文献速递心血管CT

基于深度学习的心脏计算机断层扫描左心室心肌自动分割

Automated Segmentation of Left Ventricular Myocardium on Cardiac Computed Tomography Using Deep Learning.
PubMed 文献 · Korean J Radiol · 2020-01-01

研究开发并评估基于深度学习的心脏CT左心室心肌全自动分割算法,使用100例冠心病患者(50训练/20验证/30内部测试)建立模型,另用1000例验证集评估。自动分割各节段敏感度和特异度高(85.5-100.0%),Dice相似系数88.3±6.2%,视觉评估无不准病例,深度学习掩膜非常准确病例数多于手动分割。

要点

  • 自动分割各节段(1-16节段)敏感度和特异度为85.5-100.0%,Dice相似系数88.3±6.2%。
  • 视觉评估中手动与深度学习掩膜均无不准病例,深度学习非常准确病例数(53例)多于手动(31例)。
  • 研究使用100例冠心病患者开发模型(50训练/20验证/30内部测试),另以1000例验证集评估。

核心结论

  • 基于深度学习的心脏CT左心室心肌自动分割结果与手动分割数据相当,具有高敏感度、高特异度和高相似度评分。

研究设计与样本

  • 研究为算法开发与评估研究,随机选取100例冠心病患者作为开发集(50训练/20验证/30内部测试),由经验丰富的心脏放射科医生生成开发集手动分割。
  • 训练模型使用经验丰富的技师生成的1000例验证集进行评估,并进行视觉评估比较手动与自动分割。
  • 定量分析根据手动与深度学习三维掩膜重叠的像素数计算敏感度和特异度,并使用Dice相似系数等相似性指数评估分割掩膜边缘。

诊断标准与关键数值

  • 自动分割各节段(1-16节段)的敏感度和特异度为85.5-100.0%。
  • Dice相似系数为88.3±6.2%。
  • 视觉评估中,手动分割与深度学习掩膜均分类为非常准确至基本准确,无不准病例(手动 vs 深度学习:非常准确31 vs 53;准确64 vs 39;基本准确15 vs 8)。

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

OBJECTIVE: To evaluate the accuracy of a deep learning-based automated segmentation of the left ventricle (LV) myocardium using cardiac CT.

MATERIALS AND METHODS: To develop a fully automated algorithm, 100 subjects with coronary artery disease were randomly selected as a development set (50 training / 20 validation / 30 internal test). An experienced cardiac radiologist generated the manual segmentation of the development set. The trained model was evaluated using 1000 validation set generated by an experienced technician. Visual assessment was performed to compare the manual and automatic segmentations. In a quantitative analysis, sensitivity and specificity were calculated according to the number of pixels where two three-dimensional masks of the manual and deep learning segmentations overlapped. Similarity indices, such as the Dice similarity coefficient (DSC), were used to evaluate the margin of each segmented masks.

RESULTS: The sensitivity and specificity of automated segmentation for each segment (1-16 segments) were high (85.5-100.0%). The DSC was 88.3 ± 6.2%. Among randomly selected 100 cases, all manual segmentation and deep learning masks for visual analysis were classified as very accurate to mostly accurate and there were no inaccurate cases (manual vs. deep learning: very accurate, 31 vs. 53; accurate, 64 vs. 39; mostly accurate, 15 vs. 8). The number of very accurate cases for deep learning masks was greater than that for manually segmented masks.

CONCLUSION: We present deep learning-based automatic segmentation of the LV myocardium and the results are comparable to manual segmentation data with high sensitivity, specificity, and high similarity scores.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Koo HJ, Lee JG, Ko JY, et al. Automated Segmentation of Left Ventricular Myocardium on Cardiac Computed Tomography Using Deep Learning. Korean J Radiol. 2020. PMID: 32410405. doi:10.3348/kjr.2019.0378

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。