Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment Detection
Mild Cognitive Impairment (MCI) is often considered a precursor to Alzheimer’s disease (AD), with a high likelihood of progression. Accurate and timely diagnosis of MCI is essential for halting the progression of AD and other forms of dementia. Electroencephalography (EEG) is the prevalen...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10373947/ |
| _version_ | 1797354545958879232 |
|---|---|
| author | Md. Nurul Ahad Tawhid Siuly Siuly Enamul Kabir Yan Li |
| author_facet | Md. Nurul Ahad Tawhid Siuly Siuly Enamul Kabir Yan Li |
| author_sort | Md. Nurul Ahad Tawhid |
| collection | DOAJ |
| description | Mild Cognitive Impairment (MCI) is often considered a precursor to Alzheimer’s disease (AD), with a high likelihood of progression. Accurate and timely diagnosis of MCI is essential for halting the progression of AD and other forms of dementia. Electroencephalography (EEG) is the prevalent method for identifying MCI biomarkers. Frequency band-based EEG biomarkers are crucial for identifying MCI as they capture neuronal activities and connectivity patterns linked to cognitive functions. However, traditional approaches struggle to identify precise frequency band-based biomarkers for MCI diagnosis. To address this challenge, a novel framework has been developed for identifying important frequency sub-bands within EEG signals for MCI detection. In the proposed scheme, the signals are first denoised using a stationary wavelet transformation and segmented into small time frames. Then, four frequency sub-bands are extracted from each segment, and spectrogram images are generated for each sub-band as well as for the full filtered frequency band signal segments. This process produces five different sets of images for five separate frequency bands. Afterwards, a convolutional neural network is used individually on those image sets to perform the classification task. Finally, the obtained results for the tested four sub-bands are compared with the results obtained using the full bandwidth. Our proposed framework was tested on two MCI datasets, and the results indicate that the 16–32 Hz sub-band range has the greatest impact on MCI detection, followed by 4–8 Hz. Furthermore, our framework, utilizing the full frequency band, outperformed existing state-of-the-art methods, indicating its potential for developing diagnostic tools for MCI detection. |
| first_indexed | 2024-03-08T13:51:59Z |
| format | Article |
| id | doaj.art-2b376ece3ad24c9abc78f5da86e8e63a |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-08T13:51:59Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-2b376ece3ad24c9abc78f5da86e8e63a2024-01-16T00:00:18ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102024-01-013218919910.1109/TNSRE.2023.334703210373947Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment DetectionMd. Nurul Ahad Tawhid0https://orcid.org/0000-0002-6100-4895Siuly Siuly1https://orcid.org/0000-0003-2491-0546Enamul Kabir2https://orcid.org/0000-0002-6157-2753Yan Li3https://orcid.org/0000-0002-4694-4926Institute for Sustainable Industries and Liveable Cities, Victoria University, Melbourne, VIC, AustraliaInstitute for Sustainable Industries and Liveable Cities, Victoria University, Melbourne, VIC, AustraliaSchool of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, QLD, AustraliaSchool of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, QLD, AustraliaMild Cognitive Impairment (MCI) is often considered a precursor to Alzheimer’s disease (AD), with a high likelihood of progression. Accurate and timely diagnosis of MCI is essential for halting the progression of AD and other forms of dementia. Electroencephalography (EEG) is the prevalent method for identifying MCI biomarkers. Frequency band-based EEG biomarkers are crucial for identifying MCI as they capture neuronal activities and connectivity patterns linked to cognitive functions. However, traditional approaches struggle to identify precise frequency band-based biomarkers for MCI diagnosis. To address this challenge, a novel framework has been developed for identifying important frequency sub-bands within EEG signals for MCI detection. In the proposed scheme, the signals are first denoised using a stationary wavelet transformation and segmented into small time frames. Then, four frequency sub-bands are extracted from each segment, and spectrogram images are generated for each sub-band as well as for the full filtered frequency band signal segments. This process produces five different sets of images for five separate frequency bands. Afterwards, a convolutional neural network is used individually on those image sets to perform the classification task. Finally, the obtained results for the tested four sub-bands are compared with the results obtained using the full bandwidth. Our proposed framework was tested on two MCI datasets, and the results indicate that the 16–32 Hz sub-band range has the greatest impact on MCI detection, followed by 4–8 Hz. Furthermore, our framework, utilizing the full frequency band, outperformed existing state-of-the-art methods, indicating its potential for developing diagnostic tools for MCI detection.https://ieeexplore.ieee.org/document/10373947/CNNdeep learningelectroencephalogram (EEG)frequency sub-bandmild cognitive impairment (MCI)spectrogram |
| spellingShingle | Md. Nurul Ahad Tawhid Siuly Siuly Enamul Kabir Yan Li Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment Detection IEEE Transactions on Neural Systems and Rehabilitation Engineering CNN deep learning electroencephalogram (EEG) frequency sub-band mild cognitive impairment (MCI) spectrogram |
| title | Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment Detection |
| title_full | Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment Detection |
| title_fullStr | Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment Detection |
| title_full_unstemmed | Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment Detection |
| title_short | Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment Detection |
| title_sort | exploring frequency band based biomarkers of eeg signals for mild cognitive impairment detection |
| topic | CNN deep learning electroencephalogram (EEG) frequency sub-band mild cognitive impairment (MCI) spectrogram |
| url | https://ieeexplore.ieee.org/document/10373947/ |
| work_keys_str_mv | AT mdnurulahadtawhid exploringfrequencybandbasedbiomarkersofeegsignalsformildcognitiveimpairmentdetection AT siulysiuly exploringfrequencybandbasedbiomarkersofeegsignalsformildcognitiveimpairmentdetection AT enamulkabir exploringfrequencybandbasedbiomarkersofeegsignalsformildcognitiveimpairmentdetection AT yanli exploringfrequencybandbasedbiomarkersofeegsignalsformildcognitiveimpairmentdetection |