(3.236.222.124) 您好!臺灣時間:2021/05/11 08:38
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:::

我願授權國圖
: 
twitterline
研究生:吳振豪
研究生(外文):Chen-Hao
論文名稱:運用獨立成份分析及支援向量分類器技術定量分析腦部容積的初步結果
論文名稱(外文):Independent Component analysis and Support Vector Classifier Machine for Brain volume analysis
指導教授:田雨生副教授
學位類別:碩士
校院名稱:中山醫學大學
系所名稱:醫學研究所
學門:醫藥衛生學門
學類:醫學學類
論文種類:學術論文
論文出版年:2008
畢業學年度:96
語文別:中文
論文頁數:96
相關次數:
  • 被引用被引用:0
  • 點閱點閱:75
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
目的: 本研究旨在希望藉由獨立成份分析法(Independent Component Analysis, ICA)結合支援向量分類器(Support Vector Classifier Machine, SVCM)演算法,在不增加額外的檢查影像下,就能有效且準確的分析腦部容積,並提供醫師診斷上之鑑定與分別。

背景: 雖然醫學影像統計分析軟體(Statistical Parametric Mapping, SPM)是國際標準之腦部影像處理軟體。但是,在計算前,我們必須加做這個軟體所接受的 T1-weighted 3D MP-range 影像。因此,若沒有在檢查前就先決定加做這組影像,就沒有辦法在檢查後計算腦容積。然而獨立成份分析法具有增強腦部磁振造影結構的特色,而支援向量分類器則是能達成腦部磁振造影結構組織分割,這兩種演算法之結合將有助於發展電腦腦部磁振造影結構組織容量量化模式。在取影像上,這兩種演算法只需由磁振造影掃描儀取得橫斷切面的T1、T2、和proton density的腦部影像,再將所得影像經由PACS影像傳輸系統送至個人電腦,即可後處理其影像,並計算出腦容積。藉此將可省去SPM軟體需要加做影像的時間。

材料與方法: 本研究將收集14位50歲以下及16位50歲以上正常人之磁振造影掃描,取得橫斷切面的T1,T2,和proton density的腦部影像後,再經由獨立成份分析法及支援向量分類器將腦部磁振造影中分割出脊髓液(Cerebrospinal Fluid, CSF)、灰質(Gray Matter, GM)與白質(White Matter, WM),藉此測量腦部灰、白質組織容積之定量分析。同時本研究仍然加做SPM軟體所需要的T1-weighted 3D MP-range 影像,並計算其腦容積,做為對照組。以此為依據,進行驗證本系統演算法之準確性及可重複性。

結果: 本研究發現,獨立成份分析演算法與支援向量分類器結合後,可提供一個更準確且有效的腦部不同組織切割與容積定量量測。與國際標準之腦部影像處理軟體或過去文獻利用不同方法定量腦部灰、白質方式比較,本研究對腦部灰、白質組織定量之結果與國際標準軟體所算出的結果有很高的相關性。


結論與建議:本系統在計算數據方面與 SPM 所計算出的數據有著相當高的相關性。在量測程序及方式部分,本系統則相當簡單及客觀,不但可不用多花SPM量測所需的時間,且也不需檢查前就計畫好要加做其專有的影像。綜觀以上幾點之比較,可發現本研究的獨立成份分析法及支援向量分類器這兩種演算法,的確提供了一個有效、準確及方便的腦容量量測系統。


Purpose: This research aimed to combine a support vector classifier machine with independent component analysis, without additional image, to effectively and accurately evaluate brain volume. This way, we could obtain more information for diagnosis.

Background: Previously we have dealt with software in brain imaging in which Statistical Parametric Mapping is the international standard. However, before calculations, we must add and perform T1-weighted 3D MP-range images so this software can be accepted. So, without adding or running these prerequisite images before the study, we could not calculate brain volume. Independent component analysis strengthened the characteristic structure of brain magnetic resonance images, and the support vector classifier machine can segment the brain image. This combination performed the algorithm to facilitate developing quantization of brain volume. In taking the image, these two algorithms only needed the magnetic resonance axial T1, T2, and proton density images, and are then transmitted via PACS image system to PC, where we calculate brain volume. This saves time on images which SPM software requires.

