Bi‐dictionary learning model for medical image reconstruction from undersampled data. Issue 10 (1st July 2020)

• Record Type: Journal Article
• Authors: Mohaoui, Souad; Hakim, Abdelilah; Raghay, Said
• Is Part Of: IET image processing. Volume 14:Issue 10(2020)
• Page Start: 2130
• Page End: 2139
• Publication Date: 2020-07-01
• Subjects: image reconstruction -- medical image processing -- image representation -- gradient methods -- unsupervised learning -- biomedical MRI -- least squares approximations; medical image reconstruction -- undersampled data -- unsupervised learning technique -- magnetic resonance image -- undersampled measurements -- MR images -- bi‐dictionary learning model -- adaptive bi‐dictionary learning model -- least‐squares data fitting -- sparse gradient -- gradient‐based dictionary -- pixel domain; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0886
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : In recent years, dictionary learning has shown to be an efficient tool in recovering images from their degraded, damaged or incomplete version. Especially, for medical images that contain significant details and characteristics. In this work, the authors are interested in this unsupervised learning technique for discovering and visualising the underlying structure of a medical image. Therefore, an adaptive bi‐dictionary learning model for recovering magnetic resonance (MR) image from undersampled measurements is introduced. The proposed model learns two dictionaries, one over the underlying image and the other over its sparse gradient. Hence, the algorithm minimises a linear combination of three terms corresponding to the least‐squares data fitting, dictionary learning over the pixel domain, and gradient‐based dictionary. Numerically, experimental results on several MR images demonstrate that the proposed bi‐dictionary framework can improve reconstruction accuracy over other methods.