MRI-based Images Segmentation for GPU Accelerated Fuzzy Methods on Graphics Processing Units by CUDA
Author : Wei-Hung Cheng
Publisher :
ISBN 13 :
Total Pages : 92 pages
Book Rating : 4.:/5 (11 download)
Book Synopsis MRI-based Images Segmentation for GPU Accelerated Fuzzy Methods on Graphics Processing Units by CUDA by : Wei-Hung Cheng
Download or read book MRI-based Images Segmentation for GPU Accelerated Fuzzy Methods on Graphics Processing Units by CUDA written by Wei-Hung Cheng and published by . This book was released on 2018 with total page 92 pages. Available in PDF, EPUB and Kindle. Book excerpt: Medical Image Processing (MIP) have been developing rapidly over the past decades significantly due to the direct impact on the diagnosis and the treatment of many diseases. The research of medical image analysis methodologies for image acquisition equipment include image segmentation, image registration, motion tracking and change detection from image sequences, and the measurement of anatomical and physiological parameters from images. Image segmentation is a mandatory step in many image processing-based diagnosis procedures. Many segmentation algorithms use clustering approach. This research focus on Fuzzy C-Means based segmentation algorithms because it provide the accuracy. In many cases, these algorithms need long execution times especially on 3D models. We present a parallel implementation of the proposed algorithm using Graphics Processing Unit (GPU) by CUDA. The processing time of both the sequential and the parallel implementations are measured to show the efficiency of each implementation. We achieve performance increase by up to 9x without effect on the segmentation accuracy. As future work, the most important challenge in the field of medical image segmentation is 3D volume segmentation. Even though on this research shown some initial improvement for 3D volume segmentation, it still has some space for improvement. We can expand this research to considering the other steps in the segmentation process of medical images such as region growing, features selection and classification with GPU by CUDA programming.