ScPSO-Based Multithresholding Modalities for Suspicious Region Detection on Mammograms

Abstract Multithresholding techniques typically use histogram information for finding the optimal thresholds on image enhancement, segmentation, etc. In optimization-based modalities, a robust optimization algorithm is needed to realize an effective multithresholding. At this point, the robustness of an optimization algorithm is revealed by the obtained output of cost function (objective values) to be maximized or minimized. In this chapter, we handle the design of novel and stochastic multithresholding modalities that are proposed by an effective optimization algorithm named Scout Particle Swarm Optimization (ScPSO). For the aim of best gray-level distribution (optimum multithresholding), Otsu and Kapur functions are preferred in optimization algorithm owing to their popularity and efficiency. In experiments, Otsu-ScPSO and Kapur-ScPSO are compared together beside the comparison of four optimization algorithms (Particle Swarm Optimization, Genetic Algorithm, Bacterial Foraging Algorithm, and Modified Bacterial Foraging Algorithm), which previously proved themselves in segmentation of well-known benchmark images. According to results, it's seen that ScPSO-based modalities achieve better objective values and standard deviations than other optimization algorithms. In terms of being the best optimization-based approaches, Otsu-ScPSO and Kapur-ScPSO are compared by using computation time, standard deviation, PSNR, and SSIM metrics. For a real-time application, Otsu-ScPSO and Kapur-ScPSO are compared for the purpose of suspicious region detection (mass segmentation) on 15 mammogram images taken from mini-MIAS database. Consequently, it's revealed that the segmentation of breast masses and the multithresholding of benchmark images are better performed using the optimum thresholds found by Kapur-ScPSO.