Artificial intelligence-powered automatic coronary computed tomography angiography plaque quantification: comparison...

Area of Science:

• Cardiovascular Imaging
• Artificial Intelligence in Medicine
• Medical Diagnostics

Background:

• Coronary computed tomography angiography (CCTA) is a key non-invasive tool for assessing coronary artery disease (CAD).
• Artificial intelligence (AI) has the potential to enhance the interpretation of CCTA images, particularly in plaque quantification.
• Accurate plaque characterization is crucial for predicting cardiovascular events.

Purpose of the Study:

• To evaluate an AI-powered method for automatic plaque quantification from CCTA.
• To compare AI-derived plaque quantification with optical coherence tomography (OCT) as the reference standard.
• To assess the performance of AI in identifying high-risk plaque features and vulnerable plaques.

Main Methods:

• Retrospective analysis of patients who underwent both CCTA and OCT.
• AI-assisted automatic plaque quantification and composition classification on CCTA using adaptive Hounsfield unit thresholds.
• Automated co-registration of CCTA and OCT data.
• Evaluation of 91 patients with 153 co-registered lesions.

Main Results:

• AI-assisted CCTA plaque quantification showed significant correlations with OCT for plaque volume (r=0.84), plaque burden, and composition (all P<0.001).
• AI identified independent predictors of OCT-derived vulnerable plaques, including CCTA-derived plaque volume, maximal plaque burden, lipidic tissue volume, and high-risk plaque features.
• The average time for AI-based plaque quantification was 1.8 minutes per patient.

Conclusions:

• A novel AI-powered method enables fully automatic plaque quantification from CCTA.
• The AI method demonstrates strong correlation with OCT, supporting its utility in clinical practice.
• This AI tool has the potential to improve the efficiency and accuracy of coronary artery disease assessment using CCTA.