[1]GUO Lei,WANG Jun,DING Weichang,et al.Classification of the functional magnetic resonance image of autism based on 4D convolutional neural network[J].CAAI Transactions on Intelligent Systems,2021,16(6):1021-1029.[doi:10.11992/tis.202009022]
Copy

Classification of the functional magnetic resonance image of autism based on 4D convolutional neural network

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 16 Number of periods: 2021 6 Page number: 1021-1029 Column: 学术论文—机器学习 Public date: 2021-11-05
Title:
Classification of the functional magnetic resonance image of autism based on 4D convolutional neural network
Author(s):
GUO Lei1;  WANG Jun2;  DING Weichang2;  PAN Xiang1;  DENG Zhaohong1;  SHI Jun2;  WANG Shitong1
1. School of Artificial Intelligence and Computer, Jiangnan University, Wuxi 214122, China;
2. School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
Keywords:
deep learning; convolutional neural network; autism; 4D convolution; functional magnetic resonance imaging; feature extraction; feature fusion; image classification
CLC:
TP391
DOI:
10.11992/tis.202009022
Abstract:
Resting-state functional magnetic resonance images are a series of three-dimensional (3D) images that change over time. The existing 3D convolution processes 3D image data or two-dimensional image and time-dimensional data, but it cannot effectively fuse the time axis information of a resting-state functional magnetic resonance image. To resolve this, a new four-dimensional (4D) convolutional neural network (CNN) recognition model is proposed in this paper. Specifically, by performing a 4D convolution using a 4D convolution kernel on the input functional magnetic resonance imaging, features are spatially and temporally extracted from the functional magnetic resonance image of a patient with autism, thereby capturing information about the changes in the image’s time series. The developed model generates multiple information channels from the input image, and the final feature representation combines information from all channels. The experimental results show that to ensure the generalization performance of the model, the method fuses the global information of the functional image and collects its trend information over time, consequently solving the classification problem of 3D image changes with time using a CNN.
References:
[1] 张芬, 王穗苹, 杨娟华, 等. 自闭症谱系障碍者异常的大脑功能连接[J]. 心理科学进展, 2015, 23(7): 1196-1204
ZHANG Fen, WANG Suiping, YANG Juanhua, et al. Atypical brain functional connectivity in autism spectrum disorders[J]. Advances in psychological science, 2015, 23(7): 1196-1204
[2] CABALLERO-GAUDES C, REYNOLDS R C. Methods for cleaning the BOLD fMRI signal[J]. Neuroimage, 2017, 154: 128-149.
[3] MOELLER S, YACOUB E, OLMAN C A, et al. Multiband multislice GE-EPI at 7 tesla, with 16-fold acceleration using partial parallel imaging with application to high spatial and temporal whole-brain FMRI[J]. Magnetic resonance in medicine, 2010, 63(5): 1144-1153.
[4] 常春云. 基于静息态功能磁共振成像的自闭症预测研究[D]. 北京: 北京交通大学, 2017.
CHANG Chunyun. Research on prediction of autism spectrum disorder based on resting-state fMRI[D]. Beijing: Beijing Jiaotong University, 2017.
[5] DVORNEK N C, VENTOLA P, PELPHREY K A, et al. Identifying autism from resting-state fMRI using long short-term memory networks[M]//WANG Qian, SHI Yinghuan, SUK H I, et al. Machine Learning in Medical Imaging. Cham: Springer, 2017: 362-370.
[6] ZHAO Yu, DONG Qinglin, ZHANG Shu, et al. Automatic recognition of fMRI-derived functional networks using 3-D convolutional neural networks[J]. IEEE transactions on biomedical engineering, 2018, 65(9): 1975-1984.
[7] LI Xiaoxiao, DVORNEK N C, PAPADEMETRIS X, et al. 2-Channel convolutional 3D deep neural network (2CC3D) for fMRI analysis: ASD classification and feature learning[C]//2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). Washington, USA, 2018: 1252-1255.
[8] KHOSLA M, JAMISON K, KUCEYESKI A, et al. Ensemble learning with 3D convolutional neural networks for functional connectome-based prediction[J]. NeuroImage, 2019, 199: 651-662.
[9] LU Zhou, PU Hongming, WANG Feicheng, et al. The expressive power of neural networks: a view from the width[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, USA, 2017: 6232-6240.
[10] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada, 2012: 1097-1105.
[11] JI Shuiwang, XU Wei, YANG Ming, et al. 3D Convolutional neural networks for human action recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2013, 35(1): 221-231.
[12] DIBA A, FAYYAZ M, SHARMA V, et al. Temporal 3D convnets: new architecture and transfer learning for video classification [EB/OL].(2017-11-22)[2020-9-20]https:// arxiv. org/ abs/1711.08200.
[13] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[14] HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Computer science, 2012, 3(4): 212-223.
[15] SIMONYAN K, ZISSERMAN A . Very deep convolutional networks for large-scale image recognition[EB/OL]// (2018-8-16)[2019-4-26]https://arxiv.org/abs/1808.05377v1.
[16] SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA, 2014: 1-9.
[17] IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning. Lille, France, 2015: 448-456.
[18] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA, 2016: 2818-2826.
[19] SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. San Francisco, USA, 2017: 4278-4284.
[20] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA, 2016: 770-778.
[21] HUANG Gao, LIU Zhuang, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA, 2017: 2261-2269.
[22] EL GAZZAR A, CERLIANI L, VAN WINGEN G, et al. Simple 1-D convolutional networks for resting-state fMRI based classification in autism[C]//2019 International Joint Conference on Neural Networks (IJCNN). Budapest, Hungary, 2019: 1-6.
[23] YAN Chaogan, WANG Xindi, ZUO Xinian, et al. DPABI: data processing & analysis for (resting-state) brain imaging[J]. Neuroinformatics, 2016, 14(3): 339-351.
[24] HECHT-NIELSEN. Theory of the backpropagation neural network[C]//International 1989 Joint Conference on Neural Networks. Washington, USA, 1989: 593-605.
[25] ELSKEN T, METZEN J H, HUTTER F . Neural architecture search: A survey[EB/OL]. (2018-8-16)[2020-9-20]https://arxiv.org/abs/1808.05377v1.
[26] SALVADOR R, SUCKLING J, COLEMAN M R, et al. Neurophysiological architecture of functional magnetic resonance images of human brain[J]. Cerebral cortex, 2005, 15(9): 1332-1342.
Similar References:

Memo

-

Last Update: 2021-12-25

Copyright © CAAI Transactions on Intelligent Systems