Breast Cancer Image Segmentation Using K-Means Clustering Based on GPU Cuda Parallel Computing

Abstract

Utilization of image processing technology is now widely used in the health of one of them to help radiologist to analyze MRI (Magnetic Resonance Imaging), CT Scan and Mammography. Image segmentation is a process intended to get the objects contained in the image by dividing the image into several areas that have similarity attributes on an object with the aim of facilitating the analysis process. The amount of data available from each patient is increasing and the larger the image size is a new challenge to keep the process accurate but can run fast. Research on the segmentation of medical images have been done but still few that combine with parallel computing. In this research, the implementation of K-Means clustering on the image of mammography result using two way computation that is serial and parallel. The results show that parallel computing gives average performance execution time faster up to twice.

Identifikasi Burr Cell dalam Eritrosit Menggunakan Region Properties pada Citra Mikroskop

“…Jika posisinya tidak berubah maka algoritma berakhir. Namun, jika terjadi perubahan posisi centroid, maka kembali ke proses C dan D. Selanjutnya diulangi hingga semua centroid stabil (posisi tidak berubah) [10].…”