[1]KONG Lingxu,WU Haifeng,ZENG Yu,et al.Transfer learning-based feature extraction method for the classification of rs-fMRI early mild cognitive impairment[J].CAAI Transactions on Intelligent Systems,2021,16(4):662-672.[doi:10.11992/tis.202007041]
Copy

Transfer learning-based feature extraction method for the classification of rs-fMRI early mild cognitive impairment

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 16 Number of periods: 2021 4 Page number: 662-672 Column: 学术论文—机器感知与模式识别 Public date: 2021-07-05
Title:
Transfer learning-based feature extraction method for the classification of rs-fMRI early mild cognitive impairment
Author(s):
KONG Lingxu1;  WU Haifeng1; 2;  ZENG Yu1; 2;  LU Xiaoling1;  LUO Jinling1
1. School of Electrical and Information Technology, Yunnan Minzu University, Kunming 650500, China;
2. Program for Innovative Research Team (in Science and Technology) in University of Yunnan Province, Kunming 650500, China
Keywords:
EMCI; rs-fMRI; transfer learning; Alzheimer’s disease; MobileNet; deep learning; machine learning; region of interest
CLC:
TP391.41
DOI:
10.11992/tis.202007041
Abstract:
Early mild cognitive impairment (EMCI) is a necessary stage before Alzheimer’s disease (AD). Thus, accurate diagnosis of EMCI will help the early prevention and treatment of AD. The performance of the deep learning method for the diagnosis of EMCI through rest-state functional magnetic resonance imaging (rs-fMRI) mainly depends on how feature values are extracted. However, traditional extraction methods have problems, such as loss of feature information and long training network time. To address these problems, this paper proposes a transfer learning-based feature extraction method for EMCI classification. First, the region of interest (ROI) time series is extracted from rs-fMRI to complete the dimensional reduction of source data. Second, bottleneck features are extracted from the ROI by using a transfer learning MobileNet. Lastly, a final classification result is obtained from those entered features into a designed top-layer net. The data of the Alzheimer’s Disease Neuroimaging Initiative are tested through experiments. Experimental results show that compared with traditional methods, the classification accuracy of the proposed method is enhanced by around 10%, and 75% or so of classification time is saved.
References:
[1] BURNS A, ILIFFE S. Alzheimer’s disease[J]. British medical journal, 2009, 338(7692): 467-471.
[2] Alzheimer’s Association. 2018 Alzheimer’s disease facts and figures[J]. Alzheimer’s & dementia, 2018, 14(3): 367-429.
[3] DAVATZIKOS C. Baseline and longitudinal patterns of brain atrophy in MCI patients and their use in prediction of short-term conversion to Alzheimer’s disease: results from ADNI[J]. Alzheimer’s & dementia, 2009, 5(4S): P21-P22.
[4] GRUNDMAN M, PETERSEN R C, FERRIS S H. Mild cognitive impairment can be distinguished from Alzheimer disease and normal aging for clinical trials[J]. Archives of neurology, 2004, 61(1): 59-66.
[5] BISCHKOPF J, BUSSE A, ANGERMEYER M C. Mild cognitive impairment-a review of prevalence, incidence and outcome according to current approaches[J]. Acta psychiatrica scandinavica, 2002, 106(6): 403-414.
[6] SHARMA N, SINGH A N. Exploring biomarkers for Alzheimer’s disease[J]. Journal of clinical and diagnostic research, 2016, 10(7): KE01-KE06.
[7] MCKAHNN G. Clinical diagnosis of Alzheimer’s disease: report of the NINCDS-ADRDA Work Group* under the auspices of department of health and human services task force on Alzheimer’s disease[J]. Neurology, 1984, 34(7): 939.
[8] SCHROETER M L, STEIN T, MASLOWSKI N, et al. Neural correlates of Alzheimer’s disease and mild cognitive impairment: a systematic and quantitative meta-analysis involving 1351 patients[J]. NeuroImage, 2009, 47(4): 1196-1206.
[9] HALLER S, BARTSCH A J. Pitfalls in fMRI[J]. European radiology, 2009, 19(11): 2689-2706.
