AI-powered optical coherence tomography shows similar performance to intravascular ultrasound for plaque burden quantification: head-to-head benchmark study against histopathology of native coronary arteries.
Authors
Affiliations (7)
Affiliations (7)
- Biomedical Instrument Institute, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China.
- School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, Guangdong, China.
- Division of Cardiology, Department of Medicine, Verona University Hospital, Verona 37126, Italy.
- Department of Histopathology, University Hospital Galway and University of Galway, Galway H91 YR71, Ireland.
- Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China.
- The Lambe Institute for Translational Medicine, Smart Sensors Laboratory and Curam, University of Galway, H91 TK33 Galway, Ireland.
- Department of Cardiology, Erasmus University Medical Center, Rotterdam 3015 GD, the Netherlands.
Abstract
Optical coherence tomography (OCT) provides excellent resolution at the cost of shallow penetration, limiting its ability for plaque burden (PB) assessment. A deep learning (DL) algorithm was therefore developed to provide fully automated assessment of PB and vessel size from OCT. We aimed to perform a head-to-head comparison of AI-powered OCT vs. intravascular ultrasound (IVUS) for PB quantification, using histopathology as the reference standard. Ten post-mortem human hearts were harvested. All 29 major epicardial coronary arteries were perfused and underwent OCT and IVUS pullbacks. After imaging, the arteries were serially sectioned at 1-mm intervals for histopathology. Lumen and vessel contours were derived fully automatically from OCT using the DL algorithm and semi-automatically from IVUS. Histopathological measurements were obtained by experienced analysts. Statistical analyses accounted for within-patient clustering. A total of 852 paired OCT-IVUS histopathology cross-sections were obtained. AI-powered OCT showed strong correlations with histopathology for the assessment of lumen area (<i>r</i> = 0.89 [95% CI: 0.88-0.91]), vessel area (<i>r</i> = 0.85 [95% CI: 0.83-0.87]), and PB (<i>r</i> = 0.76 [95% CI: 0.73-0.79]). The corresponding correlations between IVUS and histopathology were 0.90 (95% CI: 0.89-0.92), 0.86 (95% CI: 0.84-0.88), and 0.79 (95% CI: 0.76-0.81), respectively. Comparisons of the OCT-histopathology and IVUS-histopathology correlation coefficients yielded <i>P</i> = 0.336 for lumen area, <i>P</i> = 0.444 for vessel area, and <i>P</i> = 0.161 for PB. Both OCT and IVUS showed good diagnostic performance in identifying PB > 65%, with the area under the receiver operating characteristic curve being 0.92 (95% CI: 0.90-0.94) and 0.92 (95% CI: 0.88-0.95), respectively. In this histopathology validation study of 10 post-mortem human hearts, AI-powered OCT enabled fully automated plaque burden quantification and correlated strongly with histopathology, with no statistically significant difference between the OCT-histopathology and IVUS-histopathology correlations.