Edge-enhanced dual discriminator generative adversarial network for fast MRI with parallel imaging using multi-view information

Huang, Jiahao; Ding, Weiping; Lv, Jun; Yang, Jingwen; Dong, Hao; Del Ser, Javier; Xia, Jun; Ren, Tiaojuan; Wong, Stephen T.; Yang, Guang

Edge-enhanced dual discriminator generative adversarial network for fast MRI with parallel imaging using multi-view information

Files

Huang2022_Article_Edge-enhancedDualDiscriminator.pdf (6.57 MB)

Identifiers

ISSN: 0924-669X

DOI: 10.1007/s10489-021-03092-w

Publication date

2022-01-28

Authors

Citations

Export

Abstract

In clinical medicine, magnetic resonance imaging (MRI) is one of the most important tools for diagnosis, triage, prognosis, and treatment planning. However, MRI suffers from an inherent slow data acquisition process because data is collected sequentially in k-space. In recent years, most MRI reconstruction methods proposed in the literature focus on holistic image reconstruction rather than enhancing the edge information. This work steps aside this general trend by elaborating on the enhancement of edge information. Specifically, we introduce a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction by incorporating multi-view information. The dual discriminator design aims to improve the edge information in MRI reconstruction. One discriminator is used for holistic image reconstruction, whereas the other one is responsible for enhancing edge information. An improved U-Net with local and global residual learning is proposed for the generator. Frequency channel attention blocks (FCA Blocks) are embedded in the generator for incorporating attention mechanisms. Content loss is introduced to train the generator for better reconstruction quality. We performed comprehensive experiments on Calgary-Campinas public brain MR dataset and compared our method with state-of-the-art MRI reconstruction methods. Ablation studies of residual learning were conducted on the MICCAI13 dataset to validate the proposed modules. Results show that our PIDD-GAN provides high-quality reconstructed MR images, with well-preserved edge information. The time of single-image reconstruction is below 5ms, which meets the demand of faster processing.

Description

This work was supported in part by the Zhejiang Shuren University Basic Scientifc Research Special Funds, _x000D_ in part by the European Research Council Innovative Medicines Initiative (DRAGON, H2020-JTI-IMI2 101005122),_x000D_ in part by the AI for Health Imaging Award (CHAIMELEON, H2020-SC1-FA-DTS-2019-1 952172), _x000D_ in part by the UK Research and Innovation Future Leaders Fellowship (MR/V023799/1), in part by the British Heart Foundation (Project Number: TG/18/5/34111, PG/16/78/32402), _x000D_ in part by the Foundation of Peking University School and Hospital of Stomatology [KUSSNT-19B11], _x000D_ in part by the Peking University Health Science Center Youth Science and Technology Innovation Cultivation Fund _x000D_ [BMU2021PYB017], _x000D_ in part by the National Natural Science Foundation of China [61976120],_x000D_ in part by the Natural Science Foundation of Jiangsu Province [BK20191445], _x000D_ in part by the Qing Lan Project of Jiangsu Province, in part by National Natural Science Foundation of China [61902338], in part by the Project of Shenzhen International Cooperation Foundation [GJHZ20180926165402083], _x000D_ in part by the Basque Government through the ELKARTEK funding program [KK-2020/00049], _x000D_ and in part by the consolidated research group MATHMODE [IT1294-19].

Keywords

Type

journal article

Citation

Huang , J , Ding , W , Lv , J , Yang , J , Dong , H , Del Ser , J , Xia , J , Ren , T , Wong , S T & Yang , G 2022 , ' Edge-enhanced dual discriminator generative adversarial network for fast MRI with parallel imaging using multi-view information ' , Applied Intelligence , vol. unknown , no. 13 , pp. 14693-14710 . https://doi.org/10.1007/s10489-021-03092-w

Full item page