進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-1408201317281600
論文名稱(中文) 基於多重立體像素技術及功能性核磁共振造影資料探討幸福和腦區的關係
論文名稱(英文) A Study on the Relationship between Happiness and Brain Regions Based on Multi-Voxel Pattern Analysis (MVPA) and fMRI Database
校院名稱 成功大學
系所名稱(中) 電機工程學系碩博士班
系所名稱(英) Department of Electrical Engineering
學年度 101
學期 2
出版年 102
研究生(中文) 謝承勳
研究生(英文) Cheng-Hsun Hsieh
學號 N26001466
學位類別 碩士
語文別 英文
論文頁數 53頁
口試委員 指導教授-王駿發
口試委員-龔俊嘉
口試委員-陳璽煌
口試委員-林博川
中文關鍵字 功能性核磁共振造影  多重立體像素辨識  血氧濃度相依對比  主成份分析  標準分數  變異數分析  交叉驗證  支援向量機 
英文關鍵字 Functional Magnetic Resonance Imaging  Multi-Voxel Pattern Analysis  Bold Oxygen Level Dependent  Principal Component Analysis  Standard Score  Analysis of Variance  Cross Validation  Support Vector Machine 
學科別分類
中文摘要 功能性核磁共振造影(Functional magnetic resonance imaging),除了廣泛的應用在醫學臨床檢測之外,近年來也常應用在情感認知領域。利用大腦的血氧濃度相依對比狀況(Blood oxygen-level dependent)進行受試者認知狀態的判別。這正是此論文主要利用特性,找出心靈上與幸福相關的腦區。
本論文提出了一個系統完成這項研究包含了下列不同的階段:資料的前處理、多重立體像素技術 (Multi-voxel pattern analysis)、特徵選取、特徵擷取、支援向量機的訓練階段以及交互認證的測試階段。資料的前處理階段裡,主要降低資料的雜訊,增加原本訊號的強度。接著利用多重立體像素技術將功能性核磁共振造影資料的維度進行轉換,從三維的立體像素轉成一維的向量藉此降低資料運算的複雜度。特徵選取的階段包含四個步驟: 腦區選取、基線位移校正、降低數據維度以及選取具有鑑別性的特徵。利用標準分數校正基線位移的問題。降低維度的階段裡,系統使用主成分分析消去冗餘的訊息。在特徵擷取的步驟裡,利用變異數分析根據不同條件下像素活化程度,擷取不同認知狀態下的特徵。根據所擷取到具有鑑別性的特徵,訓練其對應之支援向量機。最後測試的階段裡,利用交叉驗證收集與統計和幸福相關的腦區並且利用母愛資料庫進行系統的驗證。驗證的過程中,此研究所提出的系統可以從112個腦區中找出6個對於幸福具有較高關聯性的腦區,6個腦區中最高的平均辨識率可達到72.89%。
英文摘要 Functional magnetic resonance imaging (fMRI) has been not only commonly used to clinical trials for measuring the hemodynamic response of brain but also applied to the field of affective recognition in recent year. Based on the blood oxygen level dependent (BOLD), this work finds out the regions which are related with happiness. The proposed system includes these tasks: preprocess, multi-voxel pattern analysis (MVPA), feature selection, feature extraction, training phase with support vector machine (SVM), and testing phase with leave one out cross validation. Preprocess can handle the reduction of noises. MVPA transferred the fMRI data from 3D voxel to 1D vector in order to reduce complex of computation. The stage of feature selection includes four steps: brain region selection, run baseline correction, data dimension reduction, and differential row vector extraction. In brain region selection, there are 112 brain regions to decrease unnecessary information. Standard score is designed to eliminate the effect of baseline shift in step of baseline correction. For reducing the dimension of data, the system uses principal component analysis (PCA) to get the useful features in the stage of data dimension reduction. To increase the robust of data and extract the feature, choosing the features are estimated using analysis of variance (ANOVA). After the robust features are extracted, SVM is trained to detect the brain regions of different cognitive states based on the features. In testing phase, the leave one out cross validation is used to avoid the situation of over-fitting and calculating the accuracy of system. The experiments are carried out on Maternal-Love database and the proposed system can find out six brain regions of happiness from 112 brain regions. The brain region with the highest relation between happiness can achieve the average accuracy rate of 72.89%.
