Automatic detection of calcified coronary plaques in computed tomography data sets

Area of Science:

• Cardiovascular Imaging
• Medical Image Analysis
• Radiology

Background:

• Accurate detection of calcified plaques in coronary arteries is crucial for assessing coronary heart disease.
• Manual segmentation of these plaques suffers from significant observer variability, impacting diagnostic reliability.

Purpose of the Study:

• To develop and validate a novel framework for the automatic detection of calcified coronary plaques using Computed Tomography (CT) images.
• To enhance plaque detection and assessment by integrating both native and angio CT datasets, surpassing current state-of-the-art methods.

Main Methods:

• A new framework was designed for automatic segmentation and detection of calcified coronary plaques.
• The framework utilizes both native and angio CT datasets to provide comprehensive plaque information.
• The system was evaluated on a cohort of 127 patients.

Main Results:

• The automated framework demonstrated high detection rates for calcified coronary plaques.
• Specifically, 85.5% of calcified plaques and 96% of obstructive plaques were accurately detected.
• The integration of dual datasets improved the detection and assessment capabilities.

Conclusions:

• The proposed framework offers a reliable and automated solution for detecting calcified coronary plaques in CT images.
• This automated approach significantly reduces observer variability associated with manual segmentation.
• The method shows promise for improving the diagnosis and management of coronary heart disease.