臺灣博碩士論文加值系統

過往研究中已有相當多研究使用腦電圖(Electroencephalography, EEG)訊號來鑑別阿茲海默症(Alzheimer’s Disease, AD)，輕度認知障礙(Mild Cognitive Impairment, MCI)與健康受測者(Healthy Control, HC)，然而大多腦波測驗為休息狀態，很少使用可以更好鑑別此三類別的記憶任務作為腦波測驗。因此，本論文藉由一套記憶任務的腦波收取流程，依序收取休息狀態及記憶任務。在三種不同難度的記憶題目下，受測者會經過記憶存取(Memory Encoding, ME)、記憶維持(Memory Maintenance, MM)、記憶提取(Memory Retrival, MR)三個階段，記錄受測者進行記憶任務的腦波，以更有效地分類這三個類別。本論文總共收取21位AD患者、24位MCI患者以及27位HC的腦波訊號進行分析。
特徵收取使用子頻帶功率之電極間相對功率，並藉由休息狀態作為基準線校正記憶任務，計算記憶任務與休息狀態的差異。特徵篩選為費雪準則，分類器使用線性鑑別分析。實驗結果顯示，AD vs MCI於ME Level 3的分類率為100%、MCI vs HC於ME Level 3的分類率為97.92%、AD vs HC於ME Level 2的分類率為98.04%以及AD vs MCI vs HC於MM Level 2的分類率為90.28%。希望此結果對於失智症研究有所貢獻。

In previous studies, there have been quite a lot studies using electroencephalography (EEG) signals to discriminating Alzheimer's Disease(AD), Mild Cognitive Impairment (MCI) and healthy control(HC). But most of the EEG tests were at resting, and memory tasks are rarely used to better discriminating these 3 groups. Therefore, in this study, we through a set of EEG collection process of memory state. Under three different levels of memory tasks, the subject will go through three stages of memory encoding (ME), memory maintenance(MM), and memory retrieval(MR). Recording EEG signals of memory tasks to classify these three groups more effectively. We collected 21 AD patients, 24 MCI patients and 27 HC EEG signals for analysis.
The results show that the accuracy of AD vs MCI in ME Level 3 is 100%, the accuracy of MCI vs HC in ME Level 3 is 97.92%, the accuracy of AD vs HC in ME Level 2 is 98.04%, and the accuracy of AD vs MCI vs HC in MM Level 2 is 90.28%. Hope this result will contribute to the study of dementia.

摘要 i
ABSTRACT ii
目錄 iv
圖目錄 vi
表目錄 vii
第一章 緒論 1
1.1前言 1
1.2文獻回顧 2
1.3研究目的 10
1.4本文架構 11
第二章 實驗設計 12
2.1軟硬體實驗設備介紹 12
2.1.1腦波擷取系統 12
2.1.2腦波訊號前處理 13
2.2實驗架構 14
2.2.1實驗對象 14
2.2.2身心評估問卷調查 16
2.2.3實驗流程 17
2.2.4實驗面板與流程 18
第三章 研究方法與理論 22
3.1 Laplacian空間濾波 22
3.2特徵抽取 22
3.2.1頻帶功率 22
3.2.2基於相對功率之特徵抽取 24
3.2.3基於碎形維度之特徵抽取 24
3.3特徵選擇與分類器 26
3.3.1基於費雪準則之維度縮減 26
3.3.3基於線性鑑別分析之分類演算法 28
3.4交叉驗證法 29
3.5性能指標 31
3.5.1混淆矩陣 31
3.5.2分類率(Classification Rate, CR) 31
3.5.2平衡分類率(Balanced Classification Rate, CR) 32
第四章 結果與討論 33
4.1不同特徵之分類結果 33
4.2 使用Laplacian空間濾波之不同特徵分類結果 40
4.3跨任務之二元分類不同特徵的探討 44
4.3.1 AD vs MCI 45
4.3.2 MCI vs HC 47
4.3.3 AD vs HC 50
4.4使用休息狀態校正之三類別分類不同特徵的探討 53
4.5綜合討論 56
第五章 結論與未來研究方向 62
5.1結論 62
5.2未來研究方向 63
參考文獻 64

