Background/Aims: Intravascular imaging during percutaneous coronary intervention (PCI) improves clinical outcomes; however, is dependent on accurate and rapid interpretation of the images generated. This study aimed to compare coronary artery calcification assessment using a novel automated artificial intelligence (AI) software algorithm with manual optical coherence tomography (OCT) image analysis. Methods and Results: A deep neural network based on a UNet-like architecture was developed and trained to identify calcified atherosclerotic plaque from an independent dataset of expert-annotated clinical intravascular OCT pullbacks. The AI network was subsequently validated on previously unseen clinical OCT pullbacks that were manually annotated for plaque calcium and used to quantify clinically relevant calcified plaque characteristics. Correlation and agreement between the expert-annotated images and the model predictions were evaluated. In total, 8259 cross-sectional images comprised the training and internal validation dataset. Pixel-based classification by the AI model performed best to identify calcified plaque (AUC = 0.96), with an overall diagnostic accuracy of 73.3%. During independent external validation, the model correctly identified 934 of the 1248 calcified plaques, corresponding to a diagnostic accuracy of 74.8%. The AI model performed well in assessing the calculated OCT-calcium score (ρ = 0.84; 95% confidence interval [CI], 0.81–0.87, p ≤ 0.001). Conclusions: Implementation of an automated AI software algorithm provides a rapid and efficient method to comprehensively map coronary calcium in intravascular OCT images. With further training and refinement, it is anticipated that the AI machine learning software will continue to improve, enabling new robust tools for clinical OCT calcium detection to better guide PCI procedures.
12 August 2023 in Journal of the Society for Cardiovascular Angiography & Interventions
Long-term outcomes after percutaneous coronary intervention (PCI) for in-stent restenosis (ISR) are poor, yet limited granular procedural data exist evaluating lesion assessment, vessel treatment, and acute procedural outcomes. The LightLab Initiative was a multicenter, prospective, observational study with contemporaneous procedural data collection during PCI procedures. Data were collected during PCIs performed by 48 interventional cardiologists at 17 US hospitals (2019-2021). Optical coherence tomography (OCT) was performed pre-PCI for lesion assessment and post-PCI for stent optimization, and results were compared between ISR and de novo lesion PCI. In total, 2592 OCT-guided PCIs involving 2944 lesions were included, of which 458 procedures (17.7%) were ISR PCI. Compared with de novo lesion PCI, ISR lesions were more commonly type C (64.8% vs 52.9%) and performed via femoral artery access (46.4% vs 37.7%). Use of OCT changed operator assessment and treatment decisions more frequently in ISR PCI (94.2% vs 85.2%; P = .002). Scoring balloons (21.8% vs 2.5%), cutting balloons (16.4% vs 3.4%), and atherectomy (26.3% vs 9.9%) were used more commonly in ISR PCI (all P < .0001), and ISR PCI procedures were longer (62 vs 51 min). Moreover, the final achieved minimum stent area and percent expansion (4.4 vs 5.1 mm2 and 80% vs 83%, respectively; both P < .0001) were lower in ISR PCI. In this real-world cohort of patients who underwent OCT-guided PCI, ISR procedures were longer and final minimum stent area and percent expansion were lower despite greater use of advanced lesion modification. OCT frequently altered physician decision making, emphasizing its utility in potentially reducing recurrent stent failure in this high-risk population.