跳到主要內容

臺灣博碩士論文加值系統

(44.200.94.150) 您好!臺灣時間:2024/10/12 02:47
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:紀鈞凱
研究生(外文):Chun-Kai Chi
論文名稱:應用機器學習方法用於生物醫學訊號輔助診斷:以寫字型手部痙攣症為例
論文名稱(外文):Apply machine learning methods to aid in the diagnosis of Task-Specific Focal Hand Dystonia
指導教授:陳純娟陳純娟引用關係
指導教授(外文):Chun-Chuan Chen
學位類別:碩士
校院名稱:國立中央大學
系所名稱:生醫科學與工程學系
學門:工程學門
學類:生醫工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:139
中文關鍵詞:寫字型手部痙攣症初級運動皮質區前運動皮質區輔助運動皮質區輔助診斷系統
外文關鍵詞:Writer’s crampDynamic causal modelSupporting diagnosis system
相關次數:
  • 被引用被引用:0
  • 點閱點閱:189
  • 評分評分:
  • 下載下載:3
  • 收藏至我的研究室書目清單書目收藏:1
肌張力不全障礙(Dystonia)是一種自發性的運動障礙疾病,它泛指一群肌肉不自主的過度收縮,由於拮抗肌持續或斷斷續續地不正常收縮導致拮抗肌與收縮肌同時進行收縮的現象。其基本特徵是運動所需的肌肉過度活動。在臨床方面,由於後天性肌張力不全障礙患者的主要致病機轉尚未被完全了解,因此在診斷上只能依賴醫師的經驗來判斷。因此本研究的目的希望能夠藉由機器學習方法,建置一個客觀的寫字型手部痙攣症電腦輔助診斷系統。
本研究收集的對象為寫字型手部痙攣症(Writer’s Cramp)患者12名與正常受試者14名,進行15分鐘內自行數8秒手腕伸展(Wrist extension)的運動,並收集此運動時的腦波訊號(Electroencephalography, EEG)。利用動態因果模型(Dynamic Causal Modeling,DCM)分析患者與正常人運動神經網路連結,並以監督機器學習的方法,將病人與正常人的運動神經網路連結進行分析並找出差異,用以建立電腦輔助診斷系統。
研究結果顯示,在運動開始之前,病人在五個腦區(LM1、LPM、SMA、RM1、RPM)上的Theta頻帶以及三個腦區(LPM、RM1、RPM)上的Alpha頻帶的強度皆明顯小於正常人。而在運動開始之後,患者在Theta頻帶上四個腦區(LM1、LPM、RM1、RPM)) 強度顯大於正常人。另外在Beta頻帶上兩個腦區(RM1、RPM)強度明顯小於正常人。在大腦功能連結的部分,我們的研究結果發現寫病人與正常人之間共有3條連結在統計上有顯著差異,其中輔助運動皮質區有2條異常的連結為較重要的腦區。在輔助診斷系統的部分,我們討論了Theta頻帶改變對診斷系統的影響,我們將Theta頻帶從4-8Hz改為Low Frequency(4-12Hz),可以看到在4-8Hz的情況下,分類方法為SVM及NaiveBayes演算法便可得到較高的準確率,分別為89.4%及89.8%。若將頻帶改為Low Frequency(4-12Hz),準確率較高的演算法為SVM、Logistic regression、NaiveBayesn三種,準確率分別為90.99%、90.42%、90.55%。在頻帶組合方面,可以看到在準確率較高的演算法中,Theta頻帶皆包含在最佳組合中,表示在輔助診斷系統中,Theta頻帶被認為是較為重要頻帶。此外,根據我們輔助診斷系統所分析的重要特徵連結也發現,與患側前運動皮質區及輔助運動皮質區被認為是重要腦區,與我們統計出來的結果大致相符。未來希望我們所收的受測者人數可以更多,以避免產生Over Fitting的現象,進而影響輔助診斷的準確率。未來也可以增加更多不同的演算法來找出哪個演算法更適合我們的研究。
Dystonia is a spontaneous neurological movement disorder, which refers to a group of muscles with involuntary excessive contraction. Its basic feature is excessive muscle activity required for exercise. In clinical terms, the main pathogenesis of patients with acquired dystonia is not fully understood, so the diagnosis can only rely on the experience of the physician to diagnose. Therefore, the purpose of this research is to build an objective computer diagnosis system for task-specific focal hand dystonia by machine learning.
