跳到主要內容

臺灣博碩士論文加值系統

(34.226.244.254) 您好!臺灣時間:2021/08/01 03:35
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:廖佑晟
研究生(外文):You-Cheng Liao
論文名稱:比較評估使用最大交互資訊的不同定位方法
論文名稱(外文):Comparative Evaluation of Different Strategies for Registration by Maximization of Mutual Information
指導教授:羅祺祥
指導教授(外文):Chi-Hsiang Lo
學位類別:碩士
校院名稱:國立宜蘭大學
系所名稱:電子工程學系碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2007
畢業學年度:95
語文別:中文
論文頁數:65
中文關鍵詞:比較
外文關鍵詞:compare
相關次數:
  • 被引用被引用:0
  • 點閱點閱:121
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
現今由於電腦科技發展,功能強大,其中高速運算的功能,使醫學影像隨之發展,藉由電腦科技將醫學影像做特殊的分析以及適當的處理,已經成熟的運用於臨床之診斷與治療;在醫學影像定位的領域中,由於單一種醫學影像資訊並不足夠,因此將人體中同一部位經由不同儀器所獲取的影像融合(例如:CT-MR或CT-PET),經過三維影像定位後所得到的影像,更能精確提供醫生所需的特定位置。

在本論文中,主要是比較評估不同的腦部定位方法,針對定位所需時間、及影像定位精確度,比較優缺點,並找出造成時間過長、誤差較大等狀況,設法改進。

本文主要採用Dr. Chi-Hsiang Lo在The Retrospective Image Registration Evaluation (0Hhttp://www.vuse.vanderbilt.edu/~image/registration)中利用最大交互資訊所使用的三種不同定位方法作為研究樣本,試圖對這三種方法並與其他研究者所獲取的結果進行比較評估及改進,希望藉此能在影像定位領域中,提供實質上的幫助。
Today, due to the capability of the computer is powerful, the technique of processing the medical images is widely used in the clinical diagnosis and treatment. In the area of medical image registration, because only one kind of images is not enough to give us the entire information, therefore, it’s useful to fuse different images (ex: CT-MR or CT-PET). After three-dimension medical image registration, the specific position is shown in precisely for the doctor needs.

In this thesis, it’s mainly to evaluate the different brain registration strategies, aims to the speed and accuracy of registration. To compare the merit and defect, and find out the reason so we can improve it.

