Non‐local weighted fuzzy energy‐based active contour model with level set evolution starting with a constant function

Abstract

In the traditional active contour models, global region-based methods fail to segment images with intensity inhomogeneity, and local region-based methods are sensitive to initial contour. In this study, a novel fuzzy energy-based active contour model is proposed to segment medical images, which are always corrupted by intensity inhomogeneity. In order to deal with intensity inhomogeneity, a local energy term is first constructed by substituting a non-local weight for Gaussian kernel widely used in traditional local region-based models. Second, the defined adaptive force can drive the level set function to adaptively increase or decrease according to image intensity information. Therefore, the initial contour can be initialised as a constant function, which eliminates the problem caused by contour initialisation. Moreover, the proposed active contour model is a convex function. Thus, the problem, resulting from optimising a non-convex functional in the traditional active contour models, can be avoided. Experimental results validate the superiorities and effectiveness of the proposed model for image segmentation with comparisons of those yielded by several state-of-the-art techniques.

Robust Active Contour Model Using Patch-Based Signed Pressure Force and Optimized Fractional-Order Edge

“…Based on the SPF proposed in [13], many improved versions [4], [26]- [31], [41], [42] have been proposed by using different strategies. However, they may have low robustness to noise because the spatial information of pixels is not considered.…”

“…Among these methods, the ACM is the most influential one. The basic idea of ACMs is that a predefined energy functional combining various image information is constructed and minimized to obtain the corresponding partial differential equation, which is utilized to drive the evolving curve towards the desired object boundaries [3], [4]. The most desirable advantage of ACMs is that sub-pixel accuracy of the target boundaries and a closed contour can be obtained [2], [5].…”

“…Therefore, this paper focuses mainly on implicit ACMs, namely, ACMs in the level set framework. In these ACMs, the evolving curve is implicitly represented as the zero level set of a high-dimensional function, which is called the level set function (LSF), and then the LSF is deformed according to the evolution equation [3], [4], which is obtained via a variational level set method. Generally, most of the existing ACMs can be classified into two classes: edge-based models [7]- [10] and region-based models [11]- [16].…”

A novel deviation density peaks clustering algorithm and its applications of medical image segmentation

“…Many algorithms that work well in natural image segmentation have problems of under-segmentation and oversegmentation in medical image segmentation, and cannot be well transferred to the medical image segmentation field [9][10][11]. Density peaks clustering (DPC) is a popular clustering algorithm that has been proposed in recent years [12].…”

Fuzzy Active Contour Model Using Fractional-Order Diffusion Based Edge Indicator and Fuzzy Local Fitted Image

“…Similar to CV, these global fuzzy information based ACMs cannot obtain desirable segmentation results, because only global information of image is used to formulate the fuzzy energy functional. To overcome this problem, many fuzzy ACMs [38], [40], [41], [45], [46], [48], [52] make full use of local fuzzy statistics to cope with intensity inhomogeneity. To improve the robustness of model to initial contour, Sun et al [38] fuse an adaptive contrast constraint into the presented model.…”