論文目次 中文摘要......I
英文摘要......III
誌謝......V
List of Tables......IX
List of Figures......X
CHAPTER 1 INTRODUCTION......1
1.1 BACKGROUND AND MOTIVATION......1
1.2 THESIS OBJECTIVE......3
1.3 THESIS ORGANIZATION......3
CHAPTER 2 RELATED WORKS......5
2.1 HISTORY OF FUNCTIONAL MAGNETIC RESONANCE IMAGING......5
2.2 TREND OF FUNCTIONAL MAGNETIC RESONANCE IMAGING......8
2.2.1 Degenerative Diseases of Brain: Alzheimer’s Disease......8
2.2.2 Attention Deficit Hyperactivity Disorder......11
2.2.3 Brain Regions Relative to Anxiety Disorder......13
2.2.4 Discriminate Cognitive Situations: Persistent Vegetative State......15
CHAPTER 3 MULTI-VOXEL PATTERN ANALYSIS WITH SUPPORT VECTOR MACHINE......19
3.1 SYSTEM OVERVIEW......19
3.2 DATA PREPROCESSING FOR REDUCING NOISES......23
3.2.1 Slice Time Correction......23
3.2.2 Motion Correction......25
3.2.3 Despike......26
3.2.4 Spatial Smoothing......27
3.2.5 Mean Normalization......27
3.3 MULTI-VOXEL PATTERN ANALYSIS......28
3.4 ELIMINATE REDUNDANT VOXEL METHOD FOR FEATURE EXTRACTION......30
3.4.1 Brain Region Selection......31
3.4.2 Baseline Correction......33
3.4.3 Dimension Reduction......34
3.4.4 Differential Row Vector Extraction......37
3.5 TRAINING PHASE AND TESTING PHASE......39
3.5.1 Training with Support Vector Machine......39
3.5.2 Testing with 10-Fold Cross Validation......42
CHAPTER 4 EXPERIMENTAL RESULTS......43
4.1 DATABASE: MATERNAL-LOVE DATABASE......43
4.2 EXPERIMENT ON MATERNAL-LOVE DATABASE FOR ESTIMATION OF HAPPINESS REGION......44
4.3 EXPERIMENT ON MATERNAL-LOVE DATABASE FOR HIGHER RELATION WITH HAPPINESS AND COMPARISON......47
CHAPTER 5 CONCLUSIONS AND FUTURE WORKS......50
REFERENCES......51
參考文獻 [1]J. W. Belliveau, D. N. Kennedy, R. C. McKinstry, B. R. Buchbinder, R. M. Weisskoff, M. S. Cohen, J. M. Vevea, T.J. Brady, and B.R. Rosen, “Functional mapping of the human visual cortex by magnetic resonance imaging,” Science, vol. 254, no. 5032, pp. 716-719, Nov. 1991.
[2]K. K. Kwong, J. W. Belliveau, D. A. Chesler, I. E. Goldberg, R. M. Weisskoff, B. P. Poncelet, D. N. Kennedy, B. E. Hoppel, M. S. Cohen, R. Turner, H. Cheng, T. J. Brady, and B. R. Rosen, “Dynamic Magnetic Resonance Imaging of Human Brain Activity During Primary Sensory Stimulation,” Neurobiology, vol. 89, pp. 5675-5679, June 1992.
[3]S. GAWA, D. W. TANK, R. MENON, J. M. ELLERMANN, S. G. KIM, H. MERKLE, and K. UGURBIL, “Intrinsic signal changes accompanying sensory stimulation: Functional brain mapping with magnetic resonance imaging,” Neurobiology, vol. 89, pp. 5951-5955, July 1992.
[4]L. Nygård, “Instrumental activities of daily living: a stepping-stone towards Alzheimer's disease diagnosis in subjects with mild cognitive impairment,” Acta Neurol Scand, 2003
[5]H. Förstl, A. Kurz, “Clinical features of Alzheimer's disease,” European Archives of Psychiatry and Clinical Neuroscience, 1999
[6]L. Ferrarini, W. M. Palm, H. Olofsen, R. van der Landen, M.A. van Buchem, J. H. C. Reiber, and F. AdmiraalBehloul, “Ventricular shape biomarkers for Alzheimer’s disease in clinical MR images,” Magnetic Resonance in Medicine, vol. 59, pp. 260–267, 2008
[7]D. P. Devanand, G. Pradhaban, X. Liu, A. Khandji, S. DeSanti, S. Segal, H. Rusinek, and G.H. Pelton et al., “Hippocampal and entorhinal atrophy in mild cognitive impairment: Prediction of Alzheimer’s disease,” Neurology, vol. 68, pp. 828–836, 2007.
