臺灣博碩士論文加值系統

從電腦斷層攝影影像中切割出三維肝臟血管及其血管模型重建，在臨床的肝臟手術中扮演相當重要的腳色。然而，三維肝臟靜脈血管切割一直以來始終是一個具有挑戰性的問題，其中之一原因是由於電腦斷層攝影其影像品質不一和影像中隨機的雜訊而導致不完美的血管切割，而不完美的血管切割會產生不連續的血管區域以及錯誤的管徑估測。除此之外，另外一個會遭遇到的問題為肝臟靜脈血管中包含著門靜脈及肝門靜脈，而在肝臟電腦斷層攝影影像中，這兩血管區域有著相似的影像特徵，所以分辨這兩個血管，增加了血管切割的難度。
在本篇論文中，我們提出了一個方法包含著以下的步驟；首先，我們透過應用多規模的管狀過濾器來偵測肝臟部位電腦斷層攝影影像中血管的區域，解此來切割出血管的區域。接著，由於第一步驟的血管偵測中會包含著破碎不連續的血管區域，我們會利用我們所提出的相似分數來建立一個合理的血管樹狀結構，藉此來將所有破碎區域連接起來。再來，由於切割出的肝臟靜脈血管包含著兩個區域，門靜脈及肝門靜脈，此處我們透過簡單的互動方式搭配隨機漫步演算法來將肝臟靜脈血管區分為兩個有意義的區域。最後由於不完美的血管偵測而導致的錯誤管徑估測，我們提出一個血管追蹤及曲線配適的方法來改進原先錯誤的管徑估測。在實驗部分，我們測試了二十組臨床的肝臟部位的電腦斷層攝影影像，來評估我們所提出方法的準確度。

Liver vessel segmentation from computed tomography (CT) images is important in clinical liver surgical planning. However, liver vessel segmentation is a challenging task due to the low quality of vessel information in the CT images, which leads to errors in vessel detection and vessel type classification due to the complex vessel structures, such as portal vein, and hepatic vein to the goal of this thesis is to improve the vessel segmentation result and classify the liver venous vessel into meaningful part.
We propose an integrated framework for reconstructing 3D liver venous vessel model from 3D CT images. The proposed framework consists of vessel detection, vessel connectivity, vessel classification and vessel radius refinement. First, we employ the tubular-filter based approach to detect vessel structure inside the CT images and construct the reasonable vessel tree structure to bridge all the gaps between vessels by using the proposed similarity score. Then, we apply the random walker algorithm with simple user interaction to classify the liver venous vessel into portal vein and hepatic vein. Finally, we refine the vessel segmentation result by estimating vessel radius with vessel tracing and curve fitting. We evaluate the proposed algorithm on 20 CT datasets and experimental results show that our algorithm improves the mutual overlap rate by 7.57% when compared to the original tubular filter.

Table of Content
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Problem Description 1
1.3 Main Contribution 3
1.4 Thesis Organization 4
Chapter 2 Related Work 5
Chapter 3 Proposed Method 9
3.1 Vessel Detection 11
3.2 Vessel Connectivity 13
3.2.1 3D Skeletonization 14
3.2.2 Vessel tree structure construction 15
3.3 Vessel Classification 18
3.4 Vessel Radius Refinement 21
3.4.1 Vessel Branch Tracing 21
3.4.2 Vessel Radius Refinement 23
Chapter 4 Experimental Result 25
4.1 Dataset and Parameters 25
4.2 Preprocessing Liver Region Mask 25
4.3 Liver Venous Vessels Evaluation 26
4.4 Evaluation of Liver Venous Vessel Classification 30
4.4.1 Hepatic Vein and Portal Vein Evaluation 30
4.4.2 Visualization of Classification Result 35
4.5 Experimental Comparison 39
Chapter 5 Conclusion 40
References 41

