Abstract
Boundary extraction is recently playing a key role in biomedical image analysis. This paper proposes a method for boundary extraction of the common carotid artery using the watershed transform. The main drawback of watershed is over segmentation. This drawback is overcome using wavelets. Two level decompositions with Daubechies wavelet are used. The algorithm is tested with B-mode ultrasound images of the carotid artery. Morphological top hat and bottom hat filters are used to enhance the image and make it suitable for processing. The boundary obtained best fits the vessel wall. Any plaque deposit in the vessel is expected to reduce the diameter of the vessel. The diameter is measured form the boundary extracted. This, therefore, will serve as a step in the prevention of cardiovascular diseases.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call