Department of Cardiology (A.C., M.L.L., J.D., K.N.)
Department of Radiology (A.C., A.K., M.L.L., K.N.).
Circ Cardiovasc Imaging. 2018 Jun;11(6):e007217. doi: 10.1161/CIRCIMAGING.117.007217.
Coronary computed tomographic angiography (CTA) is a reliable modality to detect coronary artery disease. However, CTA generally overestimates stenosis severity compared with invasive angiography, and angiographic stenosis does not necessarily imply hemodynamic relevance when fractional flow reserve (FFR) is used as reference. CTA-based FFR (CT-FFR), using computational fluid dynamics (CFD), improves the correlation with invasive FFR results but is computationally demanding. More recently, a new machine-learning (ML) CT-FFR algorithm has been developed based on a deep learning model, which can be performed on a regular workstation. In this large multicenter cohort, the diagnostic performance ML-based CT-FFR was compared with CTA and CFD-based CT-FFR for detection of functionally obstructive coronary artery disease.
At 5 centers in Europe, Asia, and the United States, 351 patients, including 525 vessels with invasive FFR comparison, were included. ML-based and CFD-based CT-FFR were performed on the CTA data, and diagnostic performance was evaluated using invasive FFR as reference. Correlation between ML-based and CFD-based CT-FFR was excellent (=0.997). ML-based (area under curve, 0.84) and CFD-based CT-FFR (0.84) outperformed visual CTA (0.69; <0.0001). On a per-vessel basis, diagnostic accuracy improved from 58% (95% confidence interval, 54%-63%) by CTA to 78% (75%-82%) by ML-based CT-FFR. The per-patient accuracy improved from 71% (66%-76%) by CTA to 85% (81%-89%) by adding ML-based CT-FFR as 62 of 85 (73%) false-positive CTA results could be correctly reclassified by adding ML-based CT-FFR.
On-site CT-FFR based on ML improves the performance of CTA by correctly reclassifying hemodynamically nonsignificant stenosis and performs equally well as CFD-based CT-FFR.
冠状动脉计算机断层血管造影（CTA）是一种可靠的方法，可用于检测冠状动脉疾病。然而，与有创血管造影相比，CTA 通常会高估狭窄程度，并且当使用血流储备分数（FFR）作为参考时，血管造影狭窄并不一定意味着存在血流动力学相关性。基于计算流体动力学（CFD）的 CTA 衍生 FFR（CT-FFR）可提高与有创 FFR 结果的相关性，但计算要求较高。最近，一种新的基于机器学习（ML）的 CT-FFR 算法已基于深度学习模型开发，可以在常规工作站上进行。在这项大型多中心队列研究中，比较了基于 ML 的 CT-FFR 与 CTA 和基于 CFD 的 CT-FFR 在检测功能性阻塞性冠状动脉疾病方面的诊断性能。
在欧洲、亚洲和美国的 5 个中心，纳入了 351 例患者（包括 525 支血管有有创 FFR 比较）。在 CTA 数据上进行了基于 ML 和基于 CFD 的 CT-FFR，使用有创 FFR 作为参考来评估诊断性能。ML 与 CFD 之间的相关性非常好（=0.997）。ML （曲线下面积，0.84）和 CFD （0.84）均优于 CTA（0.69；<0.0001）。基于血管的诊断准确性从 CTA 的 58%（95%置信区间，54%-63%）提高到基于 ML 的 CT-FFR 的 78%（75%-82%）。基于患者的诊断准确性从 CTA 的 71%（66%-76%）提高到添加 ML 后为 85%（81%-89%），因为添加 ML 可将 85 例患者中的 62 例（73%）假阳性 CTA 结果正确重新分类。
基于 ML 的即时 CT-FFR 可通过正确重新分类无血流动力学意义的狭窄来提高 CTA 的性能，并且与基于 CFD 的 CT-FFR 性能相当。
