Boundary Detection in Medical Images Using Edge Following Algorithm
P. Thamarai · 2013
This paper introduces a new edge following technique for boundary detection in noisy images. Utilizati on of the proposed technique is exhibited via its appl ication to various types of medical images. Our pro posed technique can detect the boundaries of objects in n oisy images using the information from the intensit y gradient via the vector image model and the texture gradient via the edge map. The performance and robustness of the technique have been tested to segment objects in synthetic no isy images and medical images including prostates i n ultrasound images, left ventricles in cardiac magnetic resonan ce (MR) images, aortas in cardiovascular MR images, and knee joints in computerized tomography images. We compare the proposed segmentation technique with the acti ve contour models (ACM), geodesic active contourmodels, active contours without edges, gradient vector fl ow snake models, and ACMs based on vector field convolution, by using the skilled doctors’ opinions as the grou nd truths. The results show that our technique performs very w ell and yields better performance than the classica l contour models. The proposed method is robust and applicable on various kinds of noisy images without prior kn owledge of noise properties.