Comparison of machine learning approaches for enhancing Alzheimer’s disease classification
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder, accounting for nearly 60% of all dementia cases. The occurrence of the disease has been increasing rapidly in recent years. Presently about 46.8 million individuals suffer from AD worldwide. The current absence of effective treatm...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2021-02-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/10549.pdf |
| _version_ | 1797418623693750272 |
|---|---|
| author | Qi Li Mary Qu Yang |
| author_facet | Qi Li Mary Qu Yang |
| author_sort | Qi Li |
| collection | DOAJ |
| description | Alzheimer’s disease (AD) is a progressive neurodegenerative disorder, accounting for nearly 60% of all dementia cases. The occurrence of the disease has been increasing rapidly in recent years. Presently about 46.8 million individuals suffer from AD worldwide. The current absence of effective treatment to reverse or stop AD progression highlights the importance of disease prevention and early diagnosis. Brain structural Magnetic Resonance Imaging (MRI) has been widely used for AD detection as it can display morphometric differences and cerebral structural changes. In this study, we built three machine learning-based MRI data classifiers to predict AD and infer the brain regions that contribute to disease development and progression. We then systematically compared the three distinct classifiers, which were constructed based on Support Vector Machine (SVM), 3D Very Deep Convolutional Network (VGGNet) and 3D Deep Residual Network (ResNet), respectively. To improve the performance of the deep learning classifiers, we applied a transfer learning strategy. The weights of a pre-trained model were transferred and adopted as the initial weights of our models. Transferring the learned features significantly reduced training time and increased network efficiency. The classification accuracy for AD subjects from elderly control subjects was 90%, 95%, and 95% for the SVM, VGGNet and ResNet classifiers, respectively. Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to show discriminative regions that contributed most to the AD classification by utilizing the learned spatial information of the 3D-VGGNet and 3D-ResNet models. The resulted maps consistently highlighted several disease-associated brain regions, particularly the cerebellum which is a relatively neglected brain region in the present AD study. Overall, our comparisons suggested that the ResNet model provided the best classification performance as well as more accurate localization of disease-associated regions in the brain compared to the other two approaches. |
| first_indexed | 2024-03-09T06:35:35Z |
| format | Article |
| id | doaj.art-cd6d83b78e744acba0d2c290629f6f8c |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:35:35Z |
| publishDate | 2021-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-cd6d83b78e744acba0d2c290629f6f8c2023-12-03T10:59:13ZengPeerJ Inc.PeerJ2167-83592021-02-019e1054910.7717/peerj.10549Comparison of machine learning approaches for enhancing Alzheimer’s disease classificationQi Li0Mary Qu Yang1MidSouth Bioinformatics Center and Bioinformatics Graduate Program, University of Arkansas at Little Rock and University of Arkansas for Medical Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States of AmericaMidSouth Bioinformatics Center and Bioinformatics Graduate Program, University of Arkansas at Little Rock and University of Arkansas for Medical Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States of AmericaAlzheimer’s disease (AD) is a progressive neurodegenerative disorder, accounting for nearly 60% of all dementia cases. The occurrence of the disease has been increasing rapidly in recent years. Presently about 46.8 million individuals suffer from AD worldwide. The current absence of effective treatment to reverse or stop AD progression highlights the importance of disease prevention and early diagnosis. Brain structural Magnetic Resonance Imaging (MRI) has been widely used for AD detection as it can display morphometric differences and cerebral structural changes. In this study, we built three machine learning-based MRI data classifiers to predict AD and infer the brain regions that contribute to disease development and progression. We then systematically compared the three distinct classifiers, which were constructed based on Support Vector Machine (SVM), 3D Very Deep Convolutional Network (VGGNet) and 3D Deep Residual Network (ResNet), respectively. To improve the performance of the deep learning classifiers, we applied a transfer learning strategy. The weights of a pre-trained model were transferred and adopted as the initial weights of our models. Transferring the learned features significantly reduced training time and increased network efficiency. The classification accuracy for AD subjects from elderly control subjects was 90%, 95%, and 95% for the SVM, VGGNet and ResNet classifiers, respectively. Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to show discriminative regions that contributed most to the AD classification by utilizing the learned spatial information of the 3D-VGGNet and 3D-ResNet models. The resulted maps consistently highlighted several disease-associated brain regions, particularly the cerebellum which is a relatively neglected brain region in the present AD study. Overall, our comparisons suggested that the ResNet model provided the best classification performance as well as more accurate localization of disease-associated regions in the brain compared to the other two approaches.https://peerj.com/articles/10549.pdfVery deep convolutional networkDeep residual networkAlzheimer’s diseaseGradient-weighted class activation mappingMRI |
| spellingShingle | Qi Li Mary Qu Yang Comparison of machine learning approaches for enhancing Alzheimer’s disease classification PeerJ Very deep convolutional network Deep residual network Alzheimer’s disease Gradient-weighted class activation mapping MRI |
| title | Comparison of machine learning approaches for enhancing Alzheimer’s disease classification |
| title_full | Comparison of machine learning approaches for enhancing Alzheimer’s disease classification |
| title_fullStr | Comparison of machine learning approaches for enhancing Alzheimer’s disease classification |
| title_full_unstemmed | Comparison of machine learning approaches for enhancing Alzheimer’s disease classification |
| title_short | Comparison of machine learning approaches for enhancing Alzheimer’s disease classification |
| title_sort | comparison of machine learning approaches for enhancing alzheimer s disease classification |
| topic | Very deep convolutional network Deep residual network Alzheimer’s disease Gradient-weighted class activation mapping MRI |
| url | https://peerj.com/articles/10549.pdf |
| work_keys_str_mv | AT qili comparisonofmachinelearningapproachesforenhancingalzheimersdiseaseclassification AT maryquyang comparisonofmachinelearningapproachesforenhancingalzheimersdiseaseclassification |