Artificial Intelligence in Image-Based Cardiovascular Disease Analysis

Area of Science:

• Cardiovascular Disease (CVD) Analysis
• Artificial Intelligence (AI) in Medical Imaging
• Diagnostic Technologies

Background:

• Cardiovascular diseases (CVDs) remain a leading cause of mortality worldwide.
• Traditional CVD analysis methods often rely on subjective interpretation of medical images.
• Emerging AI technologies offer potential for more objective and efficient CVD assessment.

Purpose of the Study:

• To provide a comprehensive review of current Artificial Intelligence (AI) applications in image-based cardiovascular disease (CVD) analysis.
• To systematically categorize AI applications based on anatomical structures (nonvessel and vessel) and imaging modalities.
• To identify challenges and future research directions in AI-driven CVD diagnostics.

Main Methods:

• Systematic literature review of AI applications in cardiovascular imaging.
• Categorization of studies based on anatomical focus: nonvessel structures (ventricles, atria) and vessel structures (aorta, coronary arteries).
• Inclusion of various imaging modalities such as computed tomography (CT) and magnetic resonance imaging (MRI).

Main Results:

• AI demonstrates significant influence in image-based cardiovascular disease (CVD) analysis.
• Diverse AI applications identified across different anatomical structures and imaging techniques.
• Review highlights the integration of AI with modalities like CT and MRI for enhanced CVD insights.

Conclusions:

• AI holds substantial promise for advancing cardiovascular disease (CVD) diagnostics through medical image analysis.
• Current AI methods face challenges including data variability and interpretability.
• Future research should focus on addressing limitations to fully realize AI's potential in CVD care.