In this study, 12 patients with Writer's Cramp and 14 normal subjects were collected. They performed a wrist extension of 8 seconds for 15 minutes, and collect electroencephalography (EEG) signals at this time. Use dynamic causal modeling (DCM) to analyze the connection between patients and normal people's motor neural network, and use the method of supervised machine learning to analyze the connection between patients and normal people's motor neural network and find out the differences, establish a computer diagnosis system.
The results of the study showed that before the start of exercise, the power of the Theta band on the five brain regions (LM1, LPM, SMA, RM1, RPM) and the Alpha band on the three brain regions (LPM, RM1, RPM) were significantly less than normal peoele. After the start of exercise, the power of the Theta band on the four brain regions (LM1, LPM, RM1, RPM) and the Beta band on the two brain regions (RM1, RPM) were significantly greater than normal people. In the part of brain functional connections, our research results found that there are 3 abnormal connections in patients, of which Two of them are connection with reduced excitement , and one is a connection with a changed connection mechanism. The strength of these three connections is lower than normal people, which means that the increase of connection inhibition is very important for patients to perform specific tasks. Among them, there are two abnormal connections in the supplementary motor area as more important brain areas. In the part of the supporting diagnosis system, we discussed the impact of the change of Theta frequency band on the diagnosis system. We changed the Theta frequency band from 4-8Hz to Low Frequency (4-12Hz). It can be seen that in the case of 4-8Hz, the classification method is SVM and naivebayes algorithm can get higher accuracy, which are 89.4% and 89.8%, respectively. If the frequency band is changed to Low Frequency (4-12Hz), the algorithms with higher accuracy are SVM, Logistic regression, and naivebayes. The accuracy is 90.99%, 90.42%, and 90.55%. In terms of frequency band combination,we can see that in algorithms with higher accuracy, Theta band is included in the best combination, indicating that in our supporting diagnosis system, the Theta band is more able to distinguish between patients and normal people. The important frequency band of the difference. In addition, according to the important characteristic connections analyzed by our supporting diagnostic system, we also found that the connections related to the premotor cortex area and supplementary motor cortex area on the affected side are indeed considered to be used to determine whether it is an important brain area of the patient or normal, Roughly consistent with the results we have calculated. In the future, we hope that the number of subjects we receive can be greater to avoid the phenomenon of over fitting, which will affect the accuracy of auxiliary diagnosis. In the future, more different algorithms can be added to test which algorithm is more suitable for our research.
目錄
摘要 i
Abstract iii
圖目錄 vii
表目錄 viii
第一章 緒論 1
1-1研究背景與動機 1
1-2研究目標 2
第二章 文獻回顧 3
2-1肌張力不全障礙 3
2-1-1肌張力不全障礙定義與分類 4
