A Novel Convolutional Variation of Broad Learning System for Alzheimer’s Disease Diagnosis by Using MRI Images
Alzheimer's disease (AD) is a serious chronic health problem that causes great pain and loss to patients and their families. Its early and accurate diagnosis would achieve significant progress on the prevention and treatment of the disease. Magnetic Resonance Imaging (MRI) is a commonly used te...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9268103/ |
| id |
doaj-28a40cc0113b4c3ba1cac0938f730b2a |
|---|---|
| record_format |
Article |
| spelling |
doaj-28a40cc0113b4c3ba1cac0938f730b2a2021-03-30T03:41:50ZengIEEEIEEE Access2169-35362020-01-01821464621465710.1109/ACCESS.2020.30403409268103A Novel Convolutional Variation of Broad Learning System for Alzheimer’s Disease Diagnosis by Using MRI ImagesRuizhi Han0https://orcid.org/0000-0003-3323-4068C. L. Philip Chen1https://orcid.org/0000-0001-5451-7230Zhulin Liu2https://orcid.org/0000-0003-4145-823XFaculty of Science and Technology, University of Macau, Zhuhai, MacauFaculty of Science and Technology, University of Macau, Zhuhai, MacauSchool of Computer Science and Engineering, South China University of Technology, Guangzhou, ChinaAlzheimer's disease (AD) is a serious chronic health problem that causes great pain and loss to patients and their families. Its early and accurate diagnosis would achieve significant progress on the prevention and treatment of the disease. Magnetic Resonance Imaging (MRI) is a commonly used technique in nuclear medical diagnostics. However, it is still a challenging problem to diagnose AD, Control Normal (CN), and Mild Cognitive Impairment (MCI) because of the complex structures of MRI. In this paper, diagnosing models for MRI images are proposed to identify the various stages of AD based on the Broad Learning Systems (BLS), as well as its convolutional variants. To verify the validity of the proposed models, experiments on MRI images collected from the ADNI website are tested and evaluated. The results show that our algorithms outperform the other state-of-the-art algorithms for various tasks with better accuracy and less training times. Finally, the cross-domain learning ability of the proposed algorithms is verified on an independent AD dataset.https://ieeexplore.ieee.org/document/9268103/Alzheimer’s diseasebroad learning systemconvolutional neural networkimage classificationmagnetic resonance imaging |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Ruizhi Han C. L. Philip Chen Zhulin Liu |
| spellingShingle |
Ruizhi Han C. L. Philip Chen Zhulin Liu A Novel Convolutional Variation of Broad Learning System for Alzheimer’s Disease Diagnosis by Using MRI Images IEEE Access Alzheimer’s disease broad learning system convolutional neural network image classification magnetic resonance imaging |
| author_facet |
Ruizhi Han C. L. Philip Chen Zhulin Liu |
| author_sort |
Ruizhi Han |
| title |
A Novel Convolutional Variation of Broad Learning System for Alzheimer’s Disease Diagnosis by Using MRI Images |
| title_short |
A Novel Convolutional Variation of Broad Learning System for Alzheimer’s Disease Diagnosis by Using MRI Images |
| title_full |
A Novel Convolutional Variation of Broad Learning System for Alzheimer’s Disease Diagnosis by Using MRI Images |
| title_fullStr |
A Novel Convolutional Variation of Broad Learning System for Alzheimer’s Disease Diagnosis by Using MRI Images |
| title_full_unstemmed |
A Novel Convolutional Variation of Broad Learning System for Alzheimer’s Disease Diagnosis by Using MRI Images |
| title_sort |
novel convolutional variation of broad learning system for alzheimer’s disease diagnosis by using mri images |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2020-01-01 |
| description |
Alzheimer's disease (AD) is a serious chronic health problem that causes great pain and loss to patients and their families. Its early and accurate diagnosis would achieve significant progress on the prevention and treatment of the disease. Magnetic Resonance Imaging (MRI) is a commonly used technique in nuclear medical diagnostics. However, it is still a challenging problem to diagnose AD, Control Normal (CN), and Mild Cognitive Impairment (MCI) because of the complex structures of MRI. In this paper, diagnosing models for MRI images are proposed to identify the various stages of AD based on the Broad Learning Systems (BLS), as well as its convolutional variants. To verify the validity of the proposed models, experiments on MRI images collected from the ADNI website are tested and evaluated. The results show that our algorithms outperform the other state-of-the-art algorithms for various tasks with better accuracy and less training times. Finally, the cross-domain learning ability of the proposed algorithms is verified on an independent AD dataset. |
| topic |
Alzheimer’s disease broad learning system convolutional neural network image classification magnetic resonance imaging |
| url |
https://ieeexplore.ieee.org/document/9268103/ |
| work_keys_str_mv |
AT ruizhihan anovelconvolutionalvariationofbroadlearningsystemforalzheimerx2019sdiseasediagnosisbyusingmriimages AT clphilipchen anovelconvolutionalvariationofbroadlearningsystemforalzheimerx2019sdiseasediagnosisbyusingmriimages AT zhulinliu anovelconvolutionalvariationofbroadlearningsystemforalzheimerx2019sdiseasediagnosisbyusingmriimages AT ruizhihan novelconvolutionalvariationofbroadlearningsystemforalzheimerx2019sdiseasediagnosisbyusingmriimages AT clphilipchen novelconvolutionalvariationofbroadlearningsystemforalzheimerx2019sdiseasediagnosisbyusingmriimages AT zhulinliu novelconvolutionalvariationofbroadlearningsystemforalzheimerx2019sdiseasediagnosisbyusingmriimages |
| _version_ |
1724182930981388288 |