進階搜尋


 
系統識別號 U0026-0812200914044005
論文名稱(中文) 膝關節X光影像之電腦測量與分析系統
論文名稱(英文) Computer Image Assessment and Analysis for Knee X-ray Image
校院名稱 成功大學
系所名稱(中) 資訊工程學系碩博士班
系所名稱(英) Institute of Computer Science and Information Engineering
學年度 96
學期 1
出版年 97
研究生(中文) 蔡翰進
研究生(英文) Han-chin Tsai
學號 p7694410
學位類別 碩士
語文別 中文
論文頁數 74頁
口試委員 指導教授-孫永年
口試委員-劉育寰
口試委員-李同益
口試委員-陳進興
指導教授-林啟禎
中文關鍵字 膝關節X光影像  邊界追蹤  曲率估測  主成分分析 
英文關鍵字 Contour tracking  Knee X-ray Image  Principle component analysis  Curvature estimating 
學科別分類
中文摘要 本論文將針對膝關節X光側面照影像,提出一套影像分析流程,找出在醫學上對這類影像所需的特徵參數,進而了解病人膝關節的病變程度,以及不同年齡的病人,其所算參數的統計分析。此研究的目標是針對影像上的股骨(Femur)、脛骨(Tibia)及髕骨(Patella)部位取出影像邊緣,並計算相關的參數。為了從影像上取得骨頭特徵邊緣,將不重要的肌肉視為雜訊濾除,我們引用一種星形濾波器-Asterisk Filter,搭配Canny邊緣檢測法,做為這類影像的前處理;另外,為了將骨頭的邊緣精確地追蹤出來,我們提出滾球邊界追蹤法(Rolling Ball Contour Tracking),來對二值化影像進行邊緣追蹤,藉此獲得邊緣的串列資料結構(Link List Data Structure);我們採用以主成分分析(Principle Component Analysis,簡稱PCA)取代原本以迴歸方法來計算的曲率,以取得更佳的曲率估測值,其可提高計算之參數的準確性。最後,我們利用物件導向設計模式,來建立一套具備實用、操作便利的膝關節影像分析工具,並將自動化分析功能納入其中,以利醫學人員診斷分析及後續的研究。
英文摘要 This thesis presents a set of image-analysis procedures on knee X-ray lateral view image in order to find some characteristic parameters for degenerative arthritis and some medical diagnostic statistics with different ages. The first goal of our research is to get image edges of femur, tibia and patella and then to calculate the specific parameters. For getting the major characteristic edges without confusions by undesired structures like muscle edges, we integrate a star-like edge detection filter named “Asterisk Filter” with the Canny Edge Detection in the image preprocessing. In addition, we also propose a new contour tracking method named “One-Pixel Rolling Ball Contour Tracking” for getting the boundary information in a binary image which is a link-list data structure. Instead of using a regression curvature estimator, PCA is used for better curvature estimation from a discrete bony contour. At last, we utilize the Object-Oriented software design procedure for constructing a practical and friendly user interface with all the auto-analysis functions for knee arthritis
diagnosis from lateral X-ray images.
論文目次 誌 謝 iii
作者序 iv
目錄 v
表目錄 vii
圖目錄 viii
虛擬碼目錄 x
理論目錄 x
第1章 背景介紹 1
1-1節 論文架構簡介 1
1-2節 動機目的 1
1-3節 相關研究 2
1-4節 影像概述 3
1-5節 影像特徵參數需求 7
第2章 方法介紹 14
2-1節 星形濾鏡 14
2-2節 兩種邊界搜尋法 18
2-2-1節 前進邊緣搜尋法 18
2-2-2節 滾球邊界追蹤法 19
2-3節 最佳化曲率值估測 22
2-3-1節 連續定義曲率計算 22
2-3-2節 離散定義曲率估測 25
第3章 自動分析 32
3-1節 股骨分析 32
3-2節 脛骨分析 35
3-2-1節 脛骨前緣分析(Tibia Front Analysis) 35
3-2-2節 脛骨前緣T點 40
3-2-3節 脛骨後緣分析 41
3-2-4節 脛骨前緣Canny模組的錯誤觸發轉換機制 42
3-3節 髕骨分析 43
第4章 分析系統專案規畫 46
4-1節 需求分析 46
4-2節 類別圖設計 50
4-3節 活動圖設計 52
第5章 實驗與討論 54
5-1節 系統測試 54
5-1-1節 測試環境 54
5-1-2節 計算速度與結果 54
5-1-3節 股脛骨邊緣誤差 57
5-1-4節 股脛骨軸夾角 60
5-1-5節 三個特徵點 62
5-2節 醫學參數評估 64
5-2-1節 髕骨長與髕骨肌腱長比值 64
5-2-2節 脛骨橫切線與脛骨軸夾角 66
第6章 結論與未來展望 69
6-1節 結論 69
6-2節 未來展望 70
參考文獻 71
作者簡歷 74
參考文獻 [1] John C. Stewien, Timothy L.J. Ferris, “The Asterisk Operator – An Edge Detection Operator Addressing the Problem of Clean Edges in Bone X-ray Images,” Knowledge-Based Intelligent Electronic Systems. Proceedings KES '98. Volume: 3, On page(s): 28-31 vol.3, 1998.
[2] Thomas Lewiner, João D. Gomes, Hélio Lopes, Marcos Craizer, “Arc-length based curvature estimator,” Sibgrapi (October 2004) Selected for publication in Computers & Graphics : pp 250-257, 2004.
[3] Thomas Lewiner, João D. Gomes, Hélio Lopes, Marcos Craizer, “Curvature and torsion estimators based on parametric curve fitting,” Computers & Graphics (October 2005) 29(5), pp 641-655. Selected for publication at the Sibgrapi conference, 2005.
[4] A. H. Newberg and D. Seligson, “The patellofemoral joint: 30o, 60o, and 90o views,” Radiology 137, pp. 57-61, 1980.
[5] A. P. Davies and M. M. S. Glasgow, “Imaging in osteoarthritis: a guide to requesting plain X-rays of the degenerate knee,” The Knee, no. 7, pp. 139-143, 2000.
[6] S. A. Mazzuca, K. D. Brandt et. al., “Effect of alignment of the medical tibial plateau and X-Ray beam on apparent progression of osteoarthritis in the standing anteroposteior knee radiograph,” Arthritis & Rheumatism, vol. 44, no. 8, pp.1786-1794, 2001.
[7] Gert Behiels, Frederik Maes, Dirk Vandermeulen, Paul Suetens, “Evaluation of image features and search strategies for segmentation of bone structures in radiographs using Active Shape Models,” Medical Image Analysis 6(1), pp. 47--62, 2002.
[8] T.F. Cootes, D. Cooper, C.J. Taylor and J. Graham, “A Trainable Method of Parametric Shape Description” In Procs. British Machine Vision Conference, Springer, Verlag, pp.54-61, 1991.
[9] T.F. Cootes, C. J. Taylor., “Active shape models – smart snakes,” In Procs. British Machine Vision Conference, Springer, Berlin, pp. 266-275, 1992.