[8]B. Hesslinger, L. Tebartz van Elst, T. Thiel, K. Haegele, J. Hennig, and D. Ebert, “Frontoorbital volume reductions in adult patients with attention deficit hyperactivity disorder,” Neuroscience, pp. 319–321, 2002.
[9]L. J. Seidman, E. M. Valera, and N. Makris et al, “Dorsolateral prefrontal and anterior cingulate cortex volumetric abnormalities in adults with attention-deficit/hyperactivity disorder identified by magnetic resonance imaging,” Society of Biological Psychiatry, pp. 1071–1080, 2006.
[10]S. H. Mostofsky, S. L. Rimrodt, G. B. S. Joanna, B. Avery, M. C. Goldberg, J. P. James, and M. B. Denckla, “Atypical Motor and Sensory Cortex Activation in Attention-Deficit/Hyperactivity Disorder: A Functional Magnetic Resonance Imaging Study of Simple Sequential Finger Tapping,” Society of Biological Psychiatry, 2005.
[11]A. J. Holmes and D. A. Pizzagalli, “Spatio-temporal dynamics of error processing dysfunctions in MDD,” Arch. Gen. Psychiatry, vol. 65, pp. 179-188, 2008.
[12]K. J. Ressler and H. S. Mayberg, “Targeting abnormal neural circuits in mood and anxiety disorders: from the laboratory to the clinic,” Nature Neuroscience, vol. 10, pp. 1116-1124, Sep. 2007
[13]A. Etkin and T. D. Wager, “Functional Neuroimaging of Anxiety: A Meta-Analysis of Emotional Processing in PTSD, Social Anxiety Disorder, and Specific Phobia,” Am. J. Psychiatry, vol. 164, pp. 1476-1488, Oct. 2007.
[14]L. M. Shin et al., “Regional Cerebral Blood Flow in the Amygdala and Medial Prefrontal Cortex during Traumatic Imagery in Male and Female Vietnam Veterans with PTSD,” Arch. Gen. Psychiatry, vol. 61, pp. 168-176, Feb. 2004.
[15]C. Fales et al., “Altered emotional interference processing in affective and cognitive-control brain circuitry in major depression,” Biol.Psychiatry, pp. 377-384, Feb. 2008.
[16]A. M. Owen, M. R. Coleman, M. Boly, M. H. Davis, S. Laureys, and J. D. Pickard, “Detecting Awareness in the Vegetative State,” Science, vol. 313, Sep. 2006.
[17]M. M. Monti, M. R. Coleman, M. Boly, and J. D. Pickard et al. “Willful Modulation of Brain Activity in Disorders of Consciousness,” The New England Journal of Medicine, vol. 362, no.7, Feb 2010.
[18]S. P. MacEvoy, and R. A. Epstein, “Decoding the Representation of Multiple Simultaneous Objects in Human Occipitotemporal Cortex,” Current Biology, vol. 19, no. 11, pp. 943-947, Jun. 2009.
[19]Y. Miyawaki, H. Uchida, O. Yamashita, M. Sato, Y. Morito, H. C. Tanabe, N. Sadato, and Y. Kamitani, “Visual image reconstruction from human brain activity using a combination of multi scale local image decoders,” Neuron, Nov. 2008.
[20]C. C. Kung, and D. R. Yeh, “The neural substrates of maternal love in shopping: Mother's willingness to pay for her child vs. for herself - an fMRI study”
[21]J. P. Loberbaum, J. D. Newman, J. R. Duhno, A. R. Horwitz, Z. Nahas, C. C. Teneback, “Feasibility ofusing fMRI to study mothers responding to infant cries” Depression Anxiety, July 1999.
[22]A. Bartel, and S. Zeki, “The meural correlates of maternal and romantic love,” Neuroimage, 2004.
[23]J. E. Swain, E. Tasgin, L. C. Mayes, R. Feldman, R. T. Constable, and J. F. Leckman, “Maternal brain response to own baby-cry is affected by cesarean section delivery,” Journal of Child Psychology and Psychiatry, pp. 1042-1052, 2008
[24]M. Noriuchi, Y. Kikuchi, and A. Senoo, “The functional neuroanatomy of maternal love: mother's respose to infant's attachment behaviors,” Biol. Psychiatry, 2008.
[25]http://culhamlab.ssc.uwo.ca/fmri4newbies/
[26]http://www.ijbem.org/volume6/number2/001.htm
[27]http://www.fmrib.ox.ac.uk/research/introduction-to-fmri/find-out-more/a-brief-introduction-to-fmri-physiology
[28]http://neurosciencenews.com/diagnostic-biomarkers-for-alzheimers-disease/
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2023-01-01起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw