An Optimized Approach for Prostate Image Segmentation Using K-Means Clustering Algorithm with Elbow Method

Prostate cancer disease is one of the common types that cause men's prostate damage all over the world. Prostate-specific membrane antigen (PSM A) expressed by type-II is an extremely attractive style for imaging-based diagnosis of prostate cancer. Clinically, photodynamic therapy (PDT) is used as noninvasive therapy in treatment of several cancers and some other diseases. This paper aims to segment or cluster and analyze pixels of histological and near-infrared (NIR) prostate cancer images acquired by PSM A-targeting PDT low weight molecular agents. Such agents can provide image guidance to resection of the prostate tumors and permit for the subsequent PDT in order to remove remaining or noneradicable cancer cells. The color prostate image segmentation is accomplished using an optimized image segmentation approach. The optimized approach combines the k-means clustering algorithm with elbow method that can give better clustering of pixels through automatically determining the best number of clusters. Clusters' statistics and ratio results of pixels in the segmented images show the applicability of the proposed approach for giving the optimum number of clusters for prostate cancer analysis and diagnosis.

Automated summary

The research aims to segment and cluster pixels of prostate cancer images obtained by PSM A-targeting PDT low weight molecular agents, and provide the optimum number of clusters using an optimized approach that combines the k-means clustering algorithm with elbow method. The proposed method improves clustering of pixels and is suitable for analysis and diagnosis of prostate cancer.