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... Show moreObjectivesThe 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. Show less
Heterogeneous neointimal response has been observed after implantation of all generations of coronary stents. Our aim was assessing local factors of shear stress (SS) and plaque characteristics in... Show moreHeterogeneous neointimal response has been observed after implantation of all generations of coronary stents. Our aim was assessing local factors of shear stress (SS) and plaque characteristics in neointimal response after implantation of bioresorbable scaffolds (BRS) in bifurcations. Ten patients from the BIFSORB pilot study were analysed. Follow-up optical frequency domain imaging (OFDI) was performed at 1 month and 2 years. Coronary lumen and BRS structure were reconstructed by fusion of OFDI and angiography and were used for subsequent flow simulation. Plaque arc degree and SS were quantified using post-procedural OFDI data and were matched with follow-up OFDI using anatomical landmarks. Strut-level and segment-level analysis were performed for 1-month and 2-year follow-up respectively. A total of 444 struts (54 jailing struts) were included at 1-month follow-up. Time-average SS (TASS) was significantly lower for covered struts than for uncovered struts in non-bifurcation segments (TASS: 1.81 +/- 1.87 vs. 3.88 +/- 3.72 Pa, p < 0.001). The trend remained the same for jailing struts, although statistically insignificant (TASS: 10.85 +/- 13.12 vs. 13.64 +/- 14.48 Pa, p = 0.328). For 2-year follow-up, a total of 66 sub-regions were analysed. Neointimal hyperplasia area (NTA) was negatively correlated with TASS in core-segments (rho = - 0.389, p = 0.037) and positively correlated with plaque arc degree in non-core segments (rho = 0.387, p = 0.018). Slightly stronger correlations with NTA were observed when combining TASS and plaque arc degree in both core segments (rho = - 0.412, p = 0.026) and non-core segments (rho = - 0.395, p = 0.015). Hemodynamic microenvironment and baseline plaque characteristics may regulate neointimal response after BRS implantation in bifurcation. These findings underline the combined role of plaque characteristics and local hemodynamics in vessel healing after stent implantation. Show less
De Weerdt, H.G.D.G.; Ho, B.; Wagner, A.; Qiao, J.; Chu, M. 2020