2-1-2肌張力不全障礙診斷 6
2-1-3肌張力不全障礙治療 7
2-2肌張力不全障礙異常 9
2-2-1基底神經結異常 9
2-2-2運動皮質區異常 10
2-2-3腦區連結網路異常 12
2-3動態因果模型 13
2-3-1功能性連結與有效性連結 13
2-3-2誘發響應的動態因果模型 15
2-3-3線性/非線性效應 17
2-4機器學習 19
2-4-1機器學習方法 19
2-4-2機器學習平台:WEKA 20
第三章 研究方法 21
3-1收案來源 21
3-2運動試驗 21
3-3資料處理 22
3-3-1資料前處理 24
3-3-2動態因果模型 26
3-3-3大腦連結模型分析 28
3-4 ERS分析: 30
3-5診斷系統建立 32
3-5-1分類器 33
3-5-2特徵選取 37
第四章 研究結果 40
4-1 受試者行為資料結果 40
4-2 C3/C4上ERSP結果 41
4-2-1 ANOVA分析: 41
4-3 Source腦區分析 44
4-3-1 ANOVA分析: 44
4-4 動態因果模型 69
4-4-1 大腦模型選擇 69
4-4-2 大腦模型BMS 分析 72
4-5 病人與正常人大腦連結圖表分析 73
4-5-1病人與正常人大腦連結圖 74
4-5-2手部痙攣症患者大腦連結異常之單變數統計分析 75
4-5-3寫字型手部痙攣症患者大腦連結異常之多變數統計分析 77
第五章 討論 84
5-1 寫字型手部痙攣症患者與正常人相同處討論 84
5-1-1 受試者行為資料結果 84
5-1-2 Sensor上頻帶強度討論 85
5-2 寫字型手部痙攣症患者與正常人頻帶強度討論 86
5-3 寫字型手部痙攣症患者與正常人腦區連結討論 88
5-4 判斷準確率討論 91
第六章 結論與未來展望 93
6-1 結論 93
6-2 未來展望 94
第七章 參考文獻 95
附件 98
1. H. A. Jinnah, M.D., Ph.D., Diagnosis & Treatment of Dystonia. Neurologic Clinics, 2015. 33(1): p. 77–100.
2. Mark Hallett, M., The Neurophysiology of Dystonia. Arch Neurol, 1998. 55(5): p. 601-603.
3. Lin, P.T. and M. Hallett, The pathophysiology of focal hand dystonia. Journal of Hand Therapy, 2009. 22(2): p. 109–114.
4. Murase, N., et al., Subthreshold low-frequency repetitive transcranial magnetic stimulation over the premotor cortex modulates writer's cramp. Brain, 2005. 128(Pt 1): p. 104-15.
5. Hamada, I., M.R. DeLong, and N. Mano, Activity of identified wrist-related pallidal neurons during step and ramp wrist movements in the monkey. J Neurophysiol, 1990. 64(6): p. 1892-906.
6. Tseng, Y.-J., et al., Reduced Motor Cortex Deactivation in Individuals Who Suffer from Writer’s Cramp. PLoS ONE, 2014. 9(5): p. 1-6.
7. Chen, C., S.J. Kiebel, and K.J. Friston, Dynamic causal modelling of induced responses. Neuroimage, 2008. 41(4): p. 1293-1312.
8. Friston, K.J., Functional and effective connectivity in neuroimaging: a synthesis. Human brain mapping, 1994. 2(1-2): p. 56-78.
9. Aertsen, A. and H. Preissl, Dynamics of activity and connectivity in physiological neuronal networks. Nonlinear dynamics and neuronal networks, 1991. 2: p. 281-301.
10. Andrew, C. and G. Pfurtscheller, Event-related coherence as a tool for studying dynamic interaction of brain regions. Electroencephalography and clinical neurophysiology, 1996. 98(2): p. 144-148.
11. Chen, C.-C., et al., Nonlinear coupling in the human motor system. The Journal of Neuroscience, 2010. 30(25): p. 8393-8399.
12. Pfurtscheller, G. and F.H.L.d. Silva, Event-related EEG/MEG synchronization and desynchronization: basic principles. Clinical Neurophysiology, 1999. 110(5): p. 1842-857.
13. Schölkopf, B., et al., New support vector algorithms. Neural computation, 2000. 12(5): p. 1207-1245.
14. Le Cessie, S. and J. Van Houwelingen, Ridge estimators in logistic regression. Applied statistics, 1992: p. 191-201.
15. Quinlan, J.R., C4. 5: programs for machine learning. Vol. 1. 1993: Morgan kaufmann.
16. Quinlan, J.R., Improved use of continuous attributes in C4. 5. arXiv preprint cs/9603103, 1996.
17. John, G.H. and P. Langley. Estimating continuous distributions in Bayesian classifiers. in Proceedings of the Eleventh conference on Uncertainty in artificial intelligence. 1995. Morgan Kaufmann Publishers Inc.
