Artificial intelligence and cloud based platform for fully automated PCI guidance from coronary angiography-study...

Area of Science:

• Cardiology
• Medical Imaging
• Artificial Intelligence

Background:

• Ischemic heart disease poses a significant global health burden.
• Current diagnostic and treatment methods for coronary artery disease require optimization.
• Percutaneous coronary intervention (PCI) is a common treatment, but optimal strategy selection can be challenging.

Purpose of the Study:

• To develop and validate an AI-driven platform for automated PCI guidance.
• To utilize AI for 3D coronary anatomy reconstruction and functional assessment (FFR).
• To provide clinicians with comprehensive reports and treatment scenarios for optimal PCI strategy selection.

Main Methods:

• Development of multiple AI models for image analysis and functional computation.
• Integration of AI outputs into a cloud-based platform for clinical decision support.
• Prospective pilot clinical study to validate AI algorithms against invasive measurements and expert annotations.

Main Results:

• The AI platform generates 3D coronary anatomy reconstructions.
• Post-PCI fractional flow reserve (FFR) computation is performed using AI.
• The platform presents anatomical and functional assessments, pre- and post-PCI, to clinicians.

Conclusions:

• The AI-driven platform offers a novel approach to automated PCI guidance.
• Integration of AI in PCI planning may enhance treatment decision-making and patient outcomes.
• Clinical validation is crucial to establish the efficacy and reliability of AI in interventional cardiology.