文献速递外周血管腹部介入CT

用深度学习量化腹主动脉及其主要分支的钙化

Quantifying the calcification of abdominal aorta and major side branches with deep learning.
PubMed 文献 · Clin Radiol · 2024-02-03

本研究从609例CT血管造影数据集中选取58例,训练两个V-Net集成模型分别分割目标动脉及钙化,并与人工勾画的参考标准比较。钙化集成模型Dice为0.69、体积相似性为0.80;主动脉分割Dice为0.96、体积相似性为0.98;主动脉分支Dice为0.74、体积相似性为0.87;髂总动脉Dice为0.72、体积相似性为0.91。作者认为该神经网络模型首次能在对比增强CT血管造影上同时自动分割主动脉、其分支及钙化,该技术有望解决既往仅依赖平扫CT方法的局限。

要点

  • 钙化集成模型与参考标准高度相关,Dice为0.69、体积相似性为0.80。
  • 主动脉分割Dice为0.96、体积相似性为0.98,分支为Dice 0.74、体积相似性0.87。
  • 该模型首次在增强CT血管造影上同时自动分割主动脉、分支及钙化。

核心结论

  • 基于神经网络的模型能自动分割腹主动脉及其分支并量化钙化,与人工参考标准高度相关;作者认为该技术有望解决既往仅依赖平扫CT方法的局限。

研究设计与样本

  • 从609例CT血管造影数据集中选取58例不同硬化阶段的CT血管造影容积,人工勾画腹主动脉、腹腔干、肠系膜上动脉、肾动脉、髂总动脉及其钙化的参考标准,训练两个V-Net集成模型分别分割目标动脉和钙化,并对目标分支进行算法缩短后评估钙化体积。

诊断标准与关键数值

  • 钙化集成模型:Dice为0.69,体积相似性为0.80。
  • 主动脉分割:Dice为0.96,体积相似性为0.98。
  • 主动脉分支分割:Dice为0.74,体积相似性为0.87。
  • 髂总动脉分割:Dice为0.72,体积相似性为0.91。

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

AIM: To explore the possibility of a neural network-based method for quantifying calcifications of the abdominal aorta and its branches.

MATERIALS AND METHODS: In total, 58 computed tomography (CT) angiography volumes were selected from a dataset of 609 to represent different stages of sclerosis. The ground truth segmentations of the abdominal aorta, coeliac trunk, superior mesenteric artery, renal arteries, common iliac arteries, and their calcifications were delineated manually. Two V-Net ensemble models were trained, one for segmenting arteries of interest and another for calcifications. The branches of interest were shortened algorithmically. The volumes of calcification were then evaluated from the arteries of interest.

RESULTS: The results indicate that automatic detection is possible with a high correlation to the ground truth. The scores for the ensemble calcification model were dice score of 0.69 and volumetric similarity (VS) of 0.80 and for the arteries of interest segmentations: aorta: dice 0.96, VS 0.98; aortic branches: dice 0.74, VS 0.87; and common iliac arteries: dice 0.72, VS 0.91.

CONCLUSIONS: The presented neural network model is the first to be capable of automatically segmenting, in addition to calcification, both the aorta and its branches from contrast-enhanced CT angiography. This technology shows promise in addressing limitations inherent in earlier methods that relied solely on plain CT.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Halkoaho J, Niiranen O, Salli E, et al. Quantifying the calcification of abdominal aorta and major side branches with deep learning. Clin Radiol. 2024. PMID: 38365540. doi:10.1016/j.crad.2024.01.023

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。