TL-HARDI: Transform learning based accelerated reconstruction of HARDI data. (April 2022)

• Record Type: Journal Article
• Authors: Vaish, Ashutosh; Rajwade, Ajit; Gupta, Anubha
• Is Part Of: Computers in biology and medicine. Volume 143(2022)
• Publication Date: 2022-04
• Subjects: Diffusion MRI -- Diffusion tensor imaging -- HARDI -- Compressed sensing -- Transform learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105212
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Diffusion magnetic resonance imaging (dMRI) is being extensively used to study the neural architecture of the brain. High angular resolution diffusion imaging (HARDI), a variant of diffusion MRI, measures the diffusion of water molecules along the angular gradient directions in the q -space. It provides better estimates of fiber orientations compared to the traditionally used diffusion tensor imaging (DTI). However, HARDI requires acquisition of relatively large number of samples leading to longer scanning times. Several approaches based on compressive sensing (CS) have been proposed to accelerate HARDI acquisition, leveraging on the sparse representation of the HARDI signal in a pre-specified sparsifying basis. In this paper, we propose to carry out reconstruction of compressively sensed HARDI data using an adaptively learned transform. The transform is learned (i) from the compressive measurements on-the-fly, thereby, eliminating the overhead of choosing fixed sparsifying transforms, and (ii) on overlapping patches of the data, thereby, capturing local image structure effectively. Experiments are conducted on multiple real HARDI data for varying sampling ratios and sampling schemes. The performance of the proposed "TL-HARDI " method is compared with the state-of-the-art methods on various known image quality metrics as well as on dMRI feature maps derived from the reconstructed images. The proposed method is observed to yield better reconstruction than the existing state-of-the-art methods in both quantitative and qualitative comparisons. Graphical abstract: Image 1 Highlights: Proposed a novel method of accelerated reconstruction of HARDI data. Transform is learned adaptively on the fly using 2D patches from the compressive measurements. Explored the effectiveness of adaptively learned transform for HARDI reconstruction. HARDI signal along all gradient directions are reconstructed in a joint framework to exploit the correlation. Extensive quantitative and qualitative results are shown on 7 HARDI data.