An efficient multilevel thresholding segmentation method for thermography breast cancer imaging based on improved chimp optimization algorithm

摘要

Thermography images are a helpful screening tool that can detect breast cancer by showing the body parts that indicate an abnormal change in temperature. Various segmentation methods are proposed to extract regions of interest from breast cancer images to enhance the classification. Many issues were solved using thresholding. In this paper, a new efficient version of the recent chimp optimization algorithm (ChOA), namely opposition based Levy Flight chimp optimizer (IChOA), was proposed. The original ChOA algorithm can stagnate in local optima and needs varied exploration with an adequate blending of exploitation. Therefore, the convergence is accelerated by improving the initial diversity and good exploitation capability at a later stage of generations. Opposition-based learning (OBL) is applied at the initialization phase of ChOA to boost its population diversity in the search space, and the Levy Flight is used to enhance its exploitation. Moreover, the IChOA is applied to tackle the image segmentation problem using multilevel thresholding. The proposed method tested using Otsu and Kapur methods over a dataset from Mastology Research with Infrared Image (DMR-IR) database during the optimization process. Furthermore, compared against seven other meta-heuristic algorithms, namely Gray wolf optimization (GWO), Moth flame optimization (MFO), Whale optimization algorithm (WOA), Sine-cosine algorithm (SCA), Slap swarm algorithm (SSA), Equilibrium optimization (EO), and original Chimp optimization algorithm (ChOA). Results based on the fitness values of obtained best solutions revealed that the IChOA achieved valuable and accurate results in terms of quality, consistency, accuracy, and the evaluation matrices such as PSNR, SSIM, and FSIM. Eventually, IChOA obtained robustness for the segmentation of various positive and negative cases compared to the methods of its counterparts.