Material and method: 14 patients under the age of 50 and above 16 were enrolled in this study. After obtaining T1, T2, and proton density images, the independent component analysis and support vector classifier machine segmented cerebrospinal fluid, gray matter and white matter, and did a quantitative analysis of the volume of gray and white matter in the brain. This research still added T1-weighted 3D MP-range images required in SPM software. The volume of brain was also calculated, as in the control group to verify algorithm accuracy and repeatability.

Result: This study discovered independent component analysis and a support vector classifier machine algorithm that could offer accurate and effective histological segmentation and volume quantification of the brain. Dealing with internationally standard software or literature has, in the past, utilized different methods for quantifying brain volume; the quantitative results of this research had a very high correlation in comparison with the international standard.

Conclusion: The data that this system calculated with SPM has high relevance. The examination procedure and way of quantifying was simple and objective. It does not require spending the time examining SPM, and does not assign additional images before magnetic resonance images are performed. Taking a broad view of the above-mentioned comparison, we find this research, an independent component analysis and support vector classifier machine, offers an effective, accurate and convenient way for brain volume analysis.


摘 要 I
Abstract II
誌 謝 III
目 錄 IV
圖 索 引 V
表 索 引 VI
第一章 緒論 1
1-1 前言 1
1-2 研究背景 5
1-3 國內外研究情形 9
1-4 研究目的 15
第二章 研究設計過程與理論基礎 16
2-1 研究設計過程 16
2-2 理論基礎 19
2-2-1 獨立成份分析法 19
2-2-2 支援向量器 27
2-3 醫學影像統計分析軟體 33
2-3-1 SPM之概述 33
2-3-2 SPM之功能 35
2-3-3 SPM使用簡介 35
第三章 材料與方法 38
3-1 模擬腦部MR影像 38
3-2 實際腦部MR影像 40
3-3 研究流程及方法42
3-4 SPM5 的操作流程與腦容量計算 50
3-5 驗證腦容積計算的可靠性的統計方法 62
3-5-1 線性關係的分析原理 62
3-5-2 線性關係與相關 63
3-5-3 迴歸可解釋變異量比 64
3-5-4 簡單直線回歸Simple Linear Regression 67
第四章 結果與討論 68
4-1 ICA結合SVCM計算出模擬腦部影像的結果 68
4-2 ICA結合SVCM計算出實際腦部容積的結果 70
4-3 以SPM計算出實際腦部容積的結果 74
4-4 分析驗證腦容積計算結果 77
4-5 討論驗證的結果 83
第五章 結論及未來展望 85
5-1 結論 85
5-2 研究之貢獻 88
5-3 未來展望 89
參考文獻 90
作者自述 96