[1] C. Metz, M. Schaap, A. Van Der Giessen, T. Van Walsum, and W. Niessen. Semi-automatic coronary artery centerline extraction in computed tomography angiography data. In Biomedical Imaging: From Nano to Macro, 2007. ISBI 2007. 4th IEEE International Symposium on, pages 856– 859. IEEE, 2007.
[2] W. Cai, F. Dachille, G. J. Harris, and H. Yoshida. Vesselness propagation: a fast interactive vessel segmentation method. In Medical Imaging, pages 614447 614447. International Society for Optics and Photonics, 2006.
[3] J. Mille and L. D. Cohen. Deformable tree models for 2d and 3d branching structures extraction. In Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on, pages 149–156. IEEE, 2009.
[4] V. Mahadevan, H. Narasimha-Iyer, B. Roysam, and H. L. Tanenbaum. Robust model-based vasculature detection in noisy biomedical images. Information Technology in Biomedicine, IEEE Transactions on, 8(3):360–376, 2004.
[5] 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 CVRMed-MRCAS’97, pages 213–222. Springer, 1997.
[6] K. Krissian, G. Malandain, N. Ayache, R. Vaillant, and Y. Trousset. Model-based detection of tubular structures in 3d images. Computer vision and image understanding, 80(2):130–171, 2000.
[7] A. F. Frangi, W. J. Niessen, K. L. Vincken, and M. A. Viergever. Multiscale vessel enhancement filtering. In Medical Image Computing and Computer-Assisted Interventation—MICCAI’98, pages 130–137. Springer, 1998.
[8] R. Manniesing, M. A. Viergever, and W. J. Niessen. Vessel enhancing diffusion: A scale space representation of vessel structures. Medical image analysis, 10(6):815–825, 2006.
[9] J. Lee, P. Beighley, E. Ritman, and N. Smith. Automatic segmentation of 3d micro-ct coronary vascular images. Medical image analysis, 11(6):630–647, 2007.
[10] D. Lesage, E. D. Angelini, I. Bloch, and G. Funka-Lea. A review of 3d vessel lumen segmentation techniques: Models, features and extraction schemes. Medical image analysis, 13(6):819–845, 2009.
[11] E. Bullitt, S. Aylward, A. Liu, J. Stone, S. K. Mukherji, C. Coffey, G. Gerig, and S. M. Pizer. 3d graph description of the intracerebral vasculature from segmented mra and tests of accuracy by comparison with x-ray angiograms. In Information Processing in Medical Imaging, pages 308–321. Springer, 1999.
[12] C. Bauer, T. Pock, E. Sorantin, H. Bischof, and R. Beichel. Segmentation of interwoven 3d tubular tree structures utilizing shape priors and graph cuts. Medical image analysis, 14(2):172–184, 2010.
[13] Y. Jiang, Z. W. Zhuang, A. J. Sinusas, L. H. Staib, and X. Papademetris. Vessel connectivity using murray’s hypothesis. In Medical Image Computing and ComputerAssisted Intervention–MICCAI 2011, pages 528–536.Springer, 2011.
[14] Y. Chi, J. Liu, S. K. Venkatesh, S. Huang, J. Zhou, Q. Tian, and W. L. Nowinski. Segmentation of liver vasculature from contrast enhanced ct images using context-based voting. Biomedical Engineering, IEEE Transactions on, 58(8):2144–2153, 2011.
[15] L. Wang, C. Hansen, S. Zidowitz, and H. K. Hahn. Segmentation and separation of venous vasculatures in liver ct images. In SPIE Medical Imaging, pages 90350Q–90350Q. International Society for Optics and Photonics,2014.
[16] V. Pamulapati, B. J. Wood, and M. G. Linguraru. Intrahepatic vessel segmentation and classification in multiphase ct using optimized graph cuts. In Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on, pages 1982–1985. IEEE, 2011.
[17] O. Barnea. Model-based estimation of coronary vessel diameter in angiographic images. In Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE, pages 513–516. IEEE, 1998.
[18] S. Wörz and K. Rohr. Limits on estimating the width of thin vessels in 3d medical images. In Bildverarbeitung für die Medizin 2006, pages 186–190. Springer, 2006.
[19] C. Wu, J. J. K. Derwent, and P. Stanchev. Retinal vessel radius estimation and a vessel center line segmentation method based on ridge descriptors. Journal of Signal Processing Systems, 55(1-3):91–102, 2009.
[20] T.-C. Lee, R. L. Kashyap, and C.-N. Chu. Building skeleton models via 3-d medial surface axis thinning algorithms. CVGIP: Graphical Models and Image Processing, 56(6):462–478, 1994.
[21] L. Grady. Random walks for image segmentation. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 28(11):1768–1783, 2006.
[22] Y.-Y. Cheng, H.-M. Chang, H.-R. Su, S.-H. Lai, K.-C. Liu, and C.-H. Lin. 3d liver segmentation and model reconstruction from ct images. In Biomedical Engineering and Biotechnology (iCBEB), 2012 International Conference on, pages 654–657. IEEE, 2012.
[23] A. Tizon and J. Courtney. Blood vessel diameter estimation system using active contours. In Machine Vision and Image Processing Conference (IMVIP), 2011 Irish, pages 88–93. IEEE, 2011.