[1]台灣失智症協會.
http://www.tada2002.org.tw/About/IsntDementia
[2]衛生福利部. 失智症診療手冊.
https://www.mohw.gov.tw/dl-27189-8993c3ad-0f47-45e0-a602-6a4362faae9a.html
[3]B. Dubois, H. H. Feldman, C. Jacova, S. T. DeKosky, P. Barberger-Gateau, J. Cummings, A. Delacourte, D. Galasko, S. Gauthier, G. Jicha, K. Meguro, J. O'Brien, F. Pasquier, P. Robert, M. Rossor, S. Salloway, Y. Stern, P. J. Visser, and P. Scheltens, “Research criteria for the diagnosis of alzheimer's disease: Revising the NINCDS–ADRDA criteria,” The Lancet Neurology, vol. 6, no. 8, pp. 734-746, 2007.
[4]Alzheimer's Association, “2016 Alzheimer's disease facts and figures,” Alzheimer's & Dementia, vol. 12, no. 4, pp. 459-509, 2016.
[5]American Psychiatric Association, American Psychiatric Association. DSM-5 Task Force., Diagnostic and statistical manual of mental disorders: DSM-5. 5th ed. American Psychiatric Association: Washington, D.C., 2013.
[6]M. F. Folstein, S. E. Folstein, and P. R. McHugh, ““Mini-mental state”: A practical method for grading the cognitive state of patients for the clinician,” Journal of psychiatric research, vol. 12, no. 3, pp. 189-198, 1975.
[7]J. Morris, “The clinical dementia rating (CDR): Current version and scoring rules,” Neurology, vol. 43, no. 11, pp. 2412-2412, 1993.
[8]J. H. Roh, M. H. Park, D. Ko, K. Park, D. Lee, C. Han, S. A. Jo, K. Yang, and K. Jung, “Region and frequency specific changes of spectral power in alzheimer’s disease and mild cognitive impairment,” Clinical Neurophysiology, vol. 122, no. 11, pp. 2169-2176, 2011.
[9]R. Wang, J. Wang, H. Yu, X. Wei, C. Yang, and B. Deng, “Power spectral density and coherence analysis of alzheimer’s EEG,” Cognitive Neurodynamics, vol. 9, no. 3, pp. 291-304, 2015.
[10]V. Jelic, M. Shigeta, P. Julin, O. Almkvist, B. Winblad, and L. Wahlund, “Quantitative electroencephalography power and coherence in Alzheimer's disease and mild cognitive impairment,” Dementia and Geriatric Cognitive Disorders, vol. 7, no. 6, pp. 314-323, 1996.
[11]V. Jelic, S. Johansson, O. Almkvist, M. Shigeta, P. Julin, A. Nordberg, B. Winblad, and L. Wahlund, “Quantitative electroencephalography in mild cognitive impairment: Longitudinal changes and possible prediction of Alzheimer’s disease,” Neurobiology of aging, vol. 21, no. 4, pp. 533-540, 2000.
[12]P. M. Rodrigues, B. C. Bispo, D. R. Freitas, J. P. Teixeira, and A. Carreres, “Evaluation of EEG spectral features in Alzheimer disease discrimination,” Proc. 21st Eur. Signal Process. Conf., pp. 1-5, Sep. 2013.
[13]E. Neto, F. Biessmann, H. Aurlien, H. Nordby, and T. Eichele, “Regularized linear discriminant analysis of EEG features in dementia patients,” Frontiers in Aging Neuroscience, vol. 8, no. 30, 2016.
[14]J. Poza, C. Gómez, M. García, M. A. Tola-Arribas, A. Carreres, M. Cano, and R. Hornero, “Spatio-temporal fluctuations of neural dynamics in mild cognitive impairment and Alzheimer's disease,” Current Alzheimer Research, vol. 14, no. 9, pp. 924-936, 2017.
[15]C. S. Musaeus, K. Engedal, P. Høgh, V. Jelic, M. Mørup, M. Naik, A. Oeksengaard, J. Snaedal, L. Wahlund, G. Waldemar, and B. B. Andersen, “EEG theta power is an early marker of cognitive decline in dementia due to Alzheimer’s disease,” Journal of Alzheimer's Disease, vol. 64, no. 4, pp. 1359-1371, 2018.
[16]N. N. Kulkarni and V. K. Bairagi, “Extracting salient features for EEG-based diagnosis of Alzheimer's disease using support vector machine classifier,” IETE Journal of Research, vol. 63, no. 1, pp. 11-22, 2017.
[17]N. Sharma, M. H. Kolekar, K. Jha, and Y. Kumar, “EEG and cognitive biomarkers based mild cognitive impairment diagnosis,” IRBM, vol. 40, no. 2, pp. 113-121, 2019.
[18]C. Ieracitano, N. Mammone, A. Bramanti, A. Hussain, and F. C. Morabito, “A convolutional neural network approach for classification of dementia stages based on 2D-spectral representation of EEG recordings,” Neurocomputing, vol. 323, pp. 96-107, 2019.
[19]B. Güntekin, L. Hanoğlu, T. Aktürk, E. Fide, D. D. Emek‐Savaş, E. Ruşen, ... and G. G. Yener, “Impairment in recognition of emotional facial expressions in Alzheimer's disease is represented by EEG theta and alpha responses,” Psychophysiology, vol. 56, no. 11, e13434, 2019.
[20]F. M. Smits, C. Porcaro, C. Cottone, A. Cancelli, P. M. Rossini, and F. Tecchio, “Electroencephalographic fractal dimension in healthy ageing and Alzheimer’s disease,” PloS one, vol. 11, no. 2, e0149587, 2016.
[21]Y. H. Liu, S. Huang, and Y. D. Huang, “Motor imagery EEG classification for patients with amyotrophic lateral sclerosis using fractal dimension and Fisher’s criterion-based channel selection,” Sensore-Basel, vol. 17, no. 7, 2017.
[22]A. Delorme, S. Makeig, “EEGLAB: An Open Source Toolbox for Analysis of Single-Trial EEG Dynamics Including Independent Component Analysis,” J Neurosci Methods, vol. 134, iss. 1, pp. 9-12, 2004
[23]C. F. Tsai, W. J. Lee, S. J. Wang, B. C. Shia, Z. Nasreddine, and J. L. Fuh, “Psychometrics of the montreal cognitive assessment (MoCA) and its subscales: Validation of the taiwanese version of the MoCA and an item response theory analysis,” International Psychogeriatrics, vol. 24, no. 4, pp. 651-658, 2012.
[24]P. M. Rossini, M. Buscema, M. Capriotti, E. Grossi, G. Rodriguez, C. Del Percio, and C. Babiloni, “Is it possible to automatically distinguish resting EEG data of normal elderly vs. mild cognitive impairment subjects with high degree of accuracy?” Clinical Neurophysiology, vol. 119, no. 7, pp. 1534-1545, 2008.