A level‐set method for inhomogeneous image segmentation with application to breast thermography images

Abstract

Various level‐set methods have been suggested for segmenting images with intensity inhomogeneity as local region‐based models. The challenge in these methods is segmenting the inhomogeneous images with smooth edges. These methods cannot properly segment regions with smooth edges in inhomogeneous images. This paper presents a new local region‐based active contour model called local self‐weighted active contour model. In the proposed method, a novel different weighting technique is applied. In this model, the weight of each neighbour pixel in the energy function is set by a function of its intensity and not its geometrical distance regarding the central pixel as previous methods. Considering this, the presented approach can segment regions with smooth edges in the presence of inhomogeneity as breast thermography images. The experimental results of applying the model on heterogeneous images containing synthetic images and medical images, especially breast thermography images, are compared with well‐known local level‐set methods which show the perfect capability of the model. The segmentation results were evaluated using the F‐score, accuracy, precision and recall criteria. The results show values of 0.8, 0.62, 0.73 and 0.82 for the average accuracy, F‐score, precision and recall criteria on the segmentation of breast thermography images, respectively.

Research on improved level set image segmentation method

“…The level set approach in the driven evolution of the partial differential equation can thus be obtained as a formula for the process of re-initializing the level set function, as shown in Eq (10) for the solution of the partial differential equation:…”

“…In Eq (10), which ϕ 0 is the level set function that needs to be initialized again, sign(ϕ 0 ) is the symbolic function, and ϕ is the level set function after the initialization is ϕ 0 completed. Both the period of the re-initialized level set function and the choice of step size will affect the initialization of the level set function during the iteration to some extent [24].…”

“…Shamsi Koshki Asma et al proposed a new local region based active contour model, the local self-weighted active contour model. The experimental results of applying the model to include synthetic and medical images, especially breast thermography images, were compared with the well-known local level set approach and demonstrated the perfect ability of the model [ 10 ]. Weng Guirong et al proposed an additive bias correction (ABC) model based on intensity non-uniformity, which converts the local clustering criterion into an energy function based on the level set model by introducing a level set function [ 11 ].…”