In this study, the samples get from the three kinds of registration strategies by Dr. Chi-Hisang Lo, as part of The Retrospective Image Registration Evaluation (1Hhttp://www.vuse.vanderbilt.edu/~image/registration), the result of comparison with other researchers as well and improvement were proposed. I hope it can offer the help for the research of medical image registration.
致謝 i
摘要 ii
Abstract iii
目錄 iv
圖目錄 vi
表目錄 vii
第一章 緒論
1.1 背景 1
1.2 目的 1
第二章 影像
2.1 影像來源 3
2.1.1 電腦斷層掃描影像CT 3
2.1.2 核磁共振影像MR 3
2.1.3 正電子放射斷層掃描影像PET 4
2.2 影像處裡 4
2.2.1 區域成長法 4
2.2.2 K-Means群集法 5
2.2.3小波轉換 7
2.2.3.1離散小波轉換 7
2.2.3.2Daubechies 小波濾波器係數 8
第三章 醫學影像定位
3.1 醫學影像定位演算法 12
3.1.1對應標記演算法 12
3.1.2面定位 13
3.1.3根據像素強度定位-相似像素法 14
3.1.3.1 多重影像定位-由相同病患取得相同影像模式 15
3.1.3.2 像素相似法-應用不同影像模式熵值進行校准 16
3.2 正規化交互資訊 17
3.3 座標轉換 19
3.4最佳化演算法 22
3.4.1 Powell共軛方向法 22
3.4.2 Downhill單一法 23
第四章 評估
4.1 定位方法 25
4.1.1以二位元法最大交互資訊對CT-MR影像的定位 25
4.1.2使用非線性網格最大交互資訊對CT-MR影像的定位 26
4.1.3使用小波多重解析最大交互資訊對多種型態的腦部影像的
定位方法 26
4.2數據 27
4.2.1介紹 27
4.2.2以二位元法最大交互資訊對CT-MR影像的定位 27
4.2.3使用非線性網格最大交互資訊對CT-MR影像的定位 32
4.2.4使用小波多重解析最大交互資訊對多種型態的腦部影像的
定位方法 36
4.3 比較分析 45
4.3.1 中值誤差比較 45
4.3.2 最大值誤差比較 46
4.3.3 定位時間比較 47
4.3.4 探討 48
4.4 最大交互資訊法定位比較 48
4.4.1誤差值比較 48
4.4.2 結論 52
第五章 總結
5.1 結論 53
5.2 未來工作 54
參考文獻 55
[1] Kenneth R. Castleman, Digital image processing, prentice Hall,1996.
[2] R.C.Gonzalez and R.E. Woods, Digital image Processing, Prentice Hall,1996.
[3] I.Gallant Stephen, Neural network learning and expert systems, MIT Press, 1993.
[4] M.R. Anderberg, Cluster analysis for applications, Academic Press, New York, 1973.
[5] S. Mallat, A wavelet Tour of signal processing, San Diego, CA: Academic Press, 1998.
[6] S. Mallat, A theory for multiresolution signal decomposition: the wavelet repreasentation, IEEE Trans. Patt Anal. Mach. Intell., 11(7):674-693,1998.
[7] I. Daubechies, Orthogonal bases of compactly supported wavelets, Communications on Pure and Applied Mathematics., 41:909-996,1988.
[8] C.K. Chui, An introduction to wavelets, Academic Press, San Diego, CA, 1992.
[9] I. Daubechies, Ten lectures on wavelets, CBMS-NSF Regional Conference Series in Applied Mathematics, Vol. 61, SIAM, Philadelphia, PA. 1992.
[10] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham, Training models of shape form sets of examples. British Machine Vision Conference 1992 (D. Hogg and R. Boyle, EDs), pp. 9-18. London: Springer, 1992
[11] R.P. Woods, J.C. Mazziotta, and S.R. Cherry, MRI PET registration with automa-
ted algorithm. J. Comput. Assist. Tomogy. Vol. 17, pp. 536-546,1993.
[12] P.A. van den Elsen, E.J.D. Pol, T.S. Sumanaweera, P.F. Hemler, S. Napel, and J.R. Adler, Grey value correlation techniques used for automatic matching of CT and MR volume images of the head. SPIE vol.2359, pp. 205-216,1994.
[13] C.E. Shannon, The mathematical theory of communication (past 1 and 2). Bell Syst. Tech J. vol. 27, pp. 379-423 and 623-656, 1948. Reprint available from http://www.lucent.com.
[14] C. Studholme, D.L.G Hill, and D.J. Hawkes, Voxel similarity measures for MR-PET registration, in Information Processing in Medical Imaging(IPMI’95) (Y. Bizais, C. Barillot, and R. Di Paola, Eds.), pp. 287-298. Dordrecht: Kluwer, 1995.
[15] A. Collignon, F. Maes, D. Delaere, D. Vandermeulen, P. Suetens, and G. Marchal, Automated multimodality image registration using information theory, in Infor-
mation Processing in Medical Imaging (IPMI ‘95) (Y. Bizais, C. Barillot, and R. Di Paola, Eds.), pp.263-274. Dordrecht: Kluwer, 1995.
[16] F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. suetens, Multimodality image registration by maximization of mutual information, IEEE Med. Imaging, vol. 16, pp. 187-198, 1997
[17] W.M. Wells, P. Viola, H. Atsumi, S. Nakajima, and R. Kikinis, Multi-modal volume registration by maximization of mutual information, Medical Image Anal., 1, pp.35-51, 1996.
[18] C. Studholme, D.L.G. Hill, D.J. Hawkes, An overlap invariant entropy measure of 3D medical image alignment, Pattern Recognition, 32(1):71-86,1999.
[19] Frederik Maes, Dirk Vandermeulen, Paul Suetens, Multimodality Image Regis-
tration using Information Theory M.I.R.I.T. Version 97/08 Manual Pages
[20] W.H. Press, B.P. Flannery, S.A. Teukolsky, and W.T. Vetterling, Numerical recipes in C: the art of scientific computing, 2nd ed., Cambridge, U.K.:Canbridge University Press, 394-455,1999.
[21] J.A. Nelder and R. Mead, Computer Journal, vol. 7, pp.308-313
[22] J.P.W. Pluim, J.B.A. Maintz, and M.A. Vigever, Mutual information matching in
multiresolution contexts, Image and Vision Computing, 19(1-2), pp. 45-52, 2001
[23] C. Studholme, D.L.G. Hill, and D.J. Hawkes, Automated 3D registration of MR and PET brain images by multi-resolution optimization of voxel similarity measures, Medical Physics, vol. 24, pp.25-36, 1997.
[24] J.P.W. Pluim, J.B.A. Maintz, and M.A. Vigever, A multiscale approach to mutual information matching, Medical Imaging: Image Processing(K.M. Hanson, ed.), volume 3338 of Proc. SPIE, pages 1334-1344, SPIE Press, Bellingham, WA, 1998
[25] F. Maes, D. Vandermeulen, and P. Suetens, Comparative evaluation of multiresoluion optimization strategies for multimodality image registration by maximization of mutual information, Medical Image Anal., 3, pp. 373-386, 1999
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top