跳到主要內容

臺灣博碩士論文加值系統

(18.97.9.172) 您好!臺灣時間:2025/02/18 04:52
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:蔡智翔
研究生(外文):Chih-hsiang Tsai
論文名稱:應用感知分類法建立視網膜血管樹
論文名稱(外文):Perceptual Grouping for Retinal Vascular Tree
指導教授:蔡佳玲蔡佳玲引用關係
指導教授(外文):Charlene Tsai
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊工程所
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:英文
論文頁數:59
中文關鍵詞:剖學的意義連結性感知分類交叉起始點血管樹
外文關鍵詞:Vascular treeanatomical significancejunction seedconnective-nessperceptual grouping
相關次數:
  • 被引用被引用:0
  • 點閱點閱:268
  • 評分評分:
  • 下載下載:18
  • 收藏至我的研究室書目清單書目收藏:0
我們主要的目的是在視網膜上建立具有解剖學意義的血管樹,血管樹可以幫助我們找出視網膜上其他重要的結構,也能協助醫師診斷或治療疾病。我們的方法主要分成兩個部分 — 血管擷取與感知分類。
我們擷取血管的方法主要是架構在”血管可能性追蹤”(LRV tracing)演算法上,為了獲得更可靠的血管擷取結果,我們在此演算法中加入了交叉起始點(Junction seed)及連結性(Connective-ness)兩個概念。交叉起始點可以幫助我們找出更多血管,而連結性可以協助這個演算法判斷是影像上是血管的部分。藉由這兩個新增的概念,我們新的血管可能性追蹤演算法可以找出比原來的演算法更完整的血管。這樣的結果可以讓我們在建立血管樹時更容易也更正確。
最後,我們使用感知分類的方法,靠著從血管擷取結果所獲得的血管資訊,推測出血管有解剖意義的結構來建立血管樹。然而,我們血管樹建立的方法只是一個架構性的做法。這是因為我們花了釵h的時間去改善原來的血管擷取演算法。一個可靠的血管擷取演算法對於建立血管樹是十分重要的。這樣的原因造成我們沒有足夠的時間去發展我們的血管樹建立演算法。我們建構的血管樹初步的正確率為46.1%,我們的血管樹建立演算法還有釵h改善的空間。
The goal of our work is vascular tree construction on retinal image and the tree has the anatomical significance of blood vessels. Vascular trees can help to extract the important structures from retinal images, and the trees also can assist the doctor in diagnosis and therapy of diseases. We separate the vascular trees construction into two main steps — vessel extraction and perceptual grouping.
Our vessel extraction method is based on Likelihood Ratio Vesselness (LRV) tracing. For obtaining the robust result of vessel extraction, we introduce the junction seeds and connective-ness measure into LRV tracing. Extraction of junction seeds enables tracing of more vessels and the connective-ness measure improves the robustness of tracing. Our new LRV tracing obtains more complete results of vessel extraction than the previous LRV tracing. The improved tracing can facilitate easier and more correct tree construction.
Vascular tree is constructed by perceptual grouping that uses the vessel information from vessel extraction to infer the anatomical structure of blood vessel. The information includes vessel width and vessel direction. Our vessel tree construction is only a framework. We spent a lot of time on improvement of vessel extraction, because the robust vessel extraction is important for vessel tree construction. This reason causes that we have insufficient time to develop our tree construction method. The preliminary correctness of the tree construction is 46.1%. Our vessel tree construction has many improved spaces.
Chapter 1 Introduction
1.1 Motivation
1.2 Challenges
1.3 Problem Definition
1.4 Summary of our Approach
1.5 Contributions
1.6 Overview of this thesis
Chapter 2 Related Work
Chapter 3 Vessel Extraction
3.1 LRV Vessel Tracing
3.2 Modifications to LRV Vessel Tracing
Chapter 4 Vascular Tree Construction
Chapter 5 Experimental Evaluation
5.1 Algorithm Summary
5.2 Evaluation for Vessel Extraction
5.3 Evaluation for Vascular Tree Construction
Chapter 6 Discussion and Conclusion
6.1 Conclusion
6.2 Limitations
6.3 Future Work
Reference
[1]M. Sonka, A. Stolpen, W. Liang, and R. M. Stefancik. Handbook of Medical Imaging, Medical Image Processing and Analysis, volume 2, chapter Vascular Imaging and Analysis., page 809V914. SPIE Press, 2001.
[2]C.S. Ogilvy, B.S. Carter, Kaplan S., Rich C., and R.M. Crowell. Temporary vessel occlusion for aneurysm surgery: risk factors for stroke in patients protected by induced hypothermia and hypertension and intravenous mannitol administration. Journal of Neurosurgery, 84(5):785–91, May 1996.
[3]N.M. Bressler. Early detection and treatment of neovascular agerelated macular degeneration. Journal of the American Board of Family Practice, 15(2):142–152, March-April 2002.
[4]K. Rapantzikos, M. Zervakis, and K. Balas. Detection and segmentation of drusen deposits on human retina: Potential in the diagnosis of age-related macular degeneration. Medical Image Analysis, 7:95–108, 2003.
[5]D. S. Shin, N. B. Javornik, and J. W. Berger. Computer-assisted interactive fundus image processing for macular drusen quantitation. Ophthalmology, 106(6):1119–1125, June 1999.
[6]M. Sofka, and C.V. Stewart. Multiscale Matched Filters, Confidence and Edge Measures, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 25, NO. 12, DECEMBER 2006.
