Level set active contour model improving boundary indicator function

ZHENG Wei; ZHANG Jing; YANG Hu

doi:10.7510/jgjs.issn.1001-3806.2016.01.028

Because of the restriction of imaging principle, ultrasound images led toare always with low contrast and weak boundaries, segmentation effect of level set based on edge was not ideal. In order to improve segmentation precision and efficiency of ultrasound images, new a novel level set segmentation algorithm was proposed combining gradient information with regional information was proposed. Firstly, distance regularized level set evolution (DRLSE) model based on boundary was improved, regional information was put into boundary indicator function. And then, the improved boundary indicator function was used instead of DRLSE model's. Finally, a level set evolution model combining gradient information with regional information was obtained. The experimental results show that the model can accurately segment ultrasound images of thyroid tumor and the segmentation efficiency and precision are higher than DRLSE model.

Level set active contour model improving boundary indicator function

1. College of Electronic and Information Engineering, Hebei University, Baoding 071002, China;

2. Key Laboratory of Hebei on Digital Medical Engineering, Hebei University, Baoding 071002, China;

3. 3

Received Date: 2014-10-24

Accepted Date: 2014-12-17

Available Online: 2016-01-25

Abstract: Because of the restriction of imaging principle, ultrasound images led toare always with low contrast and weak boundaries, segmentation effect of level set based on edge was not ideal. In order to improve segmentation precision and efficiency of ultrasound images, new a novel level set segmentation algorithm was proposed combining gradient information with regional information was proposed. Firstly, distance regularized level set evolution (DRLSE) model based on boundary was improved, regional information was put into boundary indicator function. And then, the improved boundary indicator function was used instead of DRLSE model's. Finally, a level set evolution model combining gradient information with regional information was obtained. The experimental results show that the model can accurately segment ultrasound images of thyroid tumor and the segmentation efficiency and precision are higher than DRLSE model.

HTML

Reference (15)

[1]	ZHANG K H, SONG H H, ZHANG L. Active contours driven by local image fitting energy[J]. Pattern Recognition, 2010, 43(4):1199-1206.
[2]	CHEN K, LI B, TIAN L F. A segmentation algorithm of pulmonary nodules using active contour model based on fuzzy speed function[J]. Acta Automatica Sinica, 2013, 39(8):1257-1264(in Chinese).
[3]	LIU R J, HE C J, YUAN Y. Active contours driven by local and global image fitting energy[J]. Journal of Computer-Aided Design Computer Graphics, 2012, 24(3):364-371(in Chinese).
[4]	LI C M, XU C Y, GUI C F, et al. Distance regularized level set evolution and its application to image segmentation[J]. IEEE Transactions Image Processing, 2010, 19(12):3243-3254.
[5]	CASELES V, KIMMEL R, SAPIRO G. Geodesic active contour[J]. International Journal of Computer Vision,1997,22(1):61-79.
[6]	ZHENG W, PAN Z Y, HAO D M. The Improved DRLSE ultrasound image segmentation model based on phase congruency[J]. Opto-Electronic Engineering, 2014, 41(1):60-64(in Chinese).
[7]	ZHANG J W, FANG L, CHEN Y J, et al. Application of local GAC model for medical image segentation[J]. Journal of Image and Graphics, 2012, 17(2):215-221(in Chinese).
[8]	WANG S F, RUAN J, WANG Y. Image segmentation based on improved LBF model[J]. Computer Applications and Software, 2011, 28(2):25-28(in Chinese).
[9]	ZHAO J, QI Y M, PAN Z Y. Active contour segmentation modal of combining global and dual-core local fitting energy[J]. Journal of Computer Applications, 2013, 33(4):1092-1095(in Chinese).
[10]	LI Ch M, XU Ch Y, GUI Ch F, et al. Level set evolution without re-initialization:A new variational formulation[C]//IEEE International Conference on Computer Vision and Pattern Recognition. New York, USA:IEEE,2005:430-436.
[11]	YU R X, ZHU B. New stop function of level set method[J]. Journal of System Simulation, 2008, 20(22):6154-6157(in Chinese).
[12]	ZHOU B, HE C J, YUAN Y. Edge-based active contour model with adaptive varying stopping function[J]. Application Research of Computers, 2012, 29(1):366-368(in Chinese).
[13]	QI Y Q, ZHANG T. Region-based method of adaptive distance preserving level set evolution[J]. Research Journal of Applied Sciences, Engineering and Technology, 2013, 5(5):1608-1613.
[14]	ZHANG K H, ZHANG L, SONG H H. Active contours with selective local or global segmentation:A new formulation and level set method[J]. Image and Vision Computing, 2010, 28(4):668-676.
[15]	COLLINS D L, EVANS A C, HOLMS C, et al. Automatic 3-D segmentation of neuro-anatomical structures from MRI[C]//14th International Conference on Information Processing in Medical Imaging. De Berder, France:Information Processing in Medical Imaging,1995:139-152.

Level set active contour model improving boundary indicator function

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views