在本論文中，我們發展出一套在缺少背景圖的情況下的血管偵測方法。我們的方法首先透過改良式的區域式直方圖等化法提高數位減法攝影圖的影像對比。之後透過自動化黑塞矩陣為基礎的血管增強遮罩給予每個像素一個適當的血管信任程度，以解決數位減法攝影圖高雜訊問題。最後利用血管信任程度於影像中找出血管的位置。由實驗結果可看出，所提出之方法可以偵測大多數主要的血管，亦可準確地偵測到部分微血管。

In this thesis, we develop a vessel detection method without
background image. In the proposed method, we first exploit the
improved sub-block histogram equalization to enhance the contrast of the image produced by digital subtraction angiography. To reduce the noise in the digital subtraction image, we can assign an appropriate vesselness to each pixel in the image by using the Hessian-based vessel enhancement filters. Finally, according to the assigned vesselness of each pixel, the vessel regions of an image can be detected. By experimenting on some test images, the results demonstrate that the proposed method can detect most principal vessels as well as some capillaries.

[1] [Online] 醫學影像-維基百科 Available：http://zh.wikipedia.org/wiki/%E9%86%AB%E5%AD%B8%E5%BD%B1%E5%83%8F
[2] [Online] 陸坤池, 周鈺峰, 施威名, 許智鈞, 簡隆至, 許博仁, X-ray影像系統介紹 Available：http://bmeimage.be.cycu.edu.tw/Lab/database/X-RAY/X-ray.html
[3] [Online] 國醫中心放射診斷部 電腦斷層掃瞄 Available：
http://wwwu.tsgh.ndmctsgh.edu.tw/TM/mywebs/fang_she/mysite13/CT注意事項.htm
[4] [Online] 核磁共振-維基百科 Available：
http://zh.wikipedia.org/wiki/%E6%A0%B8%E7%A3%81%E5%85% B1%E6%8C%AF
[5] A. F. Frangi, W. J. Niessen, K. L. Vincken, and M. A. Viergever,
“Multiscale vessel enhancement filtering,” International Society and Conference Series on Medical Image Computing and Computer-Assisted Intervention, vol. 1496, pp.130-137, 1998.
[6] C. Lorenz, I. C. Carlsen, T. M. Buzug, C. Fassnacht and J. Weese, “Multi-scale line segmentation with automatic medical images,” in Proceedings of Computer Vision, Virtual Reality and Robotics in Medicine and Medical Robotics and Computer-Assisted Surgery, pp. 233-242, 1997.
[7] Y. Sato, S. Nakajima, H. Atsumi, T. Koller, G. Gerig, S. Yoshida, and R. Kikinis, “3D multi-scale line filter for segmentation and visualization of curvilinear structures in medical images,” in Proceedings of Computer Vision, Virtual Reality and Robotics in Medicine and Medical Robotics and Computer-Assisted Surgery, vol. 1205, pp. 213-222, 1997.
[8] O. Wink, A. F. Frangi, B. Verdonck, M. A. Viergerver and W. J. Niessen, “3D MRA coronary axis determination using a minimum cost approach,” in Proceedings of the International Society for Magnetic Resonance in Medicine, vol. 47, pp. 1169-1175, 2002.
[9] M. J. R. Fatemi, S. M. Mirhassani and B. Yousefi, “Vessel segmentation in x-ray angiographic images using hessian-based vesselness filter and wavelet based image fusion,” IEEE International Conference on Information Technology and Applications in Biomedicine, pp. 1-5, 2010.
[10] M. Schneider, H. Sunder, “Automatic global vessel segmentation and catheter removal using local geometry information and vector field integration,” IEEE International Symposium on Biomedical Imaging, pp. 45-48, 2010.
[11] S. M. Mirhassani, M. M. Hosseini, A. Behrad, “Improvement of hessian based vessel segmentation using two stage threshold and
morphological image recovering,” International Conference on
Innovations in Information Technology, pp. 50-54, 2009.
[12] S.R. Aylward, E. Bullit, “Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction,” IEEE Transactions on Medical Imaging, vol. 21, pp. 61-75, 2002.
[13] 鍾國亮教授, 影像處理與電腦視覺, 東華書局, 台北, 第四版, 2008.
[14] J. Y. Kim, L S. Kim, and S. H. Hwang, “An advanced contrast enhancement using partially overlapped sub-block histogram equalization,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 11, pp.475-484, 2001.
[15] J. Fan, D. K. Y. Yan, A. K. Elmagarmid, W. G. Aref, “Automatic image segmentation by integrating color-edge extraction and seeded region growing,” IEEE Transactions on Image Processing, vol. 10, pp.1454-1466, 2001.
[16] F. Y. Shin, S. Cheng, “Automatic seeded region growing for color image segmentation,” Image and Vision Computing, vol.23, pp.877-886, 2005