The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Aggregated Maximum Entropy Variational Analysis Method for Magnetic Resonance Imagery
|
|
Author(s): L. J. Morales-Mendoza (CINVESTAV of the IPN, Mexico), Y. V. Shkvarko (CINVESTAV of the IPN, Mexico), R. F. Vázquez-Bautista (CINVESTAV of the IPN, Mexico)and J. L. Ponce-Dávalos (CINVESTAV of the IPN, Mexico)
Copyright: 2004
Pages: 3
Source title:
Innovations Through Information Technology
Source Editor(s): Mehdi Khosrow-Pour, D.B.A. (Information Resources Management Association, USA)
DOI: 10.4018/978-1-59140-261-9.ch207
ISBN13: 9781616921255
EISBN13: 9781466665347
|
Abstract
There is a variety of computational paradigms for post-processing of biomedical magnetic resonance (MR) images based on the use of the maximum entropy (ME) image reconstruction method. Sometimes the ME-reconstructed image quality is insufficient to clinical analysis because of the degradations of many special features of the image, i.e., edges-stopping, localization of homogeneous zones, signal-to-noise ratios, textures degradation, etcetera. In this work, we propose to modify the conventional ME image reconstruction technique by aggregating it with the variational analysis method and address a new fused maximum-entropy-variational-analysis (MEVA) method for reconstruction and denoising of the MR images. Also, we propose an efficient computational scheme for numerical implementation of the MEVA algorithm using a Hopfield-type modified neural network, and demonstrate performance outcomes of the MEMA-reconstructed MR images.
|
|