Dataset related to the article "Diagnostic performance of deep learning algorithm for analysis of computed tomography myocardial perfusion"

This record contains raw data related to the article “Diagnostic performance of deep learning algorithm for analysis of computed tomography myocardial perfusion" <strong>Purpose: </strong>To evaluate the diagnostic accuracy of a deep learning (DL) algorithm predicting hemodynamically significant coronary artery disease (CAD) by using a rest dataset of myocardial computed tomography perfusion (CTP) as compared to invasive evaluation. <strong>Methods: </strong>One hundred and twelve consecutive symptomatic patients scheduled for clinically indicated invasive coronary angiography (ICA) underwent CCTA plus static stress CTP and ICA with invasive fractional flow reserve (FFR) for stenoses ranging between 30 and 80%. Subsequently, a DL algorithm for the prediction of significant CAD by using the rest dataset (CTP-DL_rest) and stress dataset (CTP-DL_stress) was developed. The diagnostic accuracy for identification of significant CAD using CCTA, CCTA + CTP stress, CCTA + CTP-DL_rest, and CCTA + CTP-DL_stress was measured and compared. The time of analysis for CTP stress, CTP-DL_rest, and CTP-DL_Stress was recorded. <strong>Results: </strong>Patient-specific sensitivity, specificity, NPV, PPV, accuracy, and area under the curve (AUC) of CCTA alone and CCTA + CTP_Stress were 100%, 33%, 100%, 54%, 63%, 67% and 86%, 89%, 89%, 86%, 88%, 87%, respectively. Patient-specific sensitivity, specificity, NPV, PPV, accuracy, and AUC of CCTA + DL_rest and CCTA + DL_stress were 100%, 72%, 100%, 74%, 84%, 96% and 93%, 83%, 94%, 81%, 88%, 98%, respectively. All CCTA + CTP stress, CCTA + CTP-DL_Rest, and CCTA + CTP-DL_Stress significantly improved detection of hemodynamically significant CAD compared to CCTA alone (p &lt; 0.01). Time of CTP-DL was significantly lower as compared to human analysis (39.2 ± 3.2 vs. 379.6 ± 68.0 s, p &lt; 0.001). <strong>Conclusion: </strong>Evaluation of myocardial ischemia using a DL approach on rest CTP datasets is feasible and accurate. This approach may be a useful gatekeeper prior to CTP stress_..本数据集包含与题为《深度学习算法用于心肌计算机断层灌注成像分析的诊断性能》的研究论文相关的原始数据。<strong>研究目的：</strong>本研究以静息态心肌计算机断层灌注成像（Myocardial Computed Tomography Perfusion, CTP）数据集为研究对象，旨在评估深度学习（Deep Learning, DL）算法预测血流动力学显著性冠状动脉疾病（Coronary Artery Disease, CAD）的诊断准确性，并将其结果与侵入性评估结果进行对比。<strong>研究方法：</strong>共纳入112例连续就诊的有症状患者，这些患者均因临床指征计划接受侵入性冠状动脉造影（Invasive Coronary Angiography, ICA）。所有患者均接受了冠状动脉计算机断层血管造影（Coronary Computed Tomography Angiography, CCTA）、静态负荷态CTP以及针对30%~80%狭窄病变的侵入性血流储备分数（Fractional Flow Reserve, FFR）检测。随后，研究人员基于静息态CTP数据集（CTP-DL_静息）和负荷态CTP数据集（CTP-DL_负荷）开发了用于预测显著性冠状动脉疾病的DL算法。随后对单独使用CCTA、CCTA联合负荷态CTP、CCTA联合CTP-DL_静息以及CCTA联合CTP-DL_负荷识别显著性冠状动脉疾病的诊断准确性进行了测量与对比。同时记录了负荷态CTP、CTP-DL_静息与CTP-DL_负荷的分析耗时。<strong>研究结果：</strong>单独使用CCTA以及CCTA联合负荷态CTP的患者特异性灵敏度、特异度、阴性预测值、阳性预测值、准确率以及受试者工作特征曲线下面积（Area Under the Curve, AUC）分别为100%、33%、100%、54%、63%、67%与86%、89%、89%、86%、88%、87%。CCTA联合CTP-DL_静息以及CCTA联合CTP-DL_负荷的患者特异性灵敏度、特异度、阴性预测值、阳性预测值、准确率以及AUC分别为100%、72%、100%、74%、84%、96%与93%、83%、94%、81%、88%、98%。相较于单独使用CCTA，CCTA联合负荷态CTP、CCTA联合CTP-DL_静息以及CCTA联合CTP-DL_负荷均能显著提升血流动力学显著性冠状动脉疾病的检出效能（p＜0.01）。CTP-DL的分析耗时显著低于人工分析（39.2±3.2 vs. 379.6±68.0 s，p＜0.001）。<strong>研究结论：</strong>基于静息态CTP数据集的DL算法评估心肌缺血具有可行性与准确性。该方法或可成为负荷态CTP检查前的有效筛查手段。