ACGRHA-Net: Accelerated multi-contrast MR imaging with adjacency complementary graph assisted residual hybrid attention network
Multi-contrast magnetic resonance (MR) imaging is an advanced technology used in medical diagnosis, but the long acquisition process can lead to patient discomfort and limit its broader application. Shortening acquisition time by undersampling k-space data introduces noticeable aliasing artifacts. T...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S105381192400418X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846150146054684672 |
|---|---|
| author | Haotian Zhang Qiaoyu Ma Yiran Qiu Zongying Lai |
| author_facet | Haotian Zhang Qiaoyu Ma Yiran Qiu Zongying Lai |
| author_sort | Haotian Zhang |
| collection | DOAJ |
| description | Multi-contrast magnetic resonance (MR) imaging is an advanced technology used in medical diagnosis, but the long acquisition process can lead to patient discomfort and limit its broader application. Shortening acquisition time by undersampling k-space data introduces noticeable aliasing artifacts. To address this, we propose a method that reconstructs multi-contrast MR images from zero-filled data by utilizing a fully-sampled auxiliary contrast MR image as a prior to learn an adjacency complementary graph. This graph is then combined with a residual hybrid attention network, forming the adjacency complementary graph assisted residual hybrid attention network (ACGRHA-Net) for multi-contrast MR image reconstruction. Specifically, the optimal structural similarity is represented by a graph learned from the fully sampled auxiliary image, where the node features and adjacency matrices are designed to precisely capture structural information among different contrast images. This structural similarity enables effective fusion with the target image, improving the detail reconstruction. Additionally, a residual hybrid attention module is designed in parallel with the graph convolution network, allowing it to effectively capture key features and adaptively emphasize these important features in target contrast MR images. This strategy prioritizes crucial information while preserving shallow features, thereby achieving comprehensive feature fusion at deeper levels to enhance multi-contrast MR image reconstruction. Extensive experiments on the different datasets, using various sampling patterns and accelerated factors demonstrate that the proposed method outperforms the current state-of-the-art reconstruction methods. |
| format | Article |
| id | doaj-art-08e5ca96e1054a49972ae93a1b0936f0 |
| institution | Kabale University |
| issn | 1095-9572 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj-art-08e5ca96e1054a49972ae93a1b0936f02024-11-29T06:22:59ZengElsevierNeuroImage1095-95722024-12-01303120921ACGRHA-Net: Accelerated multi-contrast MR imaging with adjacency complementary graph assisted residual hybrid attention networkHaotian Zhang0Qiaoyu Ma1Yiran Qiu2Zongying Lai3School of Ocean Information Engineering, Jimei University, Xiamen, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen, ChinaCorresponding author at: No. 185 Yinjiang Road, Jimei Zone, Xiamen City, Fujian Province, 361021, China; School of Ocean Information Engineering, Jimei University, Xiamen, ChinaMulti-contrast magnetic resonance (MR) imaging is an advanced technology used in medical diagnosis, but the long acquisition process can lead to patient discomfort and limit its broader application. Shortening acquisition time by undersampling k-space data introduces noticeable aliasing artifacts. To address this, we propose a method that reconstructs multi-contrast MR images from zero-filled data by utilizing a fully-sampled auxiliary contrast MR image as a prior to learn an adjacency complementary graph. This graph is then combined with a residual hybrid attention network, forming the adjacency complementary graph assisted residual hybrid attention network (ACGRHA-Net) for multi-contrast MR image reconstruction. Specifically, the optimal structural similarity is represented by a graph learned from the fully sampled auxiliary image, where the node features and adjacency matrices are designed to precisely capture structural information among different contrast images. This structural similarity enables effective fusion with the target image, improving the detail reconstruction. Additionally, a residual hybrid attention module is designed in parallel with the graph convolution network, allowing it to effectively capture key features and adaptively emphasize these important features in target contrast MR images. This strategy prioritizes crucial information while preserving shallow features, thereby achieving comprehensive feature fusion at deeper levels to enhance multi-contrast MR image reconstruction. Extensive experiments on the different datasets, using various sampling patterns and accelerated factors demonstrate that the proposed method outperforms the current state-of-the-art reconstruction methods.http://www.sciencedirect.com/science/article/pii/S105381192400418XAdjacency complementary graphResidual hybrid attentionDeep learningAccelerated multi-contrast MR imaging |
| spellingShingle | Haotian Zhang Qiaoyu Ma Yiran Qiu Zongying Lai ACGRHA-Net: Accelerated multi-contrast MR imaging with adjacency complementary graph assisted residual hybrid attention network NeuroImage Adjacency complementary graph Residual hybrid attention Deep learning Accelerated multi-contrast MR imaging |
| title | ACGRHA-Net: Accelerated multi-contrast MR imaging with adjacency complementary graph assisted residual hybrid attention network |
| title_full | ACGRHA-Net: Accelerated multi-contrast MR imaging with adjacency complementary graph assisted residual hybrid attention network |
| title_fullStr | ACGRHA-Net: Accelerated multi-contrast MR imaging with adjacency complementary graph assisted residual hybrid attention network |
| title_full_unstemmed | ACGRHA-Net: Accelerated multi-contrast MR imaging with adjacency complementary graph assisted residual hybrid attention network |
| title_short | ACGRHA-Net: Accelerated multi-contrast MR imaging with adjacency complementary graph assisted residual hybrid attention network |
| title_sort | acgrha net accelerated multi contrast mr imaging with adjacency complementary graph assisted residual hybrid attention network |
| topic | Adjacency complementary graph Residual hybrid attention Deep learning Accelerated multi-contrast MR imaging |
| url | http://www.sciencedirect.com/science/article/pii/S105381192400418X |
| work_keys_str_mv | AT haotianzhang acgrhanetacceleratedmulticontrastmrimagingwithadjacencycomplementarygraphassistedresidualhybridattentionnetwork AT qiaoyuma acgrhanetacceleratedmulticontrastmrimagingwithadjacencycomplementarygraphassistedresidualhybridattentionnetwork AT yiranqiu acgrhanetacceleratedmulticontrastmrimagingwithadjacencycomplementarygraphassistedresidualhybridattentionnetwork AT zongyinglai acgrhanetacceleratedmulticontrastmrimagingwithadjacencycomplementarygraphassistedresidualhybridattentionnetwork |