TR-GAN: Multi-session future MRI prediction with temporal recurrent generative adversarial network

doi:10.1109/TMI.2022.3151118

CASIA OpenIR > 复杂系统认知与决策实验室 > 先进机器人

TR-GAN: Multi-session future MRI prediction with temporal recurrent generative adversarial network

Fan, Chen-Chen1,2

; Peng, Liang1

; Wang, Tian 5; Yang, Hongjun1

; Zhou, Xiao-Hu1

; Ni, Zhen-Liang1,2

; Wang, Guan’an1,2

; Chen, Sheng1,2

; Zhou, Yan-Jie1,2

; Hou, Zeng-Guang1,2,3,4

发表期刊

IEEE Transactions on Medical Imaging

2022

卷号

vol. 41 期号:no. 8 页码:1925-1937

摘要

Magnetic Resonance Imaging (MRI) has been proven to be an efficient way to diagnose Alzheimer's disease (AD). Recent dramatic progress on deep learning greatly promotes the MRI analysis based on data-driven CNN methods using a large-scale longitudinal MRI dataset. However, most of the existing MRI datasets are fragmented due to unexpected quits of volunteers. To tackle this problem, we propose a novel Temporal Recurrent Generative Adversarial Network (TR-GAN) to complete missing sessions of MRI datasets. Unlike existing GAN-based methods, which either fail to generate future sessions or only generate fixed-length sessions, TR-GAN takes all past sessions to recurrently and smoothly generate future ones with variant length. Specifically, TR-GAN adopts recurrent connection to deal with variant input sequence length and flexibly generate future variant sessions. Besides, we also design a multiple scale & location (MSL) module and a SWAP module to encourage the model to better focus on detailed information, which helps to generate high-quality MRI data. Compared with other popular GAN architectures, TR-GAN achieved the best performance in all evaluation metrics of two datasets. After expanding the Whole MRI dataset, the balanced accuracy of AD vs. cognitively normal (CN) vs. mild cognitive impairment (MCI) and stable MCI vs. progressive MCI classification can be increased by 3.61% and 4.00%, respectively.

关键词

Alzheimer’s disease magnetic resonance imaging generative adversarial network

DOI

10.1109/TMI.2022.3151118

收录类别

SCI

语种

英语

七大方向——子方向分类

人工智能+医疗

国重实验室规划方向分类

其他

是否有论文关联数据集需要存交

否

引用统计

被引频次：3[WOS] [WOS记录] [WOS相关记录]

文献类型

期刊论文

条目标识符

http://ir.ia.ac.cn/handle/173211/51864

专题

复杂系统认知与决策实验室_先进机器人

通讯作者

Hou, Zeng-Guang

作者单位

1.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
3.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing 100190, China
4.CASIA-MUST Joint Laboratory of Intelligence Science and Technology, Institute of Systems Engineering, Macau University of Science and Technology, Macau 999078, China
5.Neuroscience and Intelligent Media Institute, Communication University of China, Beijing 100024, China

第一作者单位

中国科学院自动化研究所

通讯作者单位

中国科学院自动化研究所

推荐引用方式
GB/T 7714

Fan, Chen-Chen,Peng, Liang,Wang, Tian,et al. TR-GAN: Multi-session future MRI prediction with temporal recurrent generative adversarial network[J]. IEEE Transactions on Medical Imaging,2022,vol. 41(no. 8):1925-1937.

APA

Fan, Chen-Chen.,Peng, Liang.,Wang, Tian.,Yang, Hongjun.,Zhou, Xiao-Hu.,...&Hou, Zeng-Guang.(2022).TR-GAN: Multi-session future MRI prediction with temporal recurrent generative adversarial network.IEEE Transactions on Medical Imaging,vol. 41(no. 8),1925-1937.

MLA

Fan, Chen-Chen,et al."TR-GAN: Multi-session future MRI prediction with temporal recurrent generative adversarial network".IEEE Transactions on Medical Imaging vol. 41.no. 8(2022):1925-1937.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
TR-GAN_Multi-Session（11092KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载