Prognostic Value Of Deep Learning Based RCA PCAT and Plaque Volume Beyond CT-FFR In Patients With Stent Implantation

Area of Science:

• Cardiovascular Imaging
• Artificial Intelligence in Medicine
• Interventional Cardiology

Background:

• Coronary computed tomography angiography (CTA) is crucial for assessing coronary artery disease.
• Fractional flow reserve (FFR) derived from CT (CT-FFR) assesses lesion severity, but its prognostic value post-percutaneous coronary intervention (PCI) needs further evaluation.
• Pericoronary adipose tissue (PCAT) attenuation and plaque volume are emerging imaging biomarkers.

Purpose of the Study:

• To evaluate the prognostic significance of deep learning-based PCAT attenuation and plaque volume compared to CT-FFR.
• To determine if these imaging parameters predict major adverse cardiovascular events (MACE) in patients who have undergone PCI.

Main Methods:

• Retrospective analysis of 183 patients with PCI who underwent coronary CTA.
• AI-assisted workstation used for quantifying PCAT attenuation and plaque volume.
• Kaplan-Meier analysis and multivariate Cox regression used to assess MACE (non-fatal MI, stroke, mortality).

Main Results:

• A total of 22 MACE occurred during follow-up.
• Right coronary artery (RCA) PCAT attenuation and plaque volume were significantly associated with increased MACE (p=0.007 and p=0.008, respectively).
• RCA PCAT and plaque volume were independent predictors of MACE (HR: 2.94, p=0.025 and HR: 3.91, p=0.024), whereas CT-FFR was not (p=0.271).

Conclusions:

• Deep learning-based analysis of RCA PCAT attenuation and plaque volume from coronary CTA offers significant prognostic value.
• These parameters are more strongly associated with MACE than CT-FFR in patients post-PCI.
• AI-driven imaging biomarkers hold promise for risk stratification in patients undergoing PCI.