A Fast Global Minimization of Region-Scalable Fitting Model for Medical Image Segmentation

Abstract

Active contour model (ACM) which has been extensively studied recently is one of the most successful methods in image segmentation. The present paper advances an improved hybrid model based on Region-Scalable Fitting Model by combining global convex segmentation method with edge detector operator. The proposed model not only inherits the ability of RSF model to deal with the images with intensity inhomogeneity, but also overcomes such a drawback: existence of local minima because of non-convexity that makes the segmentation result highly dependent of the initial position of the contour. In addition, the paper exploits two fast numerical implementation schemes to overcome a huge amount of level set methods. The duality projection method is implemented by introducing dual variables which lead to semi-implicit iterative scheme of dual variables as well as exact formulation of primal variables. The Split-Bregman method is implemented by introducing auxiliary variables which transform the relaxed convex model into solving simple poisson equations and exact soft thresholding formulation. Experimental results for synthetic and real medical images prove that the proposed model is featured by greater numerical accuracy and faster division speed.

Modified distance regularized level set evolution for brain ventricles segmentation

“…A fitting energy is obtained from the region of interest in the image based on pixel intensities [33]. This fitting energy is divided into two functions: one defines the intensity information inside the boundary and the other approximates the region outside the boundary [34][35][36]. Due to space constraint only, the relevant equations are given here as it will be a repetition of what is already present in ref.…”

“…RSF-based segmentation works well in case of weak boundaries as it accounts for regional (pixel wise information in a particular region) intensity information but suffers from re-initialization [34][35][36]. RSF does not account for any edge information; sometimes it fails to converge and suffers from re-initialization.…”