Journal article
Directionality guided non linear diffusion compressed sensing MR image reconstruction
Magnetic resonance in medicine, Vol.82(6), pp.2326-2342
12/2019
DOI: 10.1002/mrm.27895
PMID: 31364204
Abstract
Purpose
Address the shortcomings of edge‐preserving filters to preserve the complex nature of edges, by adapting the direction of diffusion to the local variations in intensity function on a subpixel level, thereby achieving a reconstruction accuracy superior to that of data‐driven learning‐based approaches.
Theory and Methods
Rate of diffusion for edges is found to vary in accordance with their gradient direction. Therefore, the edge preservation is strongly dependent on the direction in which the gradient is computed. Since the directionality of edges varies at different regions of the image, the proposed technique computes the gradients in all possible angular directions and uses a spatial‐frequency‐based deviation measure to choose the most reliable edges from the images diffused along different directions.
Results
The proposed method is compared with the state‐of‐the‐art data‐driven learning‐based techniques of block matching and 3D filtering (BM3D), patch‐based nonlocal operator (PANO), and dictionary learning MRI (DLMRI). Best results are obtained when directionality of edges is estimated from a prior optimized k‐space and shows an improvement in peak signal‐to‐noise ratio (PSNR) measures by a factor of 2.36 dB, 1.92 dB, and 1.59 dB over BM3D, PANO, and dictionary learning MRI, respectively.
Conclusion
The proposed technique prevents the emphasis of false edges and better captures the structural details by a locally varying directionality‐guided diffusion to make the error lower than that of the state‐of‐the‐art reconstruction techniques. In addition, a highly parallelizable form of the proposed model promises a significant gain in the reconstruction speed for practical implementations.
Details
- Title: Subtitle
- Directionality guided non linear diffusion compressed sensing MR image reconstruction
- Creators
- Ajin Joy - Indian Institute of Information Technology and Management‐KeralaMathews Jacob - University of IowaJoseph Suresh Paul - Indian Institute of Information Technology and Management‐Kerala
- Resource Type
- Journal article
- Publication Details
- Magnetic resonance in medicine, Vol.82(6), pp.2326-2342
- DOI
- 10.1002/mrm.27895
- PMID
- 31364204
- ISSN
- 0740-3194
- eISSN
- 1522-2594
- Number of pages
- 17
- Language
- English
- Date published
- 12/2019
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Iowa Neuroscience Institute; Radiation Oncology
- Record Identifier
- 9984070447902771
Metrics
10 Record Views