Kernel density estimation applications in vessel extraction for MRA images

Vascular-related diseases have become increasingly significant as public health concerns. The analysis of blood vessels plays an important role in detecting and treating diseases. Extraction of vessels is a very important technique in vascular analysis. Magnetic Resonance Angiography (MRA) is a medical imaging technique used to visualize the blood vessels and vascular system in three-dimensional images. These images provide detailed information about the size and shape of the vessels, any narrowing or stenosis, as well as blood supply and circulation in the body. Tracing vessels from medical images is an essential step in the diagnosis and treatment of vascular-related diseases. Many different techniques and algorithms have been proposed for vessel extraction. In this paper, we present a vessel extraction method based on the Kernel density estimation (KDE). Numerical experiments on real ۲D MRA images demonstrate that the presented method is very efficient. The effectiveness of the proposed method has been proven through comparative analysis with validated existing methods.

کلیدواژه ها:

vessel extraction ، Kernel density estimation ، MRA images ، bandwidth selection