臺灣博碩士論文加值系統

視網膜是醫學病狀診療上的一個重要診斷部位，醫生們可以藉由觀察視網膜裡血管的變化情況來診斷許多眼睛疾病。因此，在本論文裡我們提供兩種視網膜圖處理的方法來幫助醫學病狀的診療：第一種方法為視網膜圖血管切割法，A Novel Retinal Blood Vessel Segmentation Method Based on Line Detector and Edge Detector (RBVSLE)，這個方法採用線的運算子與邊緣偵測法切割視網膜圖上的血管；第二種方法是建造一個自動化視網膜圖分類機制，A New Classification Mechanism for Retinal Images (NCMRI)，此分類機制可以在大量圖片中區分視網膜圖與非視網膜圖。
RBVSLE的好處是能夠減少line operator造成的錯誤切割率，這個方法利用邊緣偵測法找出視網膜圖上的血管邊緣點，接著以這些邊緣點為起點使用line operator找出這些起點附近的血管點。經過實驗測試後，RBVSLE可以大量減少line operator造成的錯誤切割率，和其他血管切割法相比，RBVSLE切割品質也比這些方法好。
NCMRI是一種區分視網膜影像與非視網膜影像的方法。我們設計了兩種分類法：第一種為SVM；另一種為結合PCA與SVM的分類法。實驗部分我們使用10張影像與20張的影像來測試這兩種分類法的分類正確率，經過測試後，SVM可以達到96%的分類正確率；另外，結合PCA與SVM的分類法不僅可成功地減少影像的特徵值個數，同時此分類法的分類正確率也有92%。

Retina is an important indicator in medical treatment pathologies. By observing the tortuosity changes of blood vessels in the retina, clinicians can diagnose many eye diseases. In this thesis, we provide two retinal image processing methods for medical treatment of pathology. The first, A Novel Retinal Blood Vessel Segmentation Method Based on Line Operator and Edge Detector (RBVSLE), is based on a line operator and an edge detector for the purpose of segmenting the blood vessels in a retinal image. The second, A New Classification Mechanism for Retinal Images (NCMRI), is a mechanism for automatically classifying the retinal and non-retinal images in a large database.
The benefit of the RBVSLE is that it reduces the probability of false segmentation caused by the line operator by using a detector to detect the edge points in a retinal image and then setting the edge points as the initial points so the blood vessel around a given initial point can be segmented by using the line operator. In our experiments, the RBVSLE significantly reduces the probability of false segmentation, and the performance of RBVSLE is better than that of other methods.
NCMRI is a mechanism by which retinal images can be distinguished from non-retinal images. We design two classification methods: one is pure SVM and the other is a hybrid that combines the PCA and SVM mechanisms. Experimental results confirm that the accuracy rate of pure SVM is up to 96% for 10-image and 20-image data sets, and the hybrid method successfully reduces the features of images by using PCA while maintaining an accuracy rate above 92% for 10- and 20-image data sets.

誌謝 i
中文摘要 ii
Abstract iii
Table of Contents iv
List of Figures vi
List of Tables vii
Chapter 1 1
Introduction 1
1.1 Research Motivation and Objectives 1
1.2 Dissertation Organization 3
Chapter 2 4
Related Works 4
2.1 Retinal Blood Vessel Segmentation Method 4
2.1.1 Line Operator 4
2.1.2 Adam Hoover’s Blood Vessel Segmentation Method 7
2.1.3 Xiaoyi Jiang’s Blood Vessel Segmentation Method 11
2.2 Edge Detection Method 15
2.2.1 Canny Operator 15
2.2.2 Sobel Operator 17
2.3 Principal Components Analysis 18
2.4 Support Vector Machine 21
Chapter 3 23
A Novel Retinal Blood Vessel Segmentation Method Based on Line Operator and Edge Detector 23
3.1 Preliminary 23
3.2 Proposed Scheme 24
3.2.1 Preprocess Phase 25
3.2.2 Edge Map Establishment 26
3.2.3 Vessel Detection 27
3.3 Experimental Results 29
3.4 Summary 33
Chapter 4 34
A New Classification Mechanism for Retinal Images 34
4.1 Preliminary 34
4.2 Proposed Scheme 37
4.2.1 Pure SVM Mechanism 37
4.2.2 A Hybrid Mechanism of PCA+SVM 38
4.3 Experimental Results 41
4.4 Summary 44
Chapter 5 45
Conclusions and Future Works 45
Reference 47

