深度学习从快速心肌灌注SPECT预测阻塞性病变:一项多中心研究
本研究在9个中心纳入1638例无已知冠心病、接受新型固态探测器应激心肌灌注SPECT且6个月内行有创冠状动脉造影的患者,评估深度学习对比总灌注缺损(TPD)预测阻塞性病变的效能。深度学习预测的受试者工作特征曲线下面积高于TPD(每患者0.80 vs 0.78,每血管0.76 vs 0.73,p<0.01);在与TPD相同特异度下,每患者敏感度从79.8%提高至82.3%,每血管敏感度从64.4%提高至69.8%。
要点
- 深度学习预测阻塞性冠心病的每患者AUC为0.80,高于TPD的0.78(p<0.01)。
- 相同特异度下每患者敏感度从TPD的79.8%提升至深度学习的82.3%(p<0.05)。
- 每血管AUC为深度学习0.76 vs TPD 0.73,敏感度64.4%提升至69.8%(p<0.01)。
核心结论
- 与当前临床方法TPD相比,深度学习有潜力改善心肌灌注SPECT的自动判读。
研究设计与样本
- 多中心研究,纳入9个中心1638例(67%男性)无已知冠心病患者,使用新型固态探测器行应激99mTc-sestamibi或tetrofosmin心肌灌注SPECT,并在SPECT后6个月内行有创冠状动脉造影。
关键影像表现/征象
- 左心室心肌使用临床核心脏病学软件分割并经专家阅片者核实。
- 应激TPD使用性别和相机特异性正常限值计算。
- 深度学习使用原始和定量极坐标图训练,并在分层10折交叉验证中评估阻塞性狭窄预测。
诊断标准与关键数值
- 阻塞性病变定义为冠状动脉狭窄≥70%(左主干≥50%)。
- 深度学习预测每患者阻塞性病变的AUC为0.80,TPD为0.78(p<0.01)。
- 深度学习预测每血管阻塞性病变的AUC为0.76,TPD为0.73(p<0.01)。
- 深度学习阈值设为与TPD相同特异度时,每患者敏感度从TPD的79.8%提高至深度学习的82.3%(p<0.05)。
- 相同特异度下,每血管敏感度从TPD的64.4%提高至深度学习的69.8%(p<0.01)。
临床应用与阅片要点
- 深度学习可能改善心肌灌注SPECT对阻塞性冠心病的自动预测,但原文未据此给出具体阅片或报告建议。
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: The study evaluated the automatic prediction of obstructive disease from myocardial perfusion imaging (MPI) by deep learning as compared with total perfusion deficit (TPD).
BACKGROUND: Deep convolutional neural networks trained with a large multicenter population may provide improved prediction of per-patient and per-vessel coronary artery disease from single-photon emission computed tomography MPI.
METHODS: A total of 1,638 patients (67% men) without known coronary artery disease, undergoing stress 99mTc-sestamibi or tetrofosmin MPI with new generation solid-state scanners in 9 different sites, with invasive coronary angiography performed within 6 months of MPI, were studied. Obstructive disease was defined as ≥70% narrowing of coronary arteries (≥50% for left main artery). Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. Stress TPD was computed using sex- and camera-specific normal limits. Deep learning was trained using raw and quantitative polar maps and evaluated for prediction of obstructive stenosis in a stratified 10-fold cross-validation procedure.
RESULTS: A total of 1,018 (62%) patients and 1,797 of 4,914 (37%) arteries had obstructive disease. Area under the receiver-operating characteristic curve for disease prediction by deep learning was higher than for TPD (per patient: 0.80 vs. 0.78; per vessel: 0.76 vs. 0.73: p < 0.01). With deep learning threshold set to the same specificity as TPD, per-patient sensitivity improved from 79.8% (TPD) to 82.3% (deep learning) (p < 0.05), and per-vessel sensitivity improved from 64.4% (TPD) to 69.8% (deep learning) (p < 0.01).
CONCLUSIONS: Deep learning has the potential to improve automatic interpretation of MPI as compared with current clinical methods.
引用
- Betancur J, Commandeur F, Motlagh M, et al. Deep Learning for Prediction of Obstructive Disease From Fast Myocardial Perfusion SPECT: A Multicenter Study. JACC Cardiovasc Imaging. 2018. PMID: 29550305. doi:10.1016/j.jcmg.2018.01.020
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。