Related Experiment Video
Updated: Jul 4, 2025
08:51
Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
Published on: February 19, 2021
9.0K
A Faithful Deep Sensitivity Estimation for Accelerated Magnetic Resonance Imaging
IEEE Journal of Biomedical and Health Informatics
|February 5, 2024
Summary
This study introduces JDSI, a novel deep learning network for faster Magnetic Resonance Imaging (MRI) reconstruction. JDSI jointly estimates coil sensitivity maps and reconstructs images, significantly improving quality and speed, especially at high acceleration factors.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Healthcare
- Deep Learning for Image Reconstruction
Background:
- Magnetic Resonance Imaging (MRI) is crucial for diagnostics but limited by long scan times.
- Deep learning offers potential for accelerating MRI acquisition and enhancing image quality.
- Accurate coil sensitivity estimation is critical for high-fidelity MRI reconstruction, yet often overlooked in deep learning approaches.
Purpose of the Study:
- To develop a deep learning framework that jointly optimizes coil sensitivity estimation and image reconstruction in MRI.
- To address the limitations of relying on pre-estimated, potentially inaccurate sensitivity maps in existing deep learning MRI methods.
- To improve the quality and speed of MRI reconstruction, particularly under high acceleration factors.
Main Methods:
- Introduction of the Joint Deep Sensitivity estimation and Image reconstruction (JDSI) network.
- JDSI iteratively refines sensitivity maps during artifact removal, enhancing image reconstruction fidelity.
- Visualization techniques were employed to demonstrate the synergistic relationship between sensitivity estimation and image reconstruction within the network.
Main Results:
- JDSI achieved state-of-the-art performance in both visual and quantitative assessments on in vivo datasets.
- The network demonstrated superior image reconstruction quality compared to existing methods, especially at high acceleration factors.
- JDSI exhibited robustness across different patients and autocalibration signal qualities.
Conclusions:
- The proposed JDSI network effectively integrates sensitivity estimation and image reconstruction for accelerated MRI.
- Joint optimization leads to more faithful sensitivity maps and significantly improved image reconstruction quality.
- JDSI represents a promising advancement for fast and high-quality MRI, applicable to both calibration-based and calibrationless scenarios.
Related Concept Videos
01:24Magnetic Resonance Imaging
5.2K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.2K
01:14NMR Spectrometers: Resolution and Error Correction
698
When magnetic nuclei in a sample achieve resonance and undergo relaxation, the signal detected in NMR is an approximately exponential free induction decay. Fourier transform of an exponential decay yields a Lorentzian peak in the frequency domain. Lorentzian peaks in an NMR spectrum are defined by their amplitude, full width at half maximum, and position, where the peak width is governed by the spin-spin relaxation time alone. In real experiments, however, the applied magnetic field is rendered...
698