[1]S. R. Aylward and E. Bullitt, “Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction,” IEEE Trans. Med. Imag., vol. 21, no. 2, pp. 61–75, Feb. 2002.
[2]A. Anzalone, F. Bizzarri, M. Parodi, and M. Storace, “A modular supervised algorithm for vessel segmentation in red-free retinal images”, Computers in Biology and Medicine, vol. 38, no. 8, pp. 913-922, Aug. 2008.
[3]J. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679 – 698, Nov. 1986.
[4]S. Chaudhuri, S. Chatterjee, N. Katz, and M. Goldbaum, “Detection of blood vessels in retinal images using two-dimensional matched filters,” IEEE Transactions on Medical Imaging, vol. 8, no. 3, pp. 263–269, Sept. 1989.
[5]C. C. Chang and C. J. Lin, “LIBSVM: a library for support vector machines,” at http://www.csie.ntu.edu.tw/~cjlin/libsvm, 2001.
[6]A. Can, H. Shen, J. N. Turner, H. L. Tanenbaum, and B. Roysam, “Rapid automated tracing and feature extraction from retinal fundus images using direct exploratory algorithms,” IEEE Trans. Inform. Technol. Biomed., vol. 3, no. 2, pp.
125–138, June 1999.
[7]R.-E. Fan, P.-H. Chen, and C.-J. Lin, “Working set selection using the second order information for training SVM,” J. Mach. Learn. Res., vol. 6, pp. 1889-1918, 2005.
[8]M. Fontaine, L. Macaire, J. G. Postaire, M. Valette, and P. Labalette, “Fundus images segmentation by unsupervised classification,” Vision Interface,
Trois-Rivieres, Canada, May 1999.
[9]L. Gang, O. Chutatape, and S. M. Krishnan, “Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter,” IEEE Transactions on Biomedical Engineering, vol. 49, no. 2, pp. 168-172, Feb. 2002.
[10]A. Hoover, V. Kouznetsova, and M. Goldbaum, “Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response,”
IEEE Trans. Med. Imag., vol. 19, no. 3, pp. 203–210, Mar. 2000.
[11]X. Jiang and D. Mojon, “Adaptive local thresholding by verification based multithreshold probing with application to vessel detection in retinal images,”
IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 1, pp. 131–137, Jan. 2003.
[12]I. Liu and Y. Sun, “Recursive tracking of vascular networks in angiograms based on the detection-deletion scheme,” IEEE Trans. Med. Imag., vol. 12, no. 2,
pp. 334-341, June 1993.
[13]L. Malagon-Borja and O. Fuentes. “Object detection using image reconstruction with PCA,” Image and Vision Computing, Mar. 2007.
[14]H. Narasimha-Iyer, J. M. Beach, B. Khoobehi, and B. Roysam, “Automatic identification of retinal arteries and veins from dual-wavelength images using structural and functional features,” IEEE Trans. Biomed. Eng., vol. 54, no. 8, pp. 1427–1435, Aug. 2007.
[15]R. Nekovei and Y. Sun, “Back-propagation network and its configuration for blood vessel detection in angiograms,” IEEE Trans. Neural Networks, vol. 6, no. 1, pp. 64–72, Jan. 1995.
[16]M. Niemeijer, J. Staal, B. van Ginneken, M. Loog, and M. D. Abramoff, “Comparative study of retinal vessel segmentation methods on a new publicly available database,” SPIE Medical Imaging, vol. 5370, pp. 648-656, June 2004.
[17]E. Ricci and R. Perfetti, “Retinal blood vessel segmentation using line operators and support vector classification,” IEEE Trans. Med. Imag., vol. 26, no. 10, Oct. 2007.
[18]Y. Sun, “Automated identification of vessel contours in coronary arteriograms by an adaptive tracking algorithm,” IEEE Transactions on Medical Imaging, vol. 8, no. 1, pp. 78-88, Mar. 1989.
[19]J. Staal, M. D. Abramoff, M. Niemeijer, M. A. Viergever, and B. van Ginneken, “Ridge-based vessel segmentation in color images of the retina,” IEEE Trans. Med. Imag., vol. 23, no. 4, pp. 501–509, Apr. 2004.
[20]C. Sinthanayothin, J. F. Boyce, H. L. Cook, and T. H. Williamson, “Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images,” Br. J. Ophthalmol, vol. 83, no. 8, pp. 902–910, Feb. 1999.
[21]J. V. B. Soares, J. J. G. Leandro, R. M. Cesar, Jr., H. F. Jelinek, and M. J. Cree, “Retinal vessel segmentation using the 2D Gabor wavelet and supervise classification,” IEEE Trans. Med. Imag., vol. 25, no. 9, pp. 1214–1222, Sep. 2006.
[22]Y. A. Tolias and S. M. Panas, “A fuzzy vessel tracking algorithm for retinal images based on fuzzy clustering,” IEEE Transactions on Medical Imaging, vol. 17, no. 4, pp. 263–273, Apr. 1998.
[23]T. Walter, J. C. Klein, P. Massin, and A. Erginay, “A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina,” IEEE Trans. Med. Imag., vol. 21, no. 10, pp. 1236–1244, Oct. 2002.
[24]A. A. H. A. R. Youssif, A. Z. Ghalwash, and A. A. S. A. R. Ghoneim, “Optic disc detection from normalized digital fundus images by means of a vessels'' direction matched filter,” IEEE Transactions on Medical Imaging, vol. 27, no. 1, pp. 11-18, Jan. 2008.
[25]F. Zana and J. Klein, “Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation,” IEEE Trans. Image Process., vol. 10, no.
7, pp. 1010–1019, Jul. 2001.
[26]L. Zhou, M. S. Rzeszotarski, L. J. Singerman, and J. M. Chokreff, “The detection and quantification of retinopathy using digital angiograms,” IEEE Trans. Med. Imag., vol. 13, no. 4, pp. 619–626, Dec. 1994.