Back to Search
Start Over
Self-supervised multicontrast super-resolution for diffusion-weighted prostate MRI.
- Source :
-
Magnetic resonance in medicine [Magn Reson Med] 2024 Jul; Vol. 92 (1), pp. 319-331. Date of Electronic Publication: 2024 Feb 02. - Publication Year :
- 2024
-
Abstract
- Purpose: This study addresses the challenge of low resolution and signal-to-noise ratio (SNR) in diffusion-weighted images (DWI), which are pivotal for cancer detection. Traditional methods increase SNR at high b-values through multiple acquisitions, but this results in diminished image resolution due to motion-induced variations. Our research aims to enhance spatial resolution by exploiting the global structure within multicontrast DWI scans and millimetric motion between acquisitions.<br />Methods: We introduce a novel approach employing a "Perturbation Network" to learn subvoxel-size motions between scans, trained jointly with an implicit neural representation (INR) network. INR encodes the DWI as a continuous volumetric function, treating voxel intensities of low-resolution acquisitions as discrete samples. By evaluating this function with a finer grid, our model predicts higher-resolution signal intensities for intermediate voxel locations. The Perturbation Network's motion-correction efficacy was validated through experiments on biological phantoms and in vivo prostate scans.<br />Results: Quantitative analyses revealed significantly higher structural similarity measures of super-resolution images to ground truth high-resolution images compared to high-order interpolation (p < $$ < $$ 0.005). In blind qualitative experiments, 96 . 1 % $$ 96.1\% $$ of super-resolution images were assessed to have superior diagnostic quality compared to interpolated images.<br />Conclusion: High-resolution details in DWI can be obtained without the need for high-resolution training data. One notable advantage of the proposed method is that it does not require a super-resolution training set. This is important in clinical practice because the proposed method can easily be adapted to images with different scanner settings or body parts, whereas the supervised methods do not offer such an option.<br /> (© 2024 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.)
- Subjects :
- Humans
Male
Image Processing, Computer-Assisted methods
Image Interpretation, Computer-Assisted methods
Neural Networks, Computer
Motion
Reproducibility of Results
Diffusion Magnetic Resonance Imaging methods
Prostatic Neoplasms diagnostic imaging
Phantoms, Imaging
Signal-To-Noise Ratio
Prostate diagnostic imaging
Algorithms
Subjects
Details
- Language :
- English
- ISSN :
- 1522-2594
- Volume :
- 92
- Issue :
- 1
- Database :
- MEDLINE
- Journal :
- Magnetic resonance in medicine
- Publication Type :
- Academic Journal
- Accession number :
- 38308149
- Full Text :
- https://doi.org/10.1002/mrm.30047