Particle Swarm Optimization on Follicles Segmentation to Support PCOS Detection

Particle Swarm Optimization on Follicles Segmentation to Support PCOS Detection

Author		: ENI SETIAWATI; ADIWIJAYA; TJOKORDA AGUNG BUDI WIRAYUDA
Published on	: ICoICT 2015

Abstract

“Polycystic Ovary Syndrome (PCOS) is the most common endocrine disorders affected to female in their reproductive cycle. PCO (Polycystic Ovaries) describes ovaries that contain many small cysts/follicles. This paper proposed an image clustering approach for follicles segmentation using Particle Swarm Optimization (PSO) with a new modified nonparametric fitness function. The new modified fitness function use Mean Structural Similarity Index (MSSIM) and Normalized Mean Square Error (NMSE) to produce more Dynamic and convergent cluster. Our proposed fitness function is compared to a non-parametric fitness function proposed by previous research. Experimental results showed that our proposed PSO fitness function produced more convergent solution than previous fitness function. This paper also investigated the influence of contrast enhancement to the performance of PSO image clustering and the extracted follicular size. Our experimental result showed that PSO image clustering which is preceded by contrast enhancement produced larger intracluster distance, intracluster distance and quantization error than PSO image clustering which is not preceded by contrast enhancement. PSO with contrast enhancement produce closer ROI toward to reference ROI which is manually identified by doctor.”