Stenosis Detection and Quantification of Coronary Artery Using Machine Learning and Deep Learning

Area of Science:

• Cardiology
• Radiology
• Artificial Intelligence

Background:

• Coronary artery disease is a leading cause of mortality worldwide.
• Accurate detection and quantification of coronary stenosis are crucial for patient management.
• Computed tomography angiography (CTA) is a key imaging modality for assessing coronary arteries.

Purpose of the Study:

• To review the applications of artificial intelligence (AI) algorithms for detecting and quantifying coronary stenosis using CTA.
• To summarize recent advancements and discuss future trends in AI-driven coronary stenosis analysis.
• To provide a comparative overview of different AI methods for researchers.

Main Methods:

• Review of current literature on AI applications in coronary stenosis detection and quantification.
• Focus on machine learning and deep learning techniques.
• Analysis of the steps involved: vessel central axis extraction, segmentation, stenosis detection, and quantification.

Main Results:

• AI, particularly machine learning and deep learning, shows significant promise for automating coronary stenosis detection and quantification.
• These AI techniques are increasingly utilized in medical image segmentation and stenosis detection.
• The review highlights the progress and comparative advantages/disadvantages of various AI methods.

Conclusions:

• AI algorithms are poised to enhance the automation of coronary artery stenosis detection and quantification.
• A major challenge for current AI methods is the requirement for extensive, expertly annotated datasets.
• Further research is needed to overcome data annotation limitations and optimize AI technologies in this field.