Plaque burden estimated from optical coherence tomography with deep learning: In vivo validation using co-registered intravascular ultrasound
Plaque burden estimated from optical coherence tomography with deep learning: In vivo validation using co-registered intravascular ultrasound
复制标题
通过光学相干断层扫描和深度学习估计斑块负荷：使用联合配准血管内超声进行体内验证
DOI：
10.1002/ccd.30525
复制
发表时间：
2022
影响因子：
2.3
通讯作者：
William Wijns
中科院分区：
文献类型：
--
作者：
Jiayue Huang;Shengxian Tu;Shinichiro Masuda;Kai Ninomiya;Jouke Dijkstra;Miao Chu;Daixin Ding;Sean O. Hynes;Neil O'Leary;Yoshinobu Onuma;Patrick W. Serruys;William Wijns
目的本研究的目的是比较使用深度学习（DL）从光学相干断层扫描（OCT）计算的斑块负荷（PB）与来自共配准血管内超声（IVUS）的PB。背景开发了一种用于OCT图像自动斑块表征和PB量化的DL算法。然而，这种算法的性能PB量化尚未validated.MethodsFive年随访OCT和IVUS图像从15例植入生物可吸收血管支架（BVS）在基线进行了分析。使用独特的BVS不透射线标记实现了72个解剖切片的精确配准。比较OCT DL和IVUS的PB。OCT横截面分为4个亚组，具有不同的介质可见性水平。研究了介质可见性对OCT和IVUS PB之间数值差异的影响。OCT DL和IVUS选择的支架尺寸进行了比较。ResultsSixty‐ 4配对OCT和IVUS横截面进行了比较。OCT DL与IVUS在PB评估方面显示出良好的一致性（ICC = 0.81，差异=-3.53 ± 6.17%，p < 0.001）。OCT DL衍生PB和IVUS衍生PB之间的数值差异基本上不受中膜可视化缺失节段的影响（p= 0.21）。OCT DL在识别PB > 65%时的诊断准确率为92%。OCT DL选择的支架尺寸小于IVUS选择的支架尺寸（差异= 0.30 ± 0.34 mm，p< 0.001）。OCT DL在识别PB > 65%时显示出良好的诊断准确性，揭示了其补充传统OCT成像的潜力。
ObjectivesThe objective of the present study was to compare plaque burden (PB) calculated from optical coherence tomography (OCT) using deep learning (DL) with PB derived from co‐registered intravascular ultrasound (IVUS).BackgroundA DL algorithm was developed for automated plaque characterization and PB quantification from OCT images. However, the performance of this algorithm for PB quantification has not been validated.MethodsFive‐year follow‐up OCT and IVUS images from 15 patients implanted with bioresorbable vascular scaffold (BVS) at baseline were analyzed. Precise co‐registration for 72 anatomical slices was achieved utilizing unique BVS radiopaque markers. PB derived from OCT DL and IVUS were compared. OCT cross‐sections were divided into four subgroups with different media visibility level. The impact of media visibility on the numerical difference between OCT‐derived and IVUS‐derived PB was investigated. The stent sizes selected by OCT DL and IVUS were compared.ResultsSixty‐four paired OCT and IVUS cross‐sections were compared. OCT DL showed good concordance with IVUS for PB assessment (ICC = 0.81, difference = −3.53 ± 6.17%,p< 0.001). The numerical difference between OCT DL‐derived PB and IVUS‐derived PB was not substantially impacted by missing segments of media visualization (p= 0.21). OCT DL showed a diagnostic accuracy of 92% in identifying PB > 65%. The stent sizes selected by OCT DL were smaller compared to the ones selected by IVUS (difference = 0.30 ± 0.34 mm,p< 0.001).ConclusionsThe DL algorithm provides a feasible and reliable method for automated PB estimation from OCT, irrespective of media visibility. OCT DL showed good diagnostic accuracy in identifying PB > 65%, revealing its potential to complement conventional OCT imaging.