Background: Coronary angiography is fundamental for the diagnosis and treatment of coronary artery disease. Manual quantitative coronary angiography (QCA) is accurate and reproducible; however, it is time-consuming and labor-intensive. However, recent advancements in artificial intelligence (AI) have enabled automated and rapid analysis of medical images, addressing the need for real-time quantitative coronary analysis.
Aims: This study aimed to evaluate the accuracy of AI-based QCA (AI-QCA) compared with that via manual QCA and clinician acceptance.
Methods: This retrospective, single-center study was conducted in two phases. Phase 1 was a pilot study comparing AI-QCA with manual QCA and visual estimation. It involved 15 patients who underwent coronary angiography at Seoul National University Bundang Hospital between September 2011 and July 2021. Phase 2 included a larger cohort of 762 patients, with 1002 coronary angiograms analyzed between May 2020 and April 2021.
Results: In phase 1, AI-QCA and manual QCA consistency varied among the observers, with AI-QCA showing superior consistency compared with visual estimation. However, a strong correlation between AI-QCA and manual-QCA was found in phase 2. AI-QCA accurately identified and quantitatively analyzed multiple lesions in the major vessels, providing results comparable with those of manual QCA.
Conclusions: AI-QCA demonstrated high concordance with manual QCA, offering real-time analysis and reduced workload. Therefore, AI-QCA has the potential to be a valuable tool for diagnosing and treating coronary artery disease, necessitating further studies for clinical validation.
Keywords: Coronary artery disease; deep learning; external validation; object detection; quantitative coronary angiography.
© The Author(s) 2024.