文献速递骨肌技术与安全胸部CT

CT椎体分割开放数据集与深度学习模型比较

Vertebral body segmentation in CT: An open dataset, deep-learning models and comparison to existing models.
PubMed 文献 · Eur J Radiol · 2026-07-30

本研究基于两个公共数据集的1460例CT扫描创建胸腰椎椎体标签,训练两个残差编码器nnU-Net模型并开发两步流程。在244例测试集及300例独立肿瘤数据集中评估分割性能与L3定位能力,并与现有模型比较。结果显示模型对L3椎体分割Dice达0.962,定位可靠,标签与模型权重已开放获取。

要点

  • 开放获取的椎体标签与模型权重可用于体成分分析等应用。
  • 模型对L3椎体分割Dice最高为0.962,定位误差低于TotalSegmentator椎体专用流程。
  • SPINEPS/VERIDAH因椎体定义不同需单独解读,不可直接比较。

核心结论

  • 所提出的模型能准确分割胸腰椎椎体并可靠识别第三腰椎(L3),标签、模型权重及体成分分析流程已开放获取。

研究设计与样本

  • 研究类型为深度学习模型开发与外部验证;训练集与测试集来自两个公共数据集的1460例CT扫描,其中1216例用于训练、244例用于测试。
  • 独立外部验证采用肿瘤数据集300例,由3名阅片者手动标注L3解剖标志作为参考标准。

关键影像表现/征象

  • 模型对L3椎体分割的Dice评分分别为0.962、0.939和0.953,中心命中率在各模型间均较高。
  • 绝对中心定位误差方面,VertebralBodiesL和VertebralBodiesStepwise低于TotalSegmentator椎体专用流程。
  • 符号中心定位误差在各模型间无显著性差异。

诊断标准与关键数值

  • L3椎体分割Dice评分:VertebralBodiesL为0.962(95%CI 0.941~0.978),另一模型为0.939(95%CI 0.907~0.965),两步流程为0.953(95%CI 0.926~0.974)。
  • 中心命中率定义为预测中心位于标注椎体范围内,各模型间均较高。
  • 绝对中心定位误差为预测中心与标注L3中心的颅尾方向距离,两种模型及两步流程均低于TotalSegmentator椎体专用流程。

临床应用与阅片要点

  • L3椎体可作为体成分分析等定量测量中的解剖定位标志。
  • 在阅片与报告中可借助该模型自动定位L3水平,提升测量一致性。
  • 与TotalSegmentator椎体专用流程比较时,优先使用VertebralBodiesL或VertebralBodiesStepwise以降低绝对定位误差。
  • SPINEPS/VERIDAH因椎体定义不同,其定位结果不能与本研究模型直接对比。

局限性

  • SPINEPS/VERIDAH的椎体定义与本研究不同,相关结果需单独解读。
  • 训练数据来源于两个公共数据集,未见前瞻性多中心外部验证。

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

PURPOSE: Vertebral bodies are anatomical landmarks for localizing measurements in applications such as body composition analysis. This study aimed to provide open-access vertebral body labels and deep-learning segmentation models, and to compare their performance in identifying the third lumbar vertebra (L3) with existing solutions.

MATERIALS AND METHODS: Thoracic and lumbar vertebral body labels were created for 1460 CT scans from two public datasets. Two residual-encoder nnU-Net models were trained on 1216 cases, and a two-step pipeline was developed. Segmentation performance was tested on 244 cases. In an independent oncological dataset of 300 cases, three readers manually annotated L3 landmarks. Labeling performance was assessed using signed and absolute center localization error (cranio-caudal distance between predicted and annotated L3 center) and center hit rate (predicted center within annotated vertebral body), followed by a comparison with existing models.

RESULTS: The two models and the two-step pipeline achieved Dice scores of 0.962 [95% CI, 0.941 to 0.978], 0.939 [95% CI, 0.907 to 0.965], and 0.953 [95% CI, 0.926 to 0.974] for segmentation of the L3 vertebral body. Center hit rates were similarly high across models. Signed center localization error did not differ significantly, whereas absolute center localization error was lower for VertebralBodiesL and VertebralBodiesStepwise than for the vertebral-body-specific TotalSegmentator pipeline. SPINEPS / VERIDAH results are reported separately because vertebral definitions differed.

CONCLUSION: The proposed models accurately segment thoracic and lumbar vertebral bodies and reliably identify L3. Labels, model weights, and a body composition analysis pipeline are openly available.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Hofmann, Auhage, Dexl, et al. Vertebral body segmentation in CT: An open dataset, deep-learning models and comparison to existing models. Eur J Radiol. 2026. PMID: 42561894. doi:10.1016/j.ejrad.2026.113118

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。