[7]G. Guy and G. Medioni. Interring global perceptual contours from local features. International Journal of Computer Vision, 20(1):113–133, 1996.
[8]J. Jomier, V. LeDigarcher, and S. Aylward. Automatic vascular tree formation using the mahalanobis distance. In Proceedings of the 7th International Conference of Medical Image Computing and Computer- Assisted Intervention (MICCAI 2005), page 806 812, Palm-Springs, USA, 200.
[9]S.M. Kay, Fundamentals of Statistical Signal Processing: Detection Theory, Prentice Hall, 1998.
[10]A. Hoover, V. Kouznetsova, and M. Goldbaum. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Transactions on Medical Imaging, 19(3):203–210, 2000.
[11]C-K. Tang, and G. Medioni. Curvature-Augmented Tensor Voting for Shape Inference from Noisy 3D Data. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 24, NO. 6, JUNE 2002.
[12]J. Jia and C-K. Tang. Image Repairing: Robust Image Synthesis by Adaptive ND Tensor Voting. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003.
[13]W-S. Tong, C-K. Tang, P. Mordohai, and G. Medioni. First Order Augmentation to Tensor Voting for Boundary Inference and Multiscale Analysis in 3D. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 26, NO. 5, MAY 2004.
[14]J. Jia, and C-K. Tang. Inference of Segmented Color and Texture Description by Tensor Voting. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 26, NO. 6, JUNE 2004.
[15]P. Mordohai, and G. Medioni. Dense Multiple View Stereo with General Camera Placement using Tensor Voting. International Symposium on 3D Data Processing, Visualization, and Transmission, 2004.
[16]W-S. Tong, and C-K. Tang. Robust Estimation of Adaptive Tensors of Curvature by Tensor Voting. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 3, MARCH 2005.
[17]A. Can, H. Shen, J. N. Turner, H. L. Tanenbaum, and B. Roysam. Rapid automated tracing and feature extraction from live high-resolution retinal fundus images using direct exploratory algorithms. IEEE Transactions on Information Technology in Biomedicine, 3(2):125–138, 1999.
[18]K. Fritzsche, A. Can, H. Shen, C. Tsai, J. Turner, H. Tanenbuam, C. Stewart, and B. Roysam. Automated model based segmentation, tracing and analysis of retinal vasculature from digital fundus images. In J. S. Suri and S. Laxminarayan, editors, State-of-The-Art Angiography, Applications and Plaque Imaging Using MR, CT, Ultrasound and X-rays, pages 225–298. Academic Press, 2003.
[19]Y. Tolias, and S. Panas. A Fuzzy Vessel Tracking Algorithm for Retinal Images Based on Fuzzy Clustering. IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 17, NO. 2, APRIL 1998.
[20]A. Hoover, V. Kouznetsova, and M. Goldbaum. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Transactions on Medical Imaging, 19(3):203–210, 2000.
[21]J. Staal, M. Abrmoff, M. Niemeijer, M. Viergever, and B. Ginneken. Ridge-Based Vessel Segmentation in Color Images of the Retina. IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 23, NO. 4, APRIL 2004.
[22]D. Selle, B. Preim, A. Schenk, and H.-O. Peitgen. Analysis of vasculature for liver surgical planning. IEEE Transactions on Medical Imaging, 21(11):1344–1357, November 2002.
[23]P.J. Yim, P.L. Choyke, and R.M. Summers. Gray-scale skeletonization of small vessels in magnetic resonance angiography. IEEE Transactions on Medical Imaging, 19:568–576, June 2000.
[24]E Bullitt, S Aylward, A. Liu, J. Stone, S. Mukherji, C. Coffey, G. Gerig, and S.M. Prizer. 3d graph description of the intracerebral vasculature from segmented mra and tests of accuracy by comparison with x-ray angiograms. In Proceedings of the International Conference on Information Processing in Medical Imaging, volume 1613 of LNCS, pages 308–320, Visegr´ad, Hungary, June/July 1999. Springer-Verlag.
[25]G. Coppini, M. Demi, R. Poli, and G. Valli. An artificial vision system for x-ray images of human coronary tree. IEEE Transactions on Pattern Analysis and Machine Intelligence, page 156 162, Feb 1993.
[26]P. Montesinos, L. Alquier, Sci. ˜ G. Parc, and Nimes Besse. Perceptual organization of thin networks with active contour functions applied to medical and aerial images. In International conference on pattern recognition (ICPR 96), volume 1, pages 647–651, 1996.
[27]T. Deschamps and L.D. Cohen. Geometric Methods in Bio-Medical Image Processing, chapter Grouping connected components using minimal path techniques. Mathematics and Visualization. Springer, 2002.
[28]Thomas Deschamps and Laurent D. Cohen. Grouping connected components using minimal path techniques. application to reconstrucion of vessels in 2d and 3d images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, volume 2, pages 102–109, 2001.
[29]K. Haris, S.N. Efstratiadis, N. Maglaveras, C. Pappas, J. Gourassas, and G. Louridas. Model-based morphological segmentation and labeling of coronary angiograms. IEEE Transactions on Medical Imaging, 18(10):1003–1015, October 1999.
[30]I. Liu and Y. Sun. Recursive tracking of vascular networks in angiograms based on the detection-deletion scheme. IEEE Transactions on Medical Imaging, 12:334 341, June 1993.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top