18. Hall, M.A. and G. Holmes, Benchmarking attribute selection techniques for discrete class data mining. Knowledge and Data Engineering, IEEE Transactions on, 2003. 15(6): p. 1437-1447.
19. Kohavi, R. and G.H. John, Wrappers for feature subset selection. Artificial intelligence, 1997. 97(1): p. 273-324.
20. Braun, C., et al., Task-specific plasticity of somatosensory cortex in patients with writer’s cramp. NeuroImage, 2003. 20: p. 1329-1338.
21. Cote, S.L., et al., Contrasting Modulatory Effects from the Dorsal and Ventral Premotor Cortex on Primary Motor Cortex Outputs. J Neurosci, 2017. 37(24): p. 5960-5973.
22. Ruiz, M.H., et al., EEG oscillatory patterns are associated with error prediction during music performance and are altered in musician's dystonia. Neuroimage, 2011. 55(4): p. 1791-803.
23. Ikeda, A., [Human supplementary motor area: a role in voluntary movements and its clinical significance]. Rinsho Shinkeigaku, 2007. 47(11): p. 723-6.
24. S. B. Kotsiantis , Supervised Machine Learning: A Review of Classification Techniques, Department of Computer Science & Technology, University of Peloponnese, Greece, sotos@math.upatras.gr
25. Trilok Chand Sharma, Manoj Jain , WEKA Approach for Comparative Study of Classification Algorithm,, Department Of Technical Education , Haryana, (M.Tech. Computer Science& Engg., Lingaya‟s University Faridabad)1 Associate. Professor (Computer Sc. & Engg.), Lingaya‟s University Faridabad2, International Journal of Advanced Research in Computer and Communication Engineering Vol. 2, Issue 4, April 2013
26. Pfurtscheller, G. and F.H. Lopes da Silva, Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin Neurophysiol, 1999. 110(11): p. 1842-57.
27. Mark F. Bear, Neuroscience: Exploring the Brain, 2nd Edition
28. Cohen, L.G. and M. Hallett, Hand cramps: clinical features and electromyographic patterns in a focal dystonia. Neurology, 1988. 38(7): p. 1005-12.
29. Neumann, W.J., et al., Cortico-pallidal oscillatory connectivity in patients with dystonia. Brain, 2015. 138(Pt 7): p. 1894-906.
30. Beck, S., et al., Short intracortical and surround inhibition are selectively reduced during movement initiation in focal hand dystonia. J Neurosci, 2008. 28(41): p. 10363-9.
31. Delnooz, C.C., et al., Writer's cramp: increased dorsal premotor activity during intended writing. Hum Brain Mapp, 2013. 34(3): p. 613-25.
32. Siebner, H.R., et al., Low-frequency repetitive transcranial magnetic stimulation of the motor cortex in writer's cramp. Neurology, 1999. 52(3): p. 529-37.
33. Kimberley, T.J., et al., Multiple sessions of low-frequency repetitive transcranial magnetic stimulation in focal hand dystonia: clinical and physiological effects. Restor Neurol Neurosci, 2013. 31(5): p. 533-42.
34. Hallett, M., Pathophysiology of writer’s cramp. Human Movement Science, 2006. Volume 25(Issues 4–5): p. 454-463.
35. Jakob Jankowski et al. Abnormal Movement Preparation in Task-SpeciÕc Focal Hand Dystonia . PLoS ONE 8(10): e78234.

35. Inken Rothkirch et al, Dynamic causal modeling revealed dysfunctional effective connectivity in both, the cortico-basal-ganglia and the cerebello-cortical motor network in writers' cramp, Neuroimage Clin. 2018; 18: 149–159.
36. Ewgenia Barow, Wolf-Julian Neumann et al, Deep brain stimulation suppresses pallidal low frequency activity in patients with phasic dystonic movements, Brain. 2014 Nov; 137(Pt 11): 3012–3024.
37. Leighton B. N. Hinkley et al, Aberrant oscillatory activity during simple movement in task-specific focal hand dystonia, Front Neurol. 2012 Nov 28;3:165. doi: 10.3389/fneur.2012.00165. eCollection 2012.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top