Exploiting spatio-temporal redundancies in sub-Nyquist sampled dynamic MRI for the suppression of undersampling artifacts was shown to be of great success. However, temporally averaged and blurred structures in image space composite data poses the risk of false information in the reconstruction. Within this work we assess the possibility of employing the composite image histogram as a measure of undersampling artifacts and as basis of their suppression. The proposed algorithm utilizes a histogram, computed from a composite image within a dynamically acquired interleaved radial MRI measurement as reference to compensate for the impact of undersampling in temporally resolved data without the incorporation of temporal averaging. In addition an image space regularization utilizing a single frame low-resolution reconstruction is implemented to enforce overall contrast fidelity. The performance of the approach was evaluated on a simulated radial dynamic MRI acquisition and on two functional in vivo radial cardiac acquisitions. Results demonstrate that the algorithm maintained contrast properties, details and temporal resolution in the images, while effectively suppressing undersampling artifacts.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jmr.2013.12.011 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
ROBUST OUTER VOLUME SUBTRACTION WITH DEEP LEARNING GHOSTING DETECTION FOR HIGHLY-ACCELERATED REAL-TIME DYNAMIC MRI.
Proc IEEE Int Symp Biomed Imaging
May 2024
Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA.
Real-time dynamic MRI is important for visualizing time-varying processes in several applications, including cardiac imaging, where it enables free-breathing images of the beating heart without ECG gating. However, current real-time MRI techniques commonly face challenges in achieving the required spatio-temporal resolutions due to limited acceleration rates. In this study, we propose a deep learning (DL) technique for improving the estimation of stationary outer-volume signal from shifted time-interleaved undersampling patterns.
View Article and Find Full Text PDFCYCLE-CONSISTENT SELF-SUPERVISED LEARNING FOR IMPROVED HIGHLY-ACCELERATED MRI RECONSTRUCTION.
Proc IEEE Int Symp Biomed Imaging
May 2024
Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States.
Physics-driven deep learning (PD-DL) has become a powerful tool for accelerated MRI. Recent developments have also developed unsupervised learning for PD-DL, including self-supervised learning. However, at very high acceleration rates, such approaches show performance deterioration.
View Article and Find Full Text PDFCardiac MR image reconstruction using cascaded hybrid dual domain deep learning framework.
PLoS One
January 2025
Medical Image Processing Research Group (MIPRG), Dept. of Elect. & Comp. Engineering, COMSATS University Islamabad, Islamabad, Pakistan.
Recovering diagnostic-quality cardiac MR images from highly under-sampled data is a current research focus, particularly in addressing cardiac and respiratory motion. Techniques such as Compressed Sensing (CS) and Parallel Imaging (pMRI) have been proposed to accelerate MRI data acquisition and improve image quality. However, these methods have limitations in high spatial-resolution applications, often resulting in blurring or residual artifacts.
View Article and Find Full Text PDFProspective Evaluation of Accelerated Brain MRI Using Deep Learning-Based Reconstruction: Simultaneous Application to 2D Spin-Echo and 3D Gradient-Echo Sequences.
Korean J Radiol
January 2025
Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea.
Objective: To prospectively evaluate the effect of accelerated deep learning-based reconstruction (Accel-DL) on improving brain magnetic resonance imaging (MRI) quality and reducing scan time compared to that in conventional MRI.
Materials And Methods: This study included 150 participants (51 male; mean age 57.3 ± 16.
Validation of a Deep Learning-Based Method for Accelerating Susceptibility-Weighted Imaging in Clinical Settings.
NMR Biomed
February 2025
Department of Radiology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Susceptibility-weighted imaging (SWI) has been widely used in clinical contexts, in which the speed of acquisition is frequently a critical issue. In this study, we aim to test the feasibility of a deep learning (DL)-based reconstruction method for accelerating SWI acquisition in clinical settings. A total of 61 subjects were consecutively enrolled.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!