Application of structural group sparsity recovery model for brain MRI

Kathiravan Srinivasan; T. Gowthaman; Anant Nema

doi:10.1117/12.2502987

9 August 2018 Application of structural group sparsity recovery model for brain MRI

Kathiravan Srinivasan, T. Gowthaman, Anant Nema

Proceedings Volume 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018); 108065H (2018) https://doi.org/10.1117/12.2502987
Event: Tenth International Conference on Digital Image Processing (ICDIP 2018), 2018, Shanghai, China

Abstract

This paper focuses on developing a Super-resolution (SR) Magnetic Resonance (MR) image restoration method using Structural Group Sparsity Recovery Model (SGSRM). However, reformation of the original image is critically viewed as an acute problem in image processing, since there is no unique elucidation. In the process of tomography and medical image computing, it is crucial to reconstruct an image for several imaging modalities like X-ray, Computed tomography (CT), Magnetic resonance imaging (MRI), Positron-emission tomography (PET), and Single-photon emission computed tomography (SPECT). The quality of the reformed image from an original one depends mostly on the limitation of the diverse techniques. The principal purpose of this research is to improve the resolution in the restoration process of MR images by using structural group sparsity recovery model. The restoration dependent approach presumes that low-resolution (LR) images are warped, blurred, distorted and decimated from the respective high resolution (HR) images. The HR image is obtained from an array of LR images. In order to simplify the images at subpixel level and the record-keeping parameters among LR images are complicated, so the reformation of the image based on a usual SR procedure gives insufficient scope for enhancing the image resolution under general circumstances. The prevailing idea for image recovery has many different scopes, and the drawbacks can be overcome by using the structural group sparsity recovery model. By using the foreseeable structured portion group under SGSRM, it offers the idea to pick out the group of the portion within a cluster section. The SGSRM technique provides a superior resolution image by overcoming the drawbacks. The paramount impetus of this paper is to devise an SGSRM technique which is robust to noise, while most other SR techniques failed to provide de-noising and super-resolution concurrently with an impressive image resolution.

Citation Download Citation

Kathiravan Srinivasan, T. Gowthaman, and Anant Nema "Application of structural group sparsity recovery model for brain MRI ", Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108065H (9 August 2018); https://doi.org/10.1117/12.2502987

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available