[10] T. F. Cootes, C. J. Taylor, D. H. Cooper, et al., “Active Shape Models - Their Training and Application,” Computer Vision and Image Understanding, pp.38-59, January 1995.

[11] T.F. Cootes, G.J. Edwards and C.J. Taylor, “Active appearance models,“ IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 23, no. 6, June 2001.

[12] F. Maes, P. Suetens and P. Dewaele, “Statistical shape model-based segmentation of digital X-ray images,“ In Procs. IEEE Workshop on Mathematical Methods in Biomedical Image Analysis 11-12, pp.61 – 68 , June, 2000.
[13] M.Seise, S. J. McKenna, I.W. Ricketts and C.A.Wigderowitz , “Segmenting Tibia and Femur from Knee X-ray Images, “In Procs. Medical Image Understanding and Analysis (MIUA), Bristol, pp.103-106, July, 2005.
[14] M. Seise, S. J. McKenna, I. W. Ricketts and C. A. Wigderowitz, "Segmenting multiple objects with overlapping appearance and uncertainty", British Machine Vision Conference 2006.
[15] Y. Chen, X. Ee, W. K. Leow and T. S. Howe, “ Automatic Extraction of Femur Contours from Hip X-ray Images,“ In Proc. First International Workshop on Computer Vision for Biomedical Image Applications(CVBIA) ,pp. 200-209, 2005.
[16] M. Kass, A. Witkin, and D. Terzopolous, ”Snake: Active Contour Models,” Int. J. Comput. Vis. 1, pp. 321-331, 1988.
[17] C. Xu, J.L. Prince,”Gradient vector flow: A new external force for snakes,” In Proc. IEEE Conf. on CVPR,1997.
[18] H. C. Lee, Y. N. Sun, “Computer X-Ray Image Reconstruction for 3D Knee Joint and Computer-Assisted Diagnosis for Knee Osteoarthritis,” 國立成功大學資訊工程所碩士論文,2005
[19] F. Bernardini, J. Mittleman, H. Rushmeier, C. Silva, and G. Taubin “The Ball-Pivoting Algorithm for Surface Reconstruction” IEEE Transactions on Visualization and Computer Graphics, 5(4):349-359, 1999
[20] Chang-Chi Huang, “Bone Spur Detection and Evaluation for Knee Joint from 2D X-Ray and 3D MR Images”, 國立成功大學資訊工程所碩士論文,2006
[21] Marcel Worring, Arnold W. M. Smeulders, “Digital curvature estimation”, CVGIP: Image Understanding, Volume 58 , Issue 3, Pages: 366 – 382, 1993.
[22] Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing”, 2nd ed, Prentice-Hall, 2001.
[23] Wikipedia(維基百科)-
作者證明稿http://pbil.univ-lyon1.fr/R/liens/pearson1901.pdf
出處:http://en.wikipedia.org/wiki/Karhunen-Lo%C3%A8ve_transform
作者:http://en.wikipedia.org/wiki/Karl_Pearson
[24] R.A. Johnson, Probability and Statistics for Engineers 7th Edition, Pearson Prentice Hall, 2005.
[25] S. Sharma, APPLIED MULTIVARIATE TECHNIQUES, WILEY, pp. 375-378, 1996
[26] Ravikanth Malladi, James A. Sethian, “A Fast Level Set Based Algorithm for Topology-Independent Shape Modeling”, Journal of Mathematical Imaging and Vision 6, 269-289, 1996.
[27] Tony F. Chan and Luminita A. Vese, “Active Contours Without Edges”, IEEE Transactions on Image Processing, Vol 10, No. 2, February 2001.
[28] Suk-Ho Lee and Jin Keun Seo, “Level Set-Based Bimodal Segmentation With Stationary Global Minimum”, IEEE Transactions on Image Processing, Vol 15, No. 9, September 2006.
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2007-10-11起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2007-10-11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