Spatial Fuzzy C-Means PET Image Segmentation of Neurodegenerative Disorder
Journal Title: Indian Journal of Computer Science and Engineering - Year 2013, Vol 4, Issue 1
Abstract
Nuclear image has emerged as a promising research work in medical field. Images from different modality meet its own challenge. Positron Emission Tomography (PET) image may help to precisely localize disease to assist in planning the right treatment for each case and saving valuable time. In this paper, a novel approach of Spatial Fuzzy C-Means (PET-SFCM) clustering algorithm is introduced on PET scan image datasets. The proposed algorithm is incorporated the spatial neighborhood information with traditional FCM and updating the objective function of each cluster. This algorithm is implemented and tested on huge data collection of patients with brain neuro degenerative disorder such as Alzheimer’s disease. It has demonstrated its effectiveness by testing it for real world patient data sets. Experimental results are compared with conventional FCM and K-Means clustering algorithm. The performance of the PET-SFCM provides satisfactory results compared with other two algorithms.
Authors and Affiliations
A. Meena , K. Raja
Keywords
Related Articles
- EP ID EP151277
- DOI -
- Views 108
- Downloads 0
NOVEL SCHEME FOR THE REMOVAL OF BLOTCHES, BLACK BAND NOISE, STREAKS AND IMPULSE NOISE IN GRAY SCALE IMAGES
A Threshold based fixed 3x3 Non linear filter for the removal of image artifact such as blotches, black band noise, streaks and impulse is proposed. The algorithm detects the corrupted pixel, if the absolute difference b...
AN ALGORITHM FOR DIGITAL WATERMARKING OF STILL IMAGES FOR COPYRIGHT PROTECTION
The rapid expansion of the Internet has rapidly increased the availability of digital data such as audio, images and videos to the public and file sharing has become very convenient. As such, the problem of protecting mu...
ANONYMIZATION BASED ON NESTED CLUSTERING FOR PRIVACY PRESERVATION IN DATA MINING
Privacy Preservation in data mining protects the data from revealing unauthorized extraction of information. Data Anonymization techniques implement this by modifying the data, so that the original values cannot be acqui...
A Novel Architecture for Domain Specific Parallel Crawler
The World Wide Web is an interlinked collection of billions of documents formatted using HTML. Due to the growing and dynamic nature of the web, it has become a challenge to traverse all URLs in the web documents and han...
Parallel Implementation of Similarity Measures on GPU Architecture using CUDA
Image processing and pattern recognition algorithms take more time for execution on a single core processor. Graphics Processing Unit (GPU) is more popular now-a-days due to their speed, programmability, low cost and mor...