1.http://sowf.moi.gov.tw/17/94/index.htm
2.Geldmacher DS, Whitehouse PJ. “Evaluation of dementia,” N Engl J Med, 335:330-336, 1996.
3.Dobbs, A. R., & Rule, B. G. “Adult age differences in working memory,” Psychology and Aging, 4:500-503, 1990.
4.Hultsch, D. F. “Adult age differences in free classification and free recall,” Developmental Psychology, 4: 338-342, 1971.
5.Plude, D. J., & Hoyer, W. J. “Adult age differences in visual search as a function of stimulus mapping and processing load,” J. Gerontol., 36: 598-604, 1981.
6.Schonfield, A. D. E., & Robertson, B. “A. Memory storage and aging. Can,” J. Psychol., 20:228-236, 1966.
7.Blatter DD, Bigler ED, Gale SD, et al. “Quantitative volumetric analysis of brain MR: normative database spanning 5 decades of life,” Am J Neuroradiol 16: 241-51, 1995.
8.Ge Y, Grossman RI, Babb JS, Rabin ML, Mannon LJ, Kolson DL. “Age-related total gray matter and white matter changes in normal adult brain. Part II: quantitative magnetization transfer ratio histogram analysis,” Am J Neuroradiol 23: 1334-41, 2002.
9.Pfefferbaum A, Mathalon DH, Sullivan EV, Rawles JM, Zipursky RB, Lim KO. “A quantitative magnetic resonance imaging study of changes in brain morphology from infancy to late adulthood,” Arch Neurol 51: 874-87, 1994.
10.Good CD, Johnsrude IS, Ashburner J, Henson RN, Friston KJ, Frackowiak RS. “A voxel-based morphometric study of ageing in 465 normal adult human brains,” Neuroimage 14: 21-36, 2001.
11.Jernigan TL, Archibald SL, Fennema-Notestine C, et al. “Effects of age on tissues and regions of the cerebrum and cerebellum,” Neurobiol Aging 22: 581-94, 2001.
12.Guttmann CR, Jolesz FA, Kikinis R, et al. “White matter changes with normal aging,” Neurology 50: 972-8, 1998.
13.Clarke, L.P., Velthuizen, R.P, Camacho, M.A., Heine, J.J., Vaidyanathan, M., Hall, L.O., Thatcher, R.W., Silbiger, M.L., “MRI segmentation: methods and applications,” Magnetic Resonance Imaging, 13(3):343-368, 1995.
14.Lange, N., Strother, S. C., Anderson, J. R., Nielsen, F. A., Holmes, A. P., Kolenda, T., Savoy, R., Hansen, L. K., “Plurality and resemblance in fMRI data analysis,” NeuroImage, 10:282–203, 1999.
15.Kobashi, S., Kamiura, N., Hata, Y., Miyawaki F., “Volume-quantization-based neural network approach to 3D MR angiography image segmentation,” Image and Vision Computing, 19:185–193, 2001.
16.Hubbard BM, Anderson JM. “A quantitative study of cerebral atrophy in old age and senile dementia,” Journal of the Neurological Sciences, 50:135– 45, 1981.
17.Dekaban AS, Sadowsky D. “Changes in brain weights during the span of human life: relation of brain weights to body heights and body weights,” Ann Neurol, 4:345–56, 1978.
18.Willerman, L., Loehlin, J.C., Horn, J.M.. “A 10-year follow-up of adoptees whose biological mothers had differed greatly in IQ,” Behav. Genet. 20 (6), 754, 1990.
19.Yeo, R.A., Turkheimer, E., Raz, N., Bigler, E.D. “Volumetric asymmetries of the human-brain-intellectual correlates,” Brain Cogn. 6 (1), 15– 23, 1987.
20.Bomans, M., Hohne, K.H., Tiede, U., Riemer, M. “3-D segmentation of MR images of the head for 3-D display,” IEEE Trans. Med. Imaging 9: 177-183, 1990.
21.Suzuki, H., Toriwaki, J.-I. “Automatic segmentation of head MRI images by knowledge guided thresholding,” Comput. Med. Imaging Graph. 15:233-240, 1991.
22.Bezdek, J.C., Hall, L.O., Clarke, L.P. “Review of MR image segmentation techniques using pattern recognition,” Med. Phys. 20: 1033-1048, 1993.
23.Clarke, L.P., Velthuizen, R.P., Phuphanich, S., Schellenberg, J.D., Arrington, J.A., Silbiger, M. “MRI: Stability of three supervised segmentation techniques,” Magn. Reson. Imaging 11: 95-106, 1993.
24.Kohn, M.I., Tanna, N.K., Herman, G.T., Resnick, S.M., Mozley, P.D., Gur, R.E., Alavi, A., Zimmerman, R.A., Gur, R.C. “Analysis of brain and cerebrospinal fluid volumes with MR imaging – Part I. Methods, reliability, and validation,” Radiology 178: 115-122, 1991.
25.Peck, D.J., Windham, J.P., Soltanian-Zadeh, H., Roebuck, J.R. “A fast and accurate algorithm for volume determination in MRI,” Med. Phys. 19:599-605, 1992.
