A fully automatic vertebra segmentation method using 3D deformable fences

被引:72
作者
Kim, Yiebin [1 ]
Kim, Dongsung [1 ]
机构
[1] Soongsil Univ, Sch Elect Engn, Seoul 156743, South Korea
关键词
Automatic vertebra segmentation; 3D deformable fence; Fence-limited labeling; IMAGES;
D O I
10.1016/j.compmedimag.2009.02.006
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
In this paper, we propose a fully automatic method for vertebra segmentation in the CT volume data. The method constructs 3D fences that separate adjacent vertebrae from valley-emphasized Gaussian images. Initial curves for the 3D fences are extracted from intervertebral discs, detected with anatomical characteristics, then optimized using a deformable model. A minimum cost path finding method corrects any erroneous curves trapped into a local minimum. Final volume is labeled with help of the 3D fences by a fence-limited region growing method. This method has been applied to 50-patient data sets and has proved to be very successful. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:343 / 352
页数:10
相关论文
共 22 条
[1]   SEEDED REGION GROWING [J].
ADAMS, R ;
BISCHOF, L .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1994, 16 (06) :641-647
[2]  
[Anonymous], LECT NOTES COMPUTER
[3]  
Barrett W A, 1997, Med Image Anal, V1, P331, DOI 10.1016/S1361-8415(97)85005-0
[4]  
Benjelloun M, 2006, INT C PATT RECOG, P476
[5]  
BENJELLOUN M, 2006, 2 IEE INT C INF COMM, P1119
[6]   Deformable boundary finding in medical images by integrating gradient and region information [J].
Chakraborty, A ;
Staib, LH ;
Duncan, JS .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1996, 15 (06) :859-870
[7]   USING DEFORMABLE SURFACES TO SEGMENT 3-D IMAGES AND INFER DIFFERENTIAL STRUCTURES [J].
COHEN, I ;
COHEN, LD ;
AYACHE, N .
CVGIP-IMAGE UNDERSTANDING, 1992, 56 (02) :242-263
[8]   Medical image analysis: Progress over two decades and the challenges ahead [J].
Duncan, JS ;
Ayache, N .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (01) :85-106
[9]   Combining strings and necklaces for interactive three-dimensional segmentation of spinal images using an integral deformable spine model [J].
Ghebreab, S ;
Smeulders, AWM .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2004, 51 (10) :1821-1829
[10]   Automatic lumbar vertebral identification using surface-based registration [J].
Herring, JL ;
Dawant, BM .
JOURNAL OF BIOMEDICAL INFORMATICS, 2001, 34 (02) :74-84