Particle Swarm Optimization on follicles segmentation to support PCOS detection

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 proposes an image clustering approach for follicles segmentation using Particle Swarm Optimization (PSO) with a new modified non-parametric fitness function. The new modified fitness function use Mean Structural Similarity Index (MSSIM) and Normalized Mean Square Error (NMSE) to produce more compact and convergent cluster. The proposed fitness function is compared to a non-parametric fitness function proposed by previous research. Experimental results show that the proposed PSO fitness function produce more convergent solution than previous fitness function especially on ultrasound images. This paper also investigates the influence of contrast enhancement to the performance of PSO image clustering and the extracted follicular size. The experimental result shows that PSO image clustering which preceded by contrast enhancement produce larger intra-cluster distance, intra-cluster distance and quantization error than PSO image clustering which not preceded by contrast enhancement. PSO with contrast enhancement produce closer Region of Interest (ROI) toward to the reference ROI which manually identified by doctor.