Visible to the public "On segmentation of CS reconstructed MR images"Conflict Detection Enabled

Title"On segmentation of CS reconstructed MR images"
Publication TypeConference Paper
Year of Publication2015
AuthorsA. Roy, S. P. Maity
Conference Name2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR)
Date PublishedJan
PublisherIEEE
ISBN Number978-1-4799-7458-0
Accession Number14949074
Keywordsadaptive filters, adaptive recursive filtering, approximate subband suppression, biomedical MRI, compressed sensing, compressive sampling, CS reconstructed MR image segmentation, curvelet transform, curvelet transforms, edge detection, edge enhancement, Entropy, GA-based clustering, genetic algorithms, hard thresholding, image denoising, Image edge detection, image enhancement, Image reconstruction, image segmentation, low-measurement space, magnetic resonance image reconstruction, medical image processing, MR Images, Noise, noise reduction, noise removal, pattern clustering, performance improvement, pubcrawl170104, random noise injection, Segmentation, sharpen MR image segmentation, spatial domain denoising, Transforms, unobserved space, weighted entropy values, weighted linear prediction, weighted variance values
Abstract

This paper addresses the issue of magnetic resonance (MR) Image reconstruction at compressive sampling (or compressed sensing) paradigm followed by its segmentation. To improve image reconstruction problem at low measurement space, weighted linear prediction and random noise injection at unobserved space are done first, followed by spatial domain de-noising through adaptive recursive filtering. Reconstructed image, however, suffers from imprecise and/or missing edges, boundaries, lines, curvatures etc. and residual noise. Curvelet transform is purposely used for removal of noise and edge enhancement through hard thresholding and suppression of approximate sub-bands, respectively. Finally Genetic algorithms (GAs) based clustering is done for segmentation of sharpen MR Image using weighted contribution of variance and entropy values. Extensive simulation results are shown to highlight performance improvement of both image reconstruction and segmentation problems.

URLhttp://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7050695&isnumber=7050639
DOI10.1109/ICAPR.2015.7050695
Citation Key7050695