Detection of Mild Cognitive Impairment Using Convolutional Neural Network: Temporal-Feature Maps of Functional Near-Infrared Spectroscopy
Mild cognitive impairment (MCI) is the clinical precursor of Alzheimer's disease (AD), which is considered the most common neurodegenerative disease in the elderly. Some MCI patients tend to remain stable over time and do not evolve to AD. It is essential to diagnose MCI in its early stages and...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-05-01
|
| Series: | Frontiers in Aging Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fnagi.2020.00141/full |
| _version_ | 1818159938942271488 |
|---|---|
| author | Dalin Yang Ruisen Huang So-Hyeon Yoo Myung-Jun Shin Jin A. Yoon Yong-Il Shin Keum-Shik Hong |
| author_facet | Dalin Yang Ruisen Huang So-Hyeon Yoo Myung-Jun Shin Jin A. Yoon Yong-Il Shin Keum-Shik Hong |
| author_sort | Dalin Yang |
| collection | DOAJ |
| description | Mild cognitive impairment (MCI) is the clinical precursor of Alzheimer's disease (AD), which is considered the most common neurodegenerative disease in the elderly. Some MCI patients tend to remain stable over time and do not evolve to AD. It is essential to diagnose MCI in its early stages and provide timely treatment to the patient. In this study, we propose a neuroimaging approach to identify MCI using a deep learning method and functional near-infrared spectroscopy (fNIRS). For this purpose, fifteen MCI subjects and nine healthy controls (HCs) were asked to perform three mental tasks: N-back, Stroop, and verbal fluency (VF) tasks. Besides examining the oxygenated hemoglobin changes (ΔHbO) in the region of interest, ΔHbO maps at 13 specific time points (i.e., 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, and 65 s) during the tasks and seven temporal feature maps (i.e., two types of mean, three types of slope, kurtosis, and skewness) in the prefrontal cortex were investigated. A four-layer convolutional neural network (CNN) was applied to identify the subjects into either MCI or HC, individually, after training the CNN model with ΔHbO maps and temporal feature maps above. Finally, we used the 5-fold cross-validation approach to evaluate the performance of the CNN. The results of temporal feature maps exhibited high classification accuracies: The average accuracies for the N-back task, Stroop task, and VFT, respectively, were 89.46, 87.80, and 90.37%. Notably, the highest accuracy of 98.61% was achieved from the ΔHbO slope map during 20–60 s interval of N-back tasks. Our results indicate that the fNIRS imaging approach based on temporal feature maps is a promising diagnostic method for early detection of MCI and can be used as a tool for clinical doctors to identify MCI from their patients. |
| first_indexed | 2024-12-11T15:53:56Z |
| format | Article |
| id | doaj.art-2cc8025141cb41fe8da7736ed8cc38d5 |
| institution | Directory Open Access Journal |
| issn | 1663-4365 |
| language | English |
| last_indexed | 2024-12-11T15:53:56Z |
| publishDate | 2020-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Aging Neuroscience |
| spelling | doaj.art-2cc8025141cb41fe8da7736ed8cc38d52022-12-22T00:59:29ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652020-05-011210.3389/fnagi.2020.00141532678Detection of Mild Cognitive Impairment Using Convolutional Neural Network: Temporal-Feature Maps of Functional Near-Infrared SpectroscopyDalin Yang0Ruisen Huang1So-Hyeon Yoo2Myung-Jun Shin3Jin A. Yoon4Yong-Il Shin5Keum-Shik Hong6School of Mechanical Engineering, Pusan National University, Busan, South KoreaSchool of Mechanical Engineering, Pusan National University, Busan, South KoreaSchool of Mechanical Engineering, Pusan National University, Busan, South KoreaDepartment of Rehabilitation Medicine, Pusan National University School of Medicine and Biomedical Research Institute, Pusan National University Hospital, Busan, South KoreaDepartment of Rehabilitation Medicine, Pusan National University School of Medicine and Biomedical Research Institute, Pusan National University Hospital, Busan, South KoreaDepartment of Rehabilitation Medicine, Pusan National University School of Medicine, Pusan National University Yangsan Hospital, Yangsan-si, South KoreaSchool of Mechanical Engineering, Pusan National University, Busan, South KoreaMild cognitive impairment (MCI) is the clinical precursor of Alzheimer's disease (AD), which is considered the most common neurodegenerative disease