Sparse Representation based Super-Resolution of MRI Images with Non-Local Total Variation Regularization
- PDF / 3,168,708 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 97 Downloads / 245 Views
ORIGINAL RESEARCH
Sparse Representation based Super‑Resolution of MRI Images with Non‑Local Total Variation Regularization Bhabesh Deka1 · Helal Uddin Mullah1 · Sumit Datta1,2 · Vijaya Lakshmi1 · Rajarajeswari Ganesan1 Received: 21 March 2020 / Accepted: 24 July 2020 © Springer Nature Singapore Pte Ltd 2020
Abstract Diffusion-weighted (DW) and spectroscopic MR (MRS) images are found to be very helpful for diagnostic purposes as they provide complementary information to that provided by conventional MRI. These images are also acquired at a faster rate, but with low signal-to-noise ratio. This limitation can be overcome by applying image super-resolution techniques. In this paper, we propose sparse representation over a learned overcomplete dictionary based single-image super-resolution (SISR) technique for DW and MRS images. The proposed SISR method incorporates patch-wise sparsity constraint based on external HR information together with the non-local total variation (NLTV) as internal information to make the regularization problem more robust. Experiments are conducted for both DW and MRS test images and results are compared with some of the recent methods. Results indicate the potential of the proposed method for clinical MRI applications. Keywords Super-resolution · NLTV regularization · DW MRI · MRSI · Sparse representation · Dictionary learning
Introduction Diffusion-weighted imaging (DWI) and magnetic resonance spectroscopy imaging (MRSI) are important techniques for brain imaging. DWI is a specific MR imaging method based on mapping of diffusion process of water molecules in tissues [1]. It is an effective technique, which provides functional information of the brain tissues; faster compared to the conventional MRI and does not require any contrast agent. Most of the images are acquired using high speed protocols with a low spatial resolution, reducing the patient stress, but results in the low quality of images [1]. On the other hand, MRSI is another non-invasive technique, which This article is part of the topical collection “Computational Biology and Biomedical Informatics” guest edited by Dhruba Kr Bhattacharyya, Sushmita Mitra and Jugal Kr Kalita. * Bhabesh Deka [email protected] Sumit Datta [email protected] 1
Department of Electronics and Communication Engineering, Tezpur University, Tezpur, Assam 784028, India
Present Address: Department of Electronics and Electrical Engineering, IIT Guwahati, Guwahati, Assam 781039, India
2
gives information about the biochemical components within the tissues [2]. It is particularly of great help in the early diagnosis of brain lesions on the basis of spectra obtained from different metabolite concentrations. It also has the same advantage, i.e. fast scan time as that of DWI. In spite of their advantages, the rise in the cost of scans and poor signal-to-noise ratio limit their clinical use. These limits can be overcome by image super-resolution (SR) [3], which estimates a high-resolution (HR) from one or more available low-resolution (LR) image (s
Data Loading...
