Saved in:
Bibliographic Details
Main Authors: Yang, Jing, Cheng, Jian, Li, Cheng, Fan, Wenxin, Zou, Juan, Wu, Ruoyou, Wang, Shanshan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.01662
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910286313684992
author Yang, Jing
Cheng, Jian
Li, Cheng
Fan, Wenxin
Zou, Juan
Wu, Ruoyou
Wang, Shanshan
author_facet Yang, Jing
Cheng, Jian
Li, Cheng
Fan, Wenxin
Zou, Juan
Wu, Ruoyou
Wang, Shanshan
contents Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the \textit{in vivo} human brain. However, to effectively capture the intricate characteristics of water diffusion at various directions and scales, it is important to employ comprehensive q-space sampling. Unfortunately, this requirement leads to long scan times, limiting the clinical applicability of dMRI. To address this challenge, we propose SSOR, a Simultaneous q-Space sampling Optimization and Reconstruction framework. We jointly optimize a subset of q-space samples using a continuous representation of spherical harmonic functions and a reconstruction network. Additionally, we integrate the unique properties of diffusion magnetic resonance imaging (dMRI) in both the q-space and image domains by applying $l1$-norm and total-variation regularization. The experiments conducted on HCP data demonstrate that SSOR has promising strengths both quantitatively and qualitatively and exhibits robustness to noise.
format Preprint
id arxiv_https___arxiv_org_abs_2401_01662
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Simultaneous q-Space Sampling Optimization and Reconstruction for Fast and High-fidelity Diffusion Magnetic Resonance Imaging
Yang, Jing
Cheng, Jian
Li, Cheng
Fan, Wenxin
Zou, Juan
Wu, Ruoyou
Wang, Shanshan
Computer Vision and Pattern Recognition
Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the \textit{in vivo} human brain. However, to effectively capture the intricate characteristics of water diffusion at various directions and scales, it is important to employ comprehensive q-space sampling. Unfortunately, this requirement leads to long scan times, limiting the clinical applicability of dMRI. To address this challenge, we propose SSOR, a Simultaneous q-Space sampling Optimization and Reconstruction framework. We jointly optimize a subset of q-space samples using a continuous representation of spherical harmonic functions and a reconstruction network. Additionally, we integrate the unique properties of diffusion magnetic resonance imaging (dMRI) in both the q-space and image domains by applying $l1$-norm and total-variation regularization. The experiments conducted on HCP data demonstrate that SSOR has promising strengths both quantitatively and qualitatively and exhibits robustness to noise.
title Simultaneous q-Space Sampling Optimization and Reconstruction for Fast and High-fidelity Diffusion Magnetic Resonance Imaging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.01662