International Journal of Image Processing Techniques
Author(s) : AHMED BOURIDANE, ALI EL-ZAART, MUHAMMAD ATIF TAHIR, RACHID SAMMOUDA
Prostate cancer is the second most common cancer in men, with 10000 new cases and 2500 deaths every year. These numbers increase every year due to the ageing of the general populace. Computer-aided detection (CAD) of prostate cancer can perhaps provide a solution. Computer algorithms allow us to combine the enormous amount of images into a much smaller amount of images with high information content. Image segmentation is an important step of CAD system, the accuracy of the CAD system is related directly to the accuracy of the image segmentation. Thresholding techniques are the most used technique in image segmentation and the statistical approaches are wieldy used in image thresholding. The Gamma distribution was used for radar images processing and mammograms images processing, the results were promised. Our contribution in this paper is to use the Gamma distribution for PSMA segmentation. In this paper, we will use Gamma distribution in order to approximate the data in PSMA image by a mixture of gamma distributions. In this paper we used the maximum likelihood estimator in order to approximate the histogram by a mixture of Gamma distributions. Thresholds between classes are then estimated by minimizing the discrimination error between the classes of pixels in PSMA image. The experimental results on PSMA prostate images using this technique showed good thresholding of images.