0.752与0.747。

核心结论

  • 基于3D V-Net的肾上腺分割模型达到可观的分割效能,并显示出从腹部CT到胸部CT的泛化性,作者认为其适用于各种扫描协议的CT图像,并有潜力作为辅助诊断的「标记」系统。

研究设计与样本

  • 回顾性收集肾上腺CT图像训练分割模型,腹部CT(正常与异常肾上腺,N=5660)作为模型开发队列并分为训练集、内部验证集和内部测试集;另纳入两组健康筛查受试者进行模型验证,验证队列1来自同一机构(N=6126),验证队列2来自外部机构(N=931),使用其胸部CT图像进行模型验证;以Dice相似系数(DSC)评估模型效能。

关键影像表现/征象

  • 模型在内部测试集对左、右肾上腺分割的DSC分别为0.920(0.890-0.930)和0.910(0.890-0.930)。
  • 验证队列1胸部CT左肾上腺DSC为0.816(0.744-0.866),右肾上腺DSC为0.819(0.743-0.865)。
  • 验证队列2胸部CT左肾上腺DSC为0.752(0.666-0.820),右肾上腺DSC为0.747(0.673-0.812)。

诊断标准与关键数值

  • 以Dice相似系数(DSC)评价分割效能,内部测试集左肾上腺0.920(0.890-0.930)、右肾上腺0.910(0.890-0.930)。
  • 验证队列1胸部CT左肾上腺DSC 0.816(0.744-0.866)、右肾上腺0.819(0.743-0.865)。
  • 验证队列2胸部CT左肾上腺DSC 0.752(0.666-0.820)、右肾上腺0.747(0.673-0.812)。

临床应用与阅片要点

  • 作者认为该模型有潜力作为辅助诊断的「标记」系统。

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

OBJECTIVES: To establish a 3D V-Net-based segmentation model for adrenal glands on abdominal CT images and validate its performance in multicentre datasets, including chest CT images.

METHODS: CT images of adrenal glands were retrospectively collected for the training of the adrenal segmentation model. Abdominal CT scans with normal and abnormal adrenal glands (N = 5660) were recruited as the model development cohort and were split into training, internal validation, and internal test sets for the development of the segmentation model. Two groups of health screening subjects were included for model validation: 1 from the same institution (N = 6126, validation cohort 1) and 1 from an outside institution (N = 931, validation cohort 2). Their chest CT images were used for model validation. The Dice similarity coefficient (DSC) was used to evaluate the efficacy of the model.

RESULTS: The DSC of the test set for left and right adrenal segmentation were 0.920 (0.890-0.930) and 0.910 (0.890-0.930), respectively. In the validation cohorts, the DSC were 0.816 (0.744-0.866) for the left adrenal gland and 0.819 (0.743-0.865) for the right adrenal gland in validation cohort 1, and 0.752 (0.666-0.820) for the left adrenal gland and 0.747 (0.673-0.812) for the right adrenal gland in validation cohort 2.

CONCLUSIONS: The 3D V-Net-based adrenal segmentation model achieves considerable segmentation efficacy and demonstrates generalizability from abdominal CT to chest CT, making it suitable for use in CT images with various scanning protocols.

ADVANCES IN KNOWLEDGE: The study developed a deep learning model using 3D V-Net for the segmentation of adrenal glands on CT images, achieving good performance of normal and abnormal glands in validation cohorts with different scanning protocols and from multiple institutions, demonstrating its potential as a "flagging" system aiding diagnosis.

来源:Br J Radiol,查看原文。版权归原作者所有。

引用

  1. Chen Y, Wang K, Zhang Y, et al. A multicentre validation study of 3D V-net-based segmentation model for adrenal glands: cross-protocol generalization from abdominal CT to chest CT. Br J Radiol. 2026. PMID: 41330715. doi:10.1093/bjr/tqaf294

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。