基于计算机断层血管造影图像利用深度学习和影像组学自动检测冠状动脉斑块、分类及狭窄分级:一项多中心多厂商研究
本研究回顾性纳入5个医疗中心的505例患者共127,763幅CTA图像,构建卷积神经网络联合影像组学的自动系统用于冠脉斑块检测、分类与狭窄分级;GBDT分类器在斑块分类(准确率87.0%、敏感度83.2%、特异度91.4%、AUC 0.873)和狭窄分级(准确率90.9%、敏感度84.1%、特异度95.7%、AUC 0.910)上表现最佳,处理每例患者耗时56.2±5.7秒,显著少于放射科医生人工分析的285.6±134.5秒(p=0.0001)。
要点
- 深度学习联合影像组学可自动完成冠脉斑块检测、分类和狭窄分级。
- GBDT模型斑块分类准确率87.0%、狭窄分级准确率90.9%。
- 自动系统处理每例患者耗时56.2±5.7秒,为人工分析的五分之一。
核心结论
- 本研究提出的自动工作流能以较高准确性和效率检测并分析冠状动脉斑块,显示出临床应用潜力。
研究设计与样本
- 回顾性研究,纳入5个医疗中心505例患者共127,763幅计算机断层血管造影(CTA)图像;采用卷积神经网络分割冠状动脉、检测斑块候选并提取图像块,再用人工设计的影像组学特征提取器收集斑块模式,由不同分类器完成斑块分类和狭窄分级。
诊断标准与关键数值
- 卷积神经网络在斑块候选检测中敏感度100%、阳性预测值83.9%,高于U-Net和基线模型;筛选26个代表性影像组学特征构建分类器,其中梯度提升决策树(GBDT)斑块分类准确率87.0%、敏感度83.2%、特异度91.4%、AUC 0.873,狭窄分级准确率90.9%、敏感度84.1%、特异度95.7%、AUC 0.910。
临床应用与阅片要点
- 自动系统处理每例患者耗时56.2±5.7秒,显著少于放射科医生人工分析的285.6±134.5秒(p=0.0001),作者认为该自动工作流显示出临床应用潜力。
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: An automatic system utilizing both the advantages of the neural network and the radiomics was proposed for coronary plaque detection, classification, and stenosis grading.
METHODS: This study retrospectively included 505 patients with 127,763 computed tomography angiography (CTA) images from 5 medical center. A convolutional neural network (CNN) model was used to segment the coronary artery, detect the plaque candidate, and extract the image patch with high computation efficiency. The manually designed radiomics feature extractor was utilized to collect plaque patterns, followed by the different classifiers to perform the plaque classification and stenosis grading.
RESULTS: The CNN model achieved 100% of sensitivity and the highest positive predictive value (83.9%) than U-Net and baseline model in plaque candidate detection. Twenty-six representative radiomics features were selected to construct the classifiers. Among different models, the gradient-boosting decision tree (GBDT) achieved the best performance in plaque classification (accuracy: 87.0%, sensitivity: 83.2%, specificity: 91.4%) and stenosis grading (accuracy: 90.9%, sensitivity: 84.1%, specificity: 95.7%). GBDT also achieved the highest AUC of 0.873 in plaque classification and 0.910 in stenosis grading. The computation time of processing one patient was 56.2 ± 5.7 s which was significantly less than radiologist manual analysis (285.6 ± 134.5 s, p = 0.0001).
CONCLUSIONS: In this study, an automatic workflow was proposed to detect and analyze coronary plaques with high accuracy and efficiency, showing the potential in clinical application.
KEY POINTS: • The proposed automatic system integrated deep learning and radiomics to perform the coronary plaque analysis. • The proposed automatic system achieved high accuracy in both plaque classification and stenosis grading. • The proposed automatic system was five times more efficient than radiologist manual analysis.
引用
- Jin, Li, Yan, et al. Automatic coronary plaque detection, classification, and stenosis grading using deep learning and radiomics on computed tomography angiography images: a multi-center multi-vendor study. Eur Radiol. 2022. PMID: 35290509. doi:10.1007/s00330-022-08664-z
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。