An adaptive snake model for ultrasound image segmentation: Modified trimmed mean filter, ramp integration and adaptive weighting parameters

被引:11
作者
Chen, CM [1 ]
Lu, HHS
机构
[1] Natl Taiwan Univ, Inst Biomed Engn, Taipei 10764, Taiwan
[2] Natl Chiao Tung Univ, Inst Stat, Hsn Chu, Taiwan
关键词
adaptive weighting parameters; modified trimmed mean filter; ramp integration; snake model; ultrasound image segmentation;
D O I
10.1177/016173460002200403
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
The snake model is a widely-used approach to finding the boundary of the object of interest in an ultrasound image. However, due to the speckles, the weak edges and the tissue-related textures in an ultrasound image, conventional snake models usually cannot obtain the desired boundary satisfactorily. In this paper, we propose a new adaptive snake model for ultrasound image segmentation. The proposed snake model is composed of three major techniques, namely, the modified trimmed mean (MTM) filtering, ramp integration and adaptive weighting parameters. With the advantages of the mean and median filters, the MIM filter is employed to alleviate the speckle interference in the segmentation process. The weak edge enhancement by ramp integration attempts to capture the slowly varying edges, which are hard to capture by conventional snake models. The adaptive weighting parameter allows weighting of each energy term to change adaptively during the deformation process. The proposed snake model has been verified on the phantom and clinical ultrasound images. The experimental results showed that the proposed snake model achieves a reasonable performance with an initial contour placed 10 to 20 pixels away from the desired boundary. The mean minimal distances from the derived boundary to the desired boundary have been shown to be less than 3.5 (for CNR greater than or equal to 0.5) and 2.5 pixels, respectively, for the phantom and ultrasound images.
引用
收藏
页码:214 / 236
页数:23
相关论文
共 30 条
[1]  
BRATHWAITE PA, 1996, P 1996 23 ANN M COMP, P37
[2]  
BUSSE LJ, 1995, P 1995 ULTR S, V2, P1353
[3]   A multiple active contour model for cardiac boundary detection on echocardiographic sequences [J].
Chalana, V ;
Linker, DT ;
Haynor, DR ;
Kim, YM .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1996, 15 (03) :290-298
[4]  
Chen C. H., 1996, Biomedical Engineering, Applications Basis Communications, V8, P287
[5]   A new ultrasound image segmentation algorithm based on an early vision model and discrete snake model [J].
Chen, CM ;
Lu, HHS ;
Lin, YC .
MEDICAL IMAGING 1998: IMAGE PROCESSING, PTS 1 AND 2, 1998, 3338 :959-970
[6]  
Czerwinski R. N., 1995, Proceedings. International Conference on Image Processing (Cat. No.95CB35819), P358, DOI 10.1109/ICIP.1995.529720
[7]  
Duquenoy E, 1995, P SOC PHOTO-OPT INS, V2588, P528, DOI 10.1117/12.222706
[8]   Statistics of the log-compressed echo envelope [J].
Dutt, V ;
Greenleaf, JF .
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1996, 99 (06) :3817-3825
[9]  
FAN L, 1996, P 1996 23 ANN M COMP, P41
[10]   COMPARISON STUDY OF NONLINEAR FILTERS IN IMAGE-PROCESSING APPLICATIONS [J].
FONG, YS ;
POMALAZARAEZ, CA ;
WANG, XH .
OPTICAL ENGINEERING, 1989, 28 (07) :749-760