MMHGE: detecting mild cognitive impairment based on multi-atlas multi-view hybrid graph convolutional networks and ensem
- PDF / 2,223,734 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 81 Downloads / 187 Views
(0123456789().,-volV)(0123456789(). ,- volV)
MMHGE: detecting mild cognitive impairment based on multi-atlas multi-view hybrid graph convolutional networks and ensemble learning Jin Liu1
•
Dejiao Zeng1 • Rui Guo1 • Mingming Lu1 • Fang-Xiang Wu2 • Jianxin Wang1
Received: 9 February 2020 / Revised: 11 September 2020 / Accepted: 23 October 2020 Ó Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Currently, it is still a great challenge in clinical practice to accurately detect the early state of Alzheimer’s disease (AD), i.e., mild cognitive impairment (MCI) including early MCI (EMCI) and late MCI (LMCI). To address this challenge, we propose a new MCI detection framework based on multi-atlas multi-view hybrid graph convolutional networks and ensemble learning. We first construct nine different graphs based on three brain atlases and three morphological measurements using both imaging and non-imaging data of each subject. Then, in order to integrate the information of different graphs and obtain more discriminative feature representations for detecting MCI, we propose a hybrid graph convolutional network method. Finally, a new ensemble learning method is proposed to perform MCI detection tasks. An evaluation of our proposed framework has been conducted with 369 subjects with cognitively normal (CN), 779 subjects with MCI including 310 subjects with EMCI and 469 subjects with LMCI, and 301 subjects with AD on three classification tasks. Experimental results show that our proposed framework can get an accuracy of 90.8% and an AUC of 0.932 for MCI/CN classification, an accuracy of 88.6% and an AUC of 0.908 for MCI/AD classification, and an accuracy of 83.5% and an AUC of 0.851 for EMCI/LMCI classification, respectively. Compared with some state-of-the-art methods about MCI detection, our proposed framework can get better performance. Overall, our proposed framework is effective and promising for MCI detection in clinical practice. Keywords MCI detection Multi-atlas multi-view feature representation Graph convolutional networks Ensemble learning
1 Introduction With the continuous improvement of quality of life and medical level, the number of elderly people is constantly increasing. Alzheimer’s disease (AD) is one of the common progressive neurodegenerative diseases in the elderly, & Jin Liu [email protected] & Jianxin Wang [email protected] 1
Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, China
2
Division of Biomedical Engineering and Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, Canada
and its etiology has not been known so far. As of 2018, there are approximately 5.5 million people with AD in the United States and more than 30 million people with AD worldwide, and by 2050, one in every 85 people around the world will have AD [2]. Since AD is currently incurable and is accompanied by memory impairment, loss of recognition, executive dysfunction, etc, AD is seriously
Data Loading...