[10] BRIER M R, THOMAS J B, SNYDER A Z, et al. Loss of intranetwork and internetwork resting state functional connections with Alzheimer’s disease progression[J]. Journal of neuroscience, 2012, 32(26): 8890-8899.
[11] STANLEY M L, MOUSSA M N, PAOLINI B M, et al. Defining nodes in complex brain networks[J]. Frontiers in computational neuroscience, 2013, 7: 169.
[12] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3): 211-252.
[13] B?CKMAN L, JONES S, BERGER A K, et al. Multiple cognitive deficits during the transition to Alzheimer’s disease[J]. Journal of internal medicine, 2004, 256(3): 195-204.
[14] WEE C Y, YAP P T, DENNY K, et al. Resting-state multi-spectrum functional connectivity networks for identification of MCI patients[J]. PLoS One, 2012, 7(5): e37828.
[15] GEHRING J, MIAO Y J, METZE F, et al. Extracting deep bottleneck features using stacked auto-encoders[C]//Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, BC, Canada, 2013: 3377-3381.
[16] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[17] HON M, KHAN N M. Towards Alzheimer’s disease classification through transfer learning[C]//Proceedings of 2017 IEEE International Conference on Bioinformatics and Biomedicine. Kansas City, MO, USA, 2017: 1166?1169.
[18] JOHNSON K A, FOX N C, SPERLING R A, et al. Brain Imaging in Alzheimer Disease[J]. Cold spring harbor perspectives in medicine, 2012, 2(4): a006213.
[19] CUINGNET R, GERARDIN E, TESSIERAS J, et al. Automatic classification of patients with Alzheimer’s disease from structural MRI: a comparison of ten methods using the ADNI database[J]. Neuroimage, 2011, 56(2): 766-781.
[20] BARKHOF F, HALLER S, ROMBOUTS S A R B. Resting-state functional MR imaging: a new window to the brain[J]. Radiology, 2014, 272(1): 29-49.
[21] MACHULDA M M, WARD H A, BOROWSKI B, et al. Comparison of memory fMRI response among Normal, MCI, and Alzheimer’s patients[J]. Neurology, 2003, 61(4): 500-506.
[22] JU Ronghui, HU Chenhui, ZHOU Pan, et al. Early diagnosis of Alzheimer’s disease based on resting-state brain networks and deep learning[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2019, 16(1): 244-257.
[23] HJELM R D, CALHOUN V D, SALAKHUTDINOV R, et al. Restricted boltzmann machines for neuroimaging: an application in identifying intrinsic networks[J]. NeuroImage, 2014, 96: 245-260.
[24] NIE Dong, LU Junfeng, ZHANG Han, et al. Multi-channel 3D deep feature learning for survival time prediction of brain tumor patients using multi-modal neuroimages[J]. Scientific reports, 2019, 9(1): 1103.
[25] TZOURIO-MAZOYER N, LANDEAU B, PAPATHANASSIOU D, et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain[J]. Neuroimage, 2002, 15(1): 273-289.
[26] HOWARD A G, ZHU Menglong, CHEN Bo, et al. Mobilenets: efficient convolutional neural networks for mobile vision applications[J/OL]. Computer Vision and Pattern Recognition. (2017-04-17) [2020-07-24] https://arxiv.org/abs/1704.04861v1.
[27] YAN Chaogan, ZANG Yufeng. DPARSF: a MATLAB toolbox for “pipeline” data analysis of resting-state fMRI[J]. Frontiers in Systems Neuroscience, 2010, 4: 13.
[28] XIONG Hui, SHEKHAR S, TAN Pangning, et al. Exploiting a support-based upper bound of Pearson’s correlation coefficient for efficiently identifying strongly correlated pairs[C]//Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Seattle, WA, USA, 2004: 334-343.
[29] MOORE A W. Cross-validation for detecting and preventing overfitting[M]. Pittsburgh, USA: Carnegie Mellon University, 2001.
[30] ZHENG Hao, YANG Zhanlei, LIU Wenju, et al. Improving deep neural networks using softplus units[C]//Proceedings of 2015 International Joint Conference on Neural Networks. Killarney, Ireland, 2015: 1?4.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems