Computer-Aided Diagnosis of Mild
Cognitive Impairment Based on SVM
Sichong Chen, Wenjing Jiang, Bingjia Liu, and Zhiqiong Wang
(B)
College of Medicine and Biological Information Engineering,
Northeastern University, Shenyang, China
{20175672, 20175664, 20175656}@stu.neu.edu.cn,
wangzq@bmie.neu.edu.cn
Abstract. Recent years, resting-state functional magnetic resonance
imaging (rs-fMRI) and complex network analysis are guiding new directions in studies of brain disease. Here, this study aims to discriminate mild cognitive impairment (MCI) from cognitive normal (CN) by
computer-aided diagnosis. For each subject, the functional brain network
was constructed by thresholding with sparsity. Features were extracted
through network measures and selected via the least absolute shrinkage
and selection operator (LASSO). Features of two forms, computed separately under each threshold and integrated into area under the curve
(AUC), were extracted. With features in the form of AUC, the support
vector machines (SVM) classifier achieved an accuracy of 87%, which
raised to 90% with threshold of 0.3. LASSO without stability selection
was examined, achieving similar performance in classification to LASSO
with stability selection while being less time consuming.
Keywords: Computer-aided diagnosis · Mild cognitive impairment ·
Functional brain network · Feature extraction and selection · Support
vector machines
1 Introduction
Mild cognitive impairment (MCI) is a kind of disease which precedes Alzheimer’s
disease (AD) and develops widely in elderly people. Research [1] has shown
that MCI patients are of higher risk converting into AD than normal aging
people. Due to the unclear etiology and pathogenesis of AD, there is no effective
treatment for AD at present. However, for patients with MCI, drug intervention
and other methods are available for effectively delaying and even curing the
disease [2]. Therefore, exploring an accurate-aided diagnosis method for MCI is
the key to curing MCI and reducing the conversion from MCI to AD.
The human brain a complex network, which continuously processing and
transporting information among different regions, not only structurally, but functionally [3]. Therefore, the connectivity could be explored by utilizing complex
c
Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 442–451, 2020.
https://doi.org/10.1007/978-981-15-0187-6_53
Cognitive Impairment Based on SVM
Sichong Chen, Wenjing Jiang, Bingjia Liu, and Zhiqiong Wang
(B)
College of Medicine and Biological Information Engineering,
Northeastern University, Shenyang, China
{20175672, 20175664, 20175656}@stu.neu.edu.cn,
wangzq@bmie.neu.edu.cn
Abstract. Recent years, resting-state functional magnetic resonance
imaging (rs-fMRI) and complex network analysis are guiding new directions in studies of brain disease. Here, this study aims to discriminate mild cognitive impairment (MCI) from cognitive normal (CN) by
computer-aided diagnosis. For each subject, the functional brain network
was constructed by thresholding with sparsity. Features were extracted
through network measures and selected via the least absolute shrinkage
and selection operator (LASSO). Features of two forms, computed separately under each threshold and integrated into area under the curve
(AUC), were extracted. With features in the form of AUC, the support
vector machines (SVM) classifier achieved an accuracy of 87%, which
raised to 90% with threshold of 0.3. LASSO without stability selection
was examined, achieving similar performance in classification to LASSO
with stability selection while being less time consuming.
Keywords: Computer-aided diagnosis · Mild cognitive impairment ·
Functional brain network · Feature extraction and selection · Support
vector machines
1 Introduction
Mild cognitive impairment (MCI) is a kind of disease which precedes Alzheimer’s
disease (AD) and develops widely in elderly people. Research [1] has shown
that MCI patients are of higher risk converting into AD than normal aging
people. Due to the unclear etiology and pathogenesis of AD, there is no effective
treatment for AD at present. However, for patients with MCI, drug intervention
and other methods are available for effectively delaying and even curing the
disease [2]. Therefore, exploring an accurate-aided diagnosis method for MCI is
the key to curing MCI and reducing the conversion from MCI to AD.
The human brain a complex network, which continuously processing and
transporting information among different regions, not only structurally, but functionally [3]. Therefore, the connectivity could be explored by utilizing complex
c
Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 442–451, 2020.
https://doi.org/10.1007/978-981-15-0187-6_53