Towards cardiovascular risk stratification using imaging data

Area of Science:

• Cardiovascular Imaging and Computational Analysis
• Medical Informatics and Disease Prediction

Background:

• Despite advances in cardiovascular imaging, predicting heart attacks remains a challenge.
• Early detection of asymptomatic cardiovascular disease is crucial for reducing mortality.
• Novel computational approaches are needed to extract quantitative data from medical images.

Purpose of the Study:

• To develop a computational framework for analyzing cardiac imaging data.
• To extract quantitative parameters for a new cardiovascular risk assessment method.
• To enable early detection and diagnosis of asymptomatic cardiovascular disease.

Main Methods:

• Development of computational methods for coronary calcification detection.
• Segmentation of the thoracic aorta using non-contrast cardiac computed tomography.
• Detection of neovessels in plaques using intravascular ultrasound imaging.

Main Results:

• Progress in developing computational tools for cardiac imaging analysis.
• Methods for detecting coronary calcification and thoracic aorta segmentation demonstrated.
• Capability for detecting neovessels in plaques established.

Conclusions:

• The developed computational framework shows promise for quantitative analysis of cardiac imaging data.
• This approach can contribute to a new risk assessment method for cardiovascular disease.
• Further development is expected to improve early detection and prediction of heart attacks.