Abstract：Segmenting CT slices featured contour accurately and rapidly is an important part in the medical image 3D reconstruction. The existing contour extracting technologies have to manually extract outlines interactively layer by layer, not only timeconsuming but also low accuracy. For this limitation, this paper proposed a automatic contour extracting method for tooth segmentation based on heuristic in dental and maxillofacial CT images. First, we enhanced all the image edges with Laplace operator. Second, the contour registration mapping technology passes the outline down heuristically. Ultimately, the shrinkwrapping algorithm is used to segment the teeth outlines automatically. With 14 cases (28～32 teeth samples) of a maxillary tooth cone beam CT tomography image sequences, at the same situation, we extract the contours of the sample with our method and the traditional method respectively. We determined the time of each tooth and the average distance between extracted contour and the real contour. From the experimental result, we concluded that the average time of our automatic extracting algorithm was about 23% of the traditional interactively algorithm time. The quality with our method is similar to traditional extracted contour. This method can provide a feasible and efficient approach to automatically segment CT slices featured areas, and further provide a new idea to improve the contour automatic extracting and image 3D reconstruction algorithm.
［1］孙涛,高东强. 基于CT图像的个性化人骨三维建模方法［J］. 机械设计与制造,2010,9(2):262-263.
［2］姜晓彤,罗立民.一种肺部肿瘤CT图像序列的自动分割方法［J］.中国图像图形学报,2003,9(8):1028-1033.
［3］李想. CT图像的应用研究［D］. 哈尔滨:哈尔滨工程大学,2004.
［4］Xu Chenyang,Prince JL.Snakes, shapes, and gradient vector flow［J］.IEEE TransactionsonImage Processing,1998, 7(3):359-369.
［5］Shang Yanfeng, Xin Yang, Zhu Lei, et al.Region competition based active contour for medical object extraction［J］. Computerized Medical Imaging and Graphics,200832(2):109-117.
［6］Yan Pingkun, Kassim AA. Segmentation of volumetric MRA images by using capillary active contour［J］. Medical Image Analysis,2006,10(3):317-329.
［7］Ghanei A,SoltanianZadeh H,Windham JP. Segmentation of the hippocampus from brain MRI using deformable contours［J］.Computerized Medical Imaging and Graphics,1998,22(3):203-216.
［8］Cohen LD,Cohen I. Finiteelement methods for active contour models and balloons for 2-D and 3-D images［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(11):1131-1147.
［9］侯晓丽，王博亮. 基于Fast Marching Method 的肝脏CT 图像序列自动分割［J］.中国数字医学, 2008,4(2):32-35.
［10］Jiao Pu, Justus R, Chin A, et al. Adaptive border marching algorithm: Automatic lung segmentation on chest
CTimages［J］.Computerized Medical Imaging andGraphics,2008,32(6):452-462.
［11］Zoroofi RA, Yoshinobu S, Toshihiko S,et al. Automated segmentation of acetabulum and femoral head from 3-D CT images［J］. IEEE Transactions on Information Technology in Biomedicine, 2003,7(4):329-343.
［12］Marcin C. Automatic liver segmentation from 2D CT images using an approximate contour model［J］. J Sign Process Syst,2014, 74(10):151-174.
［13］张飞，樊瑜波.齿颌CT图像中牙的半自动分割方法［J］.生物医学工程学杂志，2007,24(1):15-18.
［14］Dyn N, Leven D, Gregory JA. A 4point interpolatory subdivision scheme for curve design［J］.Computer Aided Geometric Design，1987,4(4):257-268.
［15］冈萨雷斯. 数字图像处理学［M］.阮秋琦译.北京: 电子工业出版社,2004.
［16］张毓晋. 图像工程：图像处理和分析［M］.北京:清华大学出版社,2000.
［17］马涛，余春暄. 数字图像处理在指针式指示表读数识别中的应用［J］. 微计算机信息2004,7(20):116-117.
［18］Kobbelt LP,Vorsatz J,LabsikU,et al.A shrink wrapping approachto remeshing polygonal surfaces［J］.Computer Graphics Forum,1999,18(1):209-237.
［19］Zhou Jinfang, Sherbrooke EC, Patrikalakis N. Computation of stationary points of distance functions［J］. Engineering with Computers, 1993, 9(4) :231-246.［20］同长虹，刘经华.用权重系数法优选机械设计方案［J］.甘肃科技，2005,11(21):121-123.
［21］尹庆水，万磊. Mimics软件在数字骨科的应用［J］. 中国骨科临床与基础研究杂志，2010,2(2):137-139.
［22］李康军.虚拟牙齿矫正系统中的排牙算法研究与实现［D］. 西安:西安科技大学，2009.
