心臟血管電腦斷層攝影之冠狀動脈自動化裁切

Automatic Segmentation of Coronary Arteries in CT-angiography

周瑞祥(Jui-Hsiang Chou)

指導教授 ： 高一峰

高雄醫學大學/健康科學院/醫學影像暨放射科學系碩士班/碩士(2010年)

https://doi.org/10.6832/KMU.2010.00011

摘要

近年來，心臟血管疾病一直排於台灣十大死因中，其中冠狀動脈疾病（CAD）佔了不小的比例。所以早期診斷的篩檢工具便顯得相當重要。由於電腦斷層攝影(Computed Tomography)在軟體和硬體上不斷的進步，臨床上已可使用心臟血管電腦斷層攝影檢查(Heart CTA)作為篩檢冠狀動脈疾病的工具；但是檢查後之冠狀動脈影像後處理相當耗時，本研究主要目標便是針對冠狀動脈裁切的步驟進行自動化演算法的研究，藉由冠狀動脈自動化裁切進一步減少心臟血管電腦斷層影像後處理的時間；此外，冠狀動脈自動裁切也是心臟血管電腦斷層影像後續自動化分析的基礎。本研究中，我們先用原始二維影像分析左、右冠狀動脈的分支種子點(seed point)；再用三維區塊成長(Region Growing)和邊緣偵測(Edge Detection)裁切冠狀動脈之三維影像。最後，比較自動化裁切和人工裁切之冠狀動脈影像。結果顯示，在自動裁切影像品質佳的冠狀動脈影像中，自動裁切演算法的裁切影像與人工裁切影像做點對點比較後，平均有97.8 ± 4.4%的準確度。

關鍵字

冠狀動脈疾病 ； 心臟血管電腦斷層攝影 ； 自動化裁切 ； 區塊成長

並列摘要

Recently, cardiovascular disease has become one of leading causes of death and coronary artery disease (CAD) has great proportion in it. Screening of patients with an intermediate risk of coronary artery disease is vital. With the advances of multidetector CT technology, both the temporal resolution and the spatial resolution of heart CT angiography have improved sufficeintly for routine noninvasive assessment of the coronary arteries for atherosclerotic disease. It is time-consuming and mental fatiguing for the postprocessing steps after scaning. The purpose of this work is to provide an algorithm for the fully automatic segmentation of coronary arteries. By this way, we can lighten the loading of the postprocessing steps and provide the foundation work for the automatic analysis of heart CT angiography. In the study, first we analyze the branch seed point of the coronary artery by 2D images; then segment the coronary artery with region growing and edge detection algorithm. In comparison with man-made segmentation images of the coronary artery, the mean accuracy of automatic segmentation image was 97.8 ± 4.4% in fine quality automatic segmentation images of heart CT angiography.

並列關鍵字

coronary artery disease ； heart CT angiography ； automatic segmentation of coronary arteries ； region growing

參考文獻

[1] U.J. Schoepf, P.L. Zwerner, G. Savino, C. Herzog, J.M. Kerl, and P.Costello, “Coronary CT Angiography,”Radiology, vol. 244, pp. 48-63, 2007.

[2] B. Ohnesorge, T. Flohr, C. Becker, A. Kopp, U. J. Schoepf, U. Baum, A. Knez, K. Klingenbeck-Regn, and M. Reiser, “ Cardiac imaging by means of electrocardiographically gated multisection spiral CT:

initial experience, ” Radiology,vol. 217, pp. 564-571, 2000.

[3] T.G. Flohr, U.J. Schoepf, A. Kuettner, S. Halliburton, H. Bruder, C. Suess, B. Schmidt, L. Hofmann, E. K. Yucel, S. Schaller, and B. M. Ohnesorge, “Advances in cardiac imaging with 16-section CT systems, ” Acad. Radiol., vol. 10, pp. 386-401, 2003.

[4] B.M. Ohnesorge, L.K. Hofmann, T.G. Flohr, and U.J. Schoepf, “CT for imaging coronary artery disease: defining the paradigm for its application, ” Int J Cardiovasc Imaging, vol. 21, pp. 85-140, 2005.