26.Gerig, G., Martin, J., Kikinis, R., Kubler, O., Shenton, M., Jolesz, F.A., “Unsupervised tissue type segmentation of 3D dual-echo MR head data,” Image Vision Comput. 10: 349-360, 1992.
27.Brandt, M.E., Bohan, T.P., Kramer, L.A., Fletcher, J.M. “Estimation of CSF, white and gray matter volumes in hydrocephalic children using fuzzy clustering of MR images,” Comput. Med. Imaging Graph. 18: 25-34, 1994.
28.Hyvarinen, A., Karhunen, J., and Oja, E. Independent Component Analysis, John Wiley & Sons, 2001.
29.Kao, Y.H., Guo, W.Y., Wu, Y.T., Liu, K.C., Chai, W.Y., Lin, C.Y., Hwang, Y.H., Liou, A.J.K., Wu, H.M., Cheng, H.C., Yeh, T.C., Hsieh, J.C., and Teng, M.M.H. “Hemodynamic Segmentation of MR Brain Perfusion Images Using Independent Component Analysis, Thresholding, and Bayesian Estimation,” Magnetic Resonance in Medicine, 49:885–894, 2003
30.McKeown, M.J., Makeig, S., Brown, G.G., Jung, T.P., Kindermann, S.S., Bell, A.J., Sejnowski, T.J., “Analysis of fMRI data by blind separation into independent spatial component,” Hum. Brain Mapp., 6: 160-188, 1998.
31.Calhoun, V.D., Adalı, T., Pearlson, G.D., Zijl, P.C.M., and Pekar, J.J. “Independent Component Analysis of fMRI Data in the Complex Domain,” Magnetic Resonance in Medicine, 48:180–192, 2002.
32.Vince D. Calhoun, Tulay AdalV, James J. Pekar, “A method for comparing group fMRI data using independent component analysis: application to visual, motor and visuomotor tasks,” Magnetic Resonance Imaging, 22: 1181–1191, 2004.
33.Vigario, R., Sarela, J., Jousmaki, V., Hamalainen, M., and Oja, E. “Independent component approach to the analysis of EEG and MEG recordings,” IEEE Trans. Biomed. Eng., 47: 589– 593, 2000.
34.Jung, T.P., Makeig, S., Stensmo, M., Sejnowski, T.J. “Estimating alertness from the EEG power spectrum,” IEEE Trans. Biomed. Eng., 44: 60– 66, 1997.
35.Vapnik, V. The Nature of Statistical Learning Theory. Springer, N.Y., 1995.
36.Kim, K. I., Jung, K., Park, S. H., and Kim. H. J. “Support Vector Machines for Texture Classification,” IEEE Trans. Pattern Anal. Mach. Intell., 24: 1542-1550, 2002.
37.Tefas, A., Kotropoulos, C., and Pitas, I. “Using Support Vector Machines to Enhance the Performance of Elastic Graph Matching for Frontal Face Authentication,” IEEE Trans. Pattern Anal. Mach. Intell., 23: 735-746, 2001.
38.Wei, L., Yang, Y., Nishikawa, R. M., and Jiang, Y. “A Study on Several Machine-Learning Methods for Classification of Malignant and Benign Clustered Microcalcifications,” IEEE Trans. Medical Imaging, 24(3): 371-380, 2005.
39.Miranda, J. M., Bokde, A. L.W., Born, C., Hampel, H., and Stetter, M. “Classifying brain states and determining the discriminating activation patterns: Support Vector Machine on functional MRI data,” NeuroImage 28: 980 – 995, 2005.
40.Lao, Z., Shen, D., Xue, Z., Karacali, B., Resnick, S. M., and Davatzikos, C. “Morphological classification of brains via high-dimensional shape transformations and machine learning methods,” NeuroImage 21: 46– 57, 2004.
41.Güler, İ., Übeyli, E. D. “Multiclass Support Vector Machines for EEG Signals Classification,” IEEE Transactions on Information Technology in Biomedicine, Accepted for future publication, 2006.
42.http://www.bic.mni.mcgill.ca/brainweb
43.Nakai, T., Muraki, S., Bagarinao, E., Miki, Y., Takehara, Y., Matsuo, K., Kato, C., Sakahara, H., and Isoda, H. “Application of independent component analysis to magnetic resonance imaging for enhancing the contrast of gray and white matter,” NeuroImage, 21: 251–260, 2004.
44.Hyvarinen, A., and Oja, E. “A fast fixed-point for independent component analysis,” Neural Computation, 9(7): 1483-1492, 1997.
45.Vapnik, V. Statistical Learning Theory. Wiley, 1998.
46.Haykin, S. Neural Networks: A Comprehensive Foundation, 2nd ed., Prentice-Hall, 1999, Chapter 6.
47.Valdes-Cristerna, R., Banuelos, V. M., Yanez-Suarez, O. “Coupling of radial basis networks and active contour model for multispectral brain MR images,” IEEE Trans. Biomedical Eng., 51(3): 459-470, 2004.
48.Bedell, B. J., Narayana, P. A. “Volumetric Analysis of White Matter, Gray Matter, and CSF Using Fractional Volume Analysis,” Magnetic Resonance in Medicine, 39:961–969, 1998.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