Multi-Layer Basis Pursuit for Compressed Sensing MR Image Reconstruction
Compressive Sensing (CS) is a widely used technique in biomedical signal acquisition and reconstruction. The technique is especially useful for reducing acquisition time for magnetic resonance imaging (MRI) signal acquisitions and reconstruction, where effects of patient fatigue and Claustrophobia n...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9214501/ |
| _version_ | 1818853270995599360 |
|---|---|
| author | Abdul Wahid Jawad Ali Shah Adnan Umar Khan Manzoor Ahmed Hanif Razali |
| author_facet | Abdul Wahid Jawad Ali Shah Adnan Umar Khan Manzoor Ahmed Hanif Razali |
| author_sort | Abdul Wahid |
| collection | DOAJ |
| description | Compressive Sensing (CS) is a widely used technique in biomedical signal acquisition and reconstruction. The technique is especially useful for reducing acquisition time for magnetic resonance imaging (MRI) signal acquisitions and reconstruction, where effects of patient fatigue and Claustrophobia need mitigation. In addition to improving patient experience, faster MRI scans are important for time sensitive imaging, such as functional or cardiac MRI, where target movement is unavoidable. Inspired from recent research works on multi-layer convolutional sparse coding (ML-CSC) theory to model deep neural networks, this work proposes a multi-layer basis pursuit framework which combines the benefit from objective-based CS reconstructions and deep learning-based reconstruction by employing iterative thresholding algorithms for successfully training a CS-MRI restoration framework on GPU and reconstruct test images using parameters of the trained model. Extensive experiments show the effectiveness of the proposed framework on four MRI datasets in terms of faster convergence, improved PSNR/SSIM, and better restoration efficiency as compared to the state of the art frameworks with different CS ratios. |
| first_indexed | 2024-12-19T07:34:09Z |
| format | Article |
| id | doaj.art-0f99a9b6256d4122baa3bc01a9e6bffa |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T07:34:09Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0f99a9b6256d4122baa3bc01a9e6bffa2022-12-21T20:30:36ZengIEEEIEEE Access2169-35362020-01-01818622218623210.1109/ACCESS.2020.30288779214501Multi-Layer Basis Pursuit for Compressed Sensing MR Image ReconstructionAbdul Wahid0https://orcid.org/0000-0003-3922-1591Jawad Ali Shah1https://orcid.org/0000-0002-0339-4370Adnan Umar Khan2Manzoor Ahmed3https://orcid.org/0000-0002-0459-9845Hanif Razali4Department of Electrical Engineering, International Islamic University, Islamabad, PakistanElectronic Section, UniKL British Malaysian Institute, Kuala Lumpur, MalaysiaDepartment of Electrical Engineering, International Islamic University, Islamabad, PakistanCollege of Computer Science and Technology, Qingdao University, Qingdao, ChinaElectronic Section, UniKL British Malaysian Institute, Kuala Lumpur, MalaysiaCompressive Sensing (CS) is a widely used technique in biomedical signal acquisition and reconstruction. The technique is especially useful for reducing acquisition time for magnetic resonance imaging (MRI) signal acquisitions and reconstruction, where effects of patient fatigue and Claustrophobia need mitigation. In addition to improving patient experience, faster MRI scans are important for time sensitive imaging, such as functional or cardiac MRI, where target movement is unavoidable. Inspired from recent research works on multi-layer convolutional sparse coding (ML-CSC) theory to model deep neural networks, this work proposes a multi-layer basis pursuit framework which combines the benefit from objective-based CS reconstructions and deep learning-based reconstruction by employing iterative thresholding algorithms for successfully training a CS-MRI restoration framework on GPU and reconstruct test images using parameters of the trained model. Extensive experiments show the effectiveness of the proposed framework on four MRI datasets in terms of faster convergence, improved PSNR/SSIM, and better restoration efficiency as compared to the state of the art frameworks with different CS ratios.https://ieeexplore.ieee.org/document/9214501/Compressive sensinginverse problems in imagingiterative thresholding algorithmsmulti-layered convolutional sparse coding |
| spellingShingle | Abdul Wahid Jawad Ali Shah Adnan Umar Khan Manzoor Ahmed Hanif Razali Multi-Layer Basis Pursuit for Compressed Sensing MR Image Reconstruction IEEE Access Compressive sensing inverse problems in imaging iterative thresholding algorithms multi-layered convolutional sparse coding |
| title | Multi-Layer Basis Pursuit for Compressed Sensing MR Image Reconstruction |
| title_full | Multi-Layer Basis Pursuit for Compressed Sensing MR Image Reconstruction |
| title_fullStr | Multi-Layer Basis Pursuit for Compressed Sensing MR Image Reconstruction |
| title_full_unstemmed | Multi-Layer Basis Pursuit for Compressed Sensing MR Image Reconstruction |
| title_short | Multi-Layer Basis Pursuit for Compressed Sensing MR Image Reconstruction |
| title_sort | multi layer basis pursuit for compressed sensing mr image reconstruction |
| topic | Compressive sensing inverse problems in imaging iterative thresholding algorithms multi-layered convolutional sparse coding |
| url | https://ieeexplore.ieee.org/document/9214501/ |
| work_keys_str_mv | AT abdulwahid multilayerbasispursuitforcompressedsensingmrimagereconstruction AT jawadalishah multilayerbasispursuitforcompressedsensingmrimagereconstruction AT adnanumarkhan multilayerbasispursuitforcompressedsensingmrimagereconstruction AT manzoorahmed multilayerbasispursuitforcompressedsensingmrimagereconstruction AT hanifrazali multilayerbasispursuitforcompressedsensingmrimagereconstruction |