in the elderly. Some MCI patients tend to remain stable over time and do not evolve to AD. It is essential to diagnose MCI in its early stages and provide timely treatment to the patient. In this study, we propose a neuroimaging approach to identify MCI using a deep learning method and functional near-infrared spectroscopy (fNIRS). For this purpose, fifteen MCI subjects and nine healthy controls (HCs) were asked to perform three mental tasks: N-back, Stroop, and verbal fluency (VF) tasks. Besides examining the oxygenated hemoglobin changes (ΔHbO) in the region of interest, ΔHbO maps at 13 specific time points (i.e., 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, and 65 s) during the tasks and seven temporal feature maps (i.e., two types of mean, three types of slope, kurtosis, and skewness) in the prefrontal cortex were investigated. A four-layer convolutional neural network (CNN) was applied to identify the subjects into either MCI or HC, individually, after training the CNN model with ΔHbO maps and temporal feature maps above. Finally, we used the 5-fold cross-validation approach to evaluate the performance of the CNN. The results of temporal feature maps exhibited high classification accuracies: The average accuracies for the N-back task, Stroop task, and VFT, respectively, were 89.46, 87.80, and 90.37%. Notably, the highest accuracy of 98.61% was achieved from the ΔHbO slope map during 20–60 s interval of N-back tasks. Our results indicate that the fNIRS imaging approach based on temporal feature maps is a promising diagnostic method for early detection of MCI and can be used as a tool for clinical doctors to identify MCI from their patients.https://www.frontiersin.org/article/10.3389/fnagi.2020.00141/fullfunctional near-infrared spectroscopy (fNIRS)mild cognitive impairment (MCI)convolutional neural network (CNN)temporal featurebrain mapN-back |
| spellingShingle | Dalin Yang Ruisen Huang So-Hyeon Yoo Myung-Jun Shin Jin A. Yoon Yong-Il Shin Keum-Shik Hong Detection of Mild Cognitive Impairment Using Convolutional Neural Network: Temporal-Feature Maps of Functional Near-Infrared Spectroscopy Frontiers in Aging Neuroscience functional near-infrared spectroscopy (fNIRS) mild cognitive impairment (MCI) convolutional neural network (CNN) temporal feature brain map N-back |
| title | Detection of Mild Cognitive Impairment Using Convolutional Neural Network: Temporal-Feature Maps of Functional Near-Infrared Spectroscopy |
| title_full | Detection of Mild Cognitive Impairment Using Convolutional Neural Network: Temporal-Feature Maps of Functional Near-Infrared Spectroscopy |
| title_fullStr | Detection of Mild Cognitive Impairment Using Convolutional Neural Network: Temporal-Feature Maps of Functional Near-Infrared Spectroscopy |
| title_full_unstemmed | Detection of Mild Cognitive Impairment Using Convolutional Neural Network: Temporal-Feature Maps of Functional Near-Infrared Spectroscopy |
| title_short | Detection of Mild Cognitive Impairment Using Convolutional Neural Network: Temporal-Feature Maps of Functional Near-Infrared Spectroscopy |
| title_sort | detection of mild cognitive impairment using convolutional neural network temporal feature maps of functional near infrared spectroscopy |
| topic | functional near-infrared spectroscopy (fNIRS) mild cognitive impairment (MCI) convolutional neural network (CNN) temporal feature brain map N-back |
| url | https://www.frontiersin.org/article/10.3389/fnagi.2020.00141/full |
| work_keys_str_mv | AT dalinyang detectionofmildcognitiveimpairmentusingconvolutionalneuralnetworktemporalfeaturemapsoffunctionalnearinfraredspectroscopy AT ruisenhuang detectionofmildcognitiveimpairmentusingconvolutionalneuralnetworktemporalfeaturemapsoffunctionalnearinfraredspectroscopy AT sohyeonyoo detectionofmildcognitiveimpairmentusingconvolutionalneuralnetworktemporalfeaturemapsoffunctionalnearinfraredspectroscopy AT myungjunshin detectionofmildcognitiveimpairmentusingconvolutionalneuralnetworktemporalfeaturemapsoffunctionalnearinfraredspectroscopy AT jinayoon detectionofmildcognitiveimpairmentusingconvolutionalneuralnetworktemporalfeaturemapsoffunctionalnearinfraredspectroscopy AT yongilshin detectionofmildcognitiveimpairmentusingconvolutionalneuralnetworktemporalfeaturemapsoffunctionalnearinfraredspectroscopy AT keumshikhong detectionofmildcognitiveimpairmentusingconvolutionalneuralnetworktemporalfeaturemapsoffunctionalnearinfraredspectroscopy |