Accuracy of Artificial Intelligence-Based Automated Quantitative Coronary Angiography Compared to Intravascular Ultrasound (Preprint)

BACKGROUND Accurate quantitative analysis of coronary artery stenotic lesions is essential to make optimal clinical decisions. Recent advances in computer vision and machine learning technology have enabled the automated analysis of coronary angiography. OBJECTIVE To validate the performance of artificial intelligence-based quantitative coronary angiography (AI-QCA) in comparison with that of intravascular ultrasound (IVUS). METHODS This retrospective study included patients who underwent IVUS-guided coronary intervention at a single center in Korea. Proximal and distal reference areas, minimal luminal area (MLA), percent plaque burden, and lesion length (LL) were measured by AI-QCA and human experts using IVUS. Scatter plots, Pearson correlation coefficients, and Bland-Altman were used to analyze the data. RESULTS A total of 54 significant lesions were analyzed in 47 patients. The proximal and distal reference areas, and MLA showed an acceptable correlation between the two modalities (correlation coefficients of 0.57, 0.80, and 0.52, respectively). The correlation was weaker for percent area stenosis and LL, although statistically significant (correlation coefficients, 0.29 and 0.33, respectively). AI-QCA tended to measure reference vessel areas smaller and lesion lengths shorter than IVUS did. The biggest cause of bias originated from the geographic mismatch of AI-QCA with IVUS. Discrepancies in the proximal and/or distal lesion margins were observed between the two modalities, which were more frequent at the distal margins. CONCLUSIONS AI-QCA showed a good correlation and acceptable accuracy compared with IVUS in analyzing coronary lesions with significant stenosis. We believe that this novel tool could provide confidence to treating physicians and help in making optimal clinical decisions.