Modern e-health systems have undergone rapid development thanks to the advances in communications, computing and machine learning technology. Especially, deep learning has great superiority in image analysis and disease prediction. In this paper, we use Alzheimer's Disease (AD) as an example to show advantages of deep learning in diagnosing brain diseases and providing clinical decision support. Firstly, we convert raw functional magnetic resonance imaging (fMRI) to a matrix to represent activity of 90 brain regions. Secondly, to represent the functional connectivity between different brain regions, a correlation matrix is obtained by calculating the correlation between each pair of brain regions. In the next, a targeted autoencoder network is built to classify the correlation matrix, which is sensitive to AD. Finally, the experiment results show that our proposed method for AD prediction achieves much better effects than traditional means. It finds the correlations between different brain regions efficiently, provides strong reference for AD prediction. Compared to Support Vector Machine (SVM), about 25% improvement is gained in prediction accuracy. The e-health field becomes more complete and effective owing to that. Our work helps predict AD at an early stage and take measures to slow down or even prevent the onset of it.
%0 Conference Paper
%1 7510831
%A Hu, C.
%A Ju, R.
%A Shen, Y.
%A Zhou, P.
%A Li, Q.
%B 2016 IEEE International Conference on Communications (ICC)
%D 2016
%K dpln healthcare
%P 1-6
%R 10.1109/ICC.2016.7510831
%T Clinical decision support for Alzheimer's disease based on deep learning and brain network
%U http://ieeexplore.ieee.org/document/7510831/
%X Modern e-health systems have undergone rapid development thanks to the advances in communications, computing and machine learning technology. Especially, deep learning has great superiority in image analysis and disease prediction. In this paper, we use Alzheimer's Disease (AD) as an example to show advantages of deep learning in diagnosing brain diseases and providing clinical decision support. Firstly, we convert raw functional magnetic resonance imaging (fMRI) to a matrix to represent activity of 90 brain regions. Secondly, to represent the functional connectivity between different brain regions, a correlation matrix is obtained by calculating the correlation between each pair of brain regions. In the next, a targeted autoencoder network is built to classify the correlation matrix, which is sensitive to AD. Finally, the experiment results show that our proposed method for AD prediction achieves much better effects than traditional means. It finds the correlations between different brain regions efficiently, provides strong reference for AD prediction. Compared to Support Vector Machine (SVM), about 25% improvement is gained in prediction accuracy. The e-health field becomes more complete and effective owing to that. Our work helps predict AD at an early stage and take measures to slow down or even prevent the onset of it.
@inproceedings{7510831,
abstract = {Modern e-health systems have undergone rapid development thanks to the advances in communications, computing and machine learning technology. Especially, deep learning has great superiority in image analysis and disease prediction. In this paper, we use Alzheimer's Disease (AD) as an example to show advantages of deep learning in diagnosing brain diseases and providing clinical decision support. Firstly, we convert raw functional magnetic resonance imaging (fMRI) to a matrix to represent activity of 90 brain regions. Secondly, to represent the functional connectivity between different brain regions, a correlation matrix is obtained by calculating the correlation between each pair of brain regions. In the next, a targeted autoencoder network is built to classify the correlation matrix, which is sensitive to AD. Finally, the experiment results show that our proposed method for AD prediction achieves much better effects than traditional means. It finds the correlations between different brain regions efficiently, provides strong reference for AD prediction. Compared to Support Vector Machine (SVM), about 25% improvement is gained in prediction accuracy. The e-health field becomes more complete and effective owing to that. Our work helps predict AD at an early stage and take measures to slow down or even prevent the onset of it.},
added-at = {2018-01-18T18:14:10.000+0100},
author = {Hu, C. and Ju, R. and Shen, Y. and Zhou, P. and Li, Q.},
biburl = {https://www.bibsonomy.org/bibtex/2cacb997be4f2fe96a5801d842428ad50/defeatnelly},
booktitle = {2016 IEEE International Conference on Communications (ICC)},
doi = {10.1109/ICC.2016.7510831},
interhash = {6acc9919c5571319883de3843638716a},
intrahash = {cacb997be4f2fe96a5801d842428ad50},
keywords = {dpln healthcare},
month = may,
pages = {1-6},
timestamp = {2018-01-18T18:14:10.000+0100},
title = {Clinical decision support for Alzheimer's disease based on deep learning and brain network},
url = {http://ieeexplore.ieee.org/document/7510831/},
year = 2016
}