Fast Brain MRI Reconstruction Using Deep Iterative Convolutional Neural Network
Human brain MRI is usually multi-slice, and there is data redundancy between adjacent slices. Deep learning has become a powerful tool in the field of undersampled MRI reconstruction. However, the current reconstruction algorithms based on deep learning are mainly for a single MRI image. In order to...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2020-12-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/CN/abstract/abstract2495.shtml |
| _version_ | 1818425929374892032 |
|---|---|
| author | DU Nianmao, SONG Wei |
| author_facet | DU Nianmao, SONG Wei |
| author_sort | DU Nianmao, SONG Wei |
| collection | DOAJ |
| description | Human brain MRI is usually multi-slice, and there is data redundancy between adjacent slices. Deep learning has become a powerful tool in the field of undersampled MRI reconstruction. However, the current reconstruction algorithms based on deep learning are mainly for a single MRI image. In order to make full use of the data redun-dancy in brain MRI data and obtain higher reconstruction quality and acceleration factor, a deep iterative convolu-tional neural network (DICNN) is proposed. In each iteration, a bi-directional convolution module (BDC) is used to explore the data redundancy between adjacent slices, and then a 2D convolution module (refine net, RNET) is used to further explore the data redundancy within a single MRI slice. Simulation experiments on a single-coil brain MRI dataset show that the proposed algorithm is better than the algorithm based on a single MRI image under different undersampling factors. This method can not only effectively make use of the data redundancy between brain MRI slices and recover more tissue structure details, but also meet real-time MRI reconstruction at a speed of 49 slices per second. |
| first_indexed | 2024-12-14T14:21:45Z |
| format | Article |
| id | doaj.art-58c4a5144f654bc6b1b30651d609d3fb |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-12-14T14:21:45Z |
| publishDate | 2020-12-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-58c4a5144f654bc6b1b30651d609d3fb2022-12-21T22:58:03ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182020-12-0114122150216010.3778/j.issn.1673-9418.2004071Fast Brain MRI Reconstruction Using Deep Iterative Convolutional Neural NetworkDU Nianmao, SONG Wei0School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, ChinaHuman brain MRI is usually multi-slice, and there is data redundancy between adjacent slices. Deep learning has become a powerful tool in the field of undersampled MRI reconstruction. However, the current reconstruction algorithms based on deep learning are mainly for a single MRI image. In order to make full use of the data redun-dancy in brain MRI data and obtain higher reconstruction quality and acceleration factor, a deep iterative convolu-tional neural network (DICNN) is proposed. In each iteration, a bi-directional convolution module (BDC) is used to explore the data redundancy between adjacent slices, and then a 2D convolution module (refine net, RNET) is used to further explore the data redundancy within a single MRI slice. Simulation experiments on a single-coil brain MRI dataset show that the proposed algorithm is better than the algorithm based on a single MRI image under different undersampling factors. This method can not only effectively make use of the data redundancy between brain MRI slices and recover more tissue structure details, but also meet real-time MRI reconstruction at a speed of 49 slices per second.http://fcst.ceaj.org/CN/abstract/abstract2495.shtmlbrain magnetic resonance imaging (mri)deep learningimage reconstructionconvolutional neural network (cnn) |
| spellingShingle | DU Nianmao, SONG Wei Fast Brain MRI Reconstruction Using Deep Iterative Convolutional Neural Network Jisuanji kexue yu tansuo brain magnetic resonance imaging (mri) deep learning image reconstruction convolutional neural network (cnn) |
| title | Fast Brain MRI Reconstruction Using Deep Iterative Convolutional Neural Network |
| title_full | Fast Brain MRI Reconstruction Using Deep Iterative Convolutional Neural Network |
| title_fullStr | Fast Brain MRI Reconstruction Using Deep Iterative Convolutional Neural Network |
| title_full_unstemmed | Fast Brain MRI Reconstruction Using Deep Iterative Convolutional Neural Network |
| title_short | Fast Brain MRI Reconstruction Using Deep Iterative Convolutional Neural Network |
| title_sort | fast brain mri reconstruction using deep iterative convolutional neural network |
| topic | brain magnetic resonance imaging (mri) deep learning image reconstruction convolutional neural network (cnn) |
| url | http://fcst.ceaj.org/CN/abstract/abstract2495.shtml |
| work_keys_str_mv | AT dunianmaosongwei fastbrainmrireconstructionusingdeepiterativeconvolutionalneuralnetwork |