深度学习合成应变:MRI 定量评估区域性心肌室壁运动
本研究开发了深度学习合成应变(DLSS)算法,从电影稳态自由进动(SSFP)图像推断心肌速度。在 40 名无心脏病个体中建立正常节段径向应变范围(中位数 38%),并在 53 例缺血性心脏病患者 846 个节段中检测室壁运动异常,DLSS 的 AUC 为 0.90,以固定 30% 阈值为异常时敏感度 86%、特异度 85%、准确率 86%,与四位心胸放射科专科医师的共识判断性能相当。
要点
- DLSS 从常规电影 SSFP 图像推断心肌速度,无需额外采集速度数据即可评估室壁运动。
- 正常个体节段径向应变中位数为 38%,可作为参考范围。
- 以 30% 阈值为异常时,DLSS 检测室壁运动异常的敏感度 86%、特异度 85%、准确率 86%。
核心结论
- DLSS 从电影 SSFP 图像推断心肌速度和识别缺血性心脏病患者静息状态心肌室壁运动异常的性能与专科放射科医师相当。
研究设计与样本
- 回顾性研究,DLSS 开发使用 2017 年 11 月至 2021 年 5 月间 223 次心脏 MRI 检查数据(含电影 SSFP 图像和四维血流速度数据);正常范围在 40 名无心脏病个体(平均年龄 41 岁±17,30 名男性)中测量;检测性能在另一组 53 例冠心病患者(平均年龄 61 岁±12,41 名男性,846 个节段)中评估,以四位独立心胸放射科医师的共识结果为参考标准,采用受试者工作特征曲线分析评价算法性能。
诊断标准与关键数值
- 正常心脏 MRI 个体节段峰值径向应变中位数为 38%(IQR:30%-48%);在缺血性心脏病患者中,四位心胸放射科医师检测室壁运动异常的 Cohen κ 为 0.60-0.78;DLSS 的受试者工作特征曲线下面积为 0.90;采用固定 30% 阈值定义峰值径向应变异常时,DLSS 的敏感度、特异度和准确率分别为 86%、85% 和 86%。
临床应用与阅片要点
- DLSS 可基于常规电影 SSFP 图像推断心肌速度并检测缺血性心脏病患者静息状态下的室壁运动异常,性能与专科放射科医师共识相当。
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
PURPOSE: To assess the feasibility of a newly developed algorithm, called deep learning synthetic strain (DLSS), to infer myocardial velocity from cine steady-state free precession (SSFP) images and detect wall motion abnormalities in patients with ischemic heart disease.
MATERIALS AND METHODS: In this retrospective study, DLSS was developed by using a data set of 223 cardiac MRI examinations including cine SSFP images and four-dimensional flow velocity data (November 2017 to May 2021). To establish normal ranges, segmental strain was measured in 40 individuals (mean age, 41 years ± 17 [SD]; 30 men) without cardiac disease. Then, DLSS performance in the detection of wall motion abnormalities was assessed in a separate group of patients with coronary artery disease, and these findings were compared with consensus results of four independent cardiothoracic radiologists (ground truth). Algorithm performance was evaluated by using receiver operating characteristic curve analysis.
RESULTS: Median peak segmental radial strain in individuals with normal cardiac MRI findings was 38% (IQR: 30%-48%). Among patients with ischemic heart disease (846 segments in 53 patients; mean age, 61 years ± 12; 41 men), the Cohen κ among four cardiothoracic readers for detecting wall motion abnormalities was 0.60-0.78. DLSS achieved an area under the receiver operating characteristic curve of 0.90. Using a fixed 30% threshold for abnormal peak radial strain, the algorithm achieved a sensitivity, specificity, and accuracy of 86%, 85%, and 86%, respectively.
CONCLUSION: The deep learning algorithm had comparable performance with subspecialty radiologists in inferring myocardial velocity from cine SSFP images and identifying myocardial wall motion abnormalities at rest in patients with ischemic heart disease.Keywords: Neural Networks, Cardiac, MR Imaging, Ischemia/Infarction Supplemental material is available for this article. © RSNA, 2023.
引用
- Masutani EM, Chandrupatla RS, Wang S, et al. Deep Learning Synthetic Strain: Quantitative Assessment of Regional Myocardial Wall Motion at MRI. Radiol Cardiothorac Imaging. 2023. PMID: 37404797. doi:10.1148/ryct.220202
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。