[1]粟华,杨冠羽,胡轶宁,等.基于相位的C-V模型乳腺超声图像分割方法[J].东南大学学报(自然科学版),2013,43(3):494-497.[doi:10.3969/j.issn.1001-0505.2013.03.009]
 Su Hua,Yang Guanyu,Hu Yining,et al.Breast ultrasound image segmentation method using C-V model based on phase[J].Journal of Southeast University (Natural Science Edition),2013,43(3):494-497.[doi:10.3969/j.issn.1001-0505.2013.03.009]
点击复制

基于相位的C-V模型乳腺超声图像分割方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
43
期数:
2013年第3期
页码:
494-497
栏目:
计算机科学与工程
出版日期:
2013-05-20

文章信息/Info

Title:
Breast ultrasound image segmentation method using C-V model based on phase
作者:
粟华杨冠羽胡轶宁舒华忠
东南大学影像科学与技术实验室, 南京 210096
Author(s):
Su Hua Yang Guanyu Hu Yining Shu Huazhong
Laboratory of Image Science and Technology, Southeast University, Nanjing 210096, China
关键词:
相位特征 超声图像分割 C-V模型
Keywords:
phase feature ultrasound image segmentation C-V(Chan-Vese)model
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2013.03.009
摘要:
为了提高乳腺超声图像分割的准确率,提出了一种基于相位特征的C-V模型超声图像分割方法.首先,采用LOG-Gabor滤波器对超声图像进行6个不同方向的滤波,提取最大能量所对应的相位信息,得到超声图像的相位特征.然后,采用SRAD方法对超声图像降噪,并将降噪后的图像与相位特征点乘,增强图像目标与背景的对比度.最后,运用C-V模型的分割算法识别图像中的目标区域,并采用腐蚀方法使目标区域边缘完整、平滑.实验结果表明, 与基于灰度的C-V模型、GAC模型以及基于相位特征的人工神经网络方法相比,利用该方法分割乳腺超声图像,分割的精确度明显提高,达到92.40%.
Abstract:
In order to improve the accuracy of breast ultrasound image segmentation, an ultrasound image segmentation method using the C-V(Chan-Vese)model based on phase is proposed. First, the ultrasound image is filtered by LOG-Gabor filters in six different orientations, and the phase feature of the image is obtained by extracting the phase information in the orientation with the maximum energy. Then, the SRAD(speckle reducing anisotropic diffusion)method is used to reduce the noise of the ultrasound image, and the processed image is multiplied by the phase features to enhance the contrast of the target and background. Finally, the target of the ultrasound image is identified by the segmentation algorithm using the C-V model, and corrosion is applied to make the edge smooth and complete. The experimental results show that compared with the C-V model and GAC(geodesic active contour)model based on image gray and the ANN(artificial neural networks)method based on phase feature, the proposed method can obviously improve the accuracy of breast ultrasound image segmentation, which is 92.40%.

参考文献/References:

[1] Alison N J, Djamal B. Ultrasound image segmentation: a survey [J]. IEEE Transactions on Medical Imaging, 2006, 25(8):987-1010.
[2] Liang K C, Rogers A J. Three-dimensional ultrasound guidance of autonomous robotic breast biopsy: feasibility study [J]. Ultrasound in Medicine and Biology, 2010, 36(1): 173-177.
[3] Chang R F, Wu W J, Moon W K, et al. Segmentation of breast tumor in three-dimensional ultrasound images using three-dimensional discrete active contour model [J]. Ultrasound in Medicine and Biology, 2003, 29(11): 1571-1581.
[4] Liu B, Cheng H D, Huang J H. Probability density difference-based active contour for ultrasound image segmentation [J].Pattern Recognition, 2010, 43(6): 2028-2042.
[5] Chen D R, Chang R F, Kuo W J, et al. Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks [J]. Ultrasound in Medicine and Biology, 2002, 28(10):1301-1310.
[6] Shan J, Wang Y X, Cheng H D. Completely automatic segmentation for breast ultrasound using multiple-domain features [C]//Proceedings of 2010 IEEE International Conference on Image Processing. Hong Kong, China, 2010: 1713-1716.
[7] 高梁, 刘晓云, 陈武凡. 基于相位和GGVF的水平集乳腺超声图像分割 [J].仪器仪表学报, 2012, 33(4): 870-877.
  Gao Liang, Liu Xiaoyun, Chen Wufan. Phase and GGVF-based level set segmentation of breast ultrasound images [J]. Chinese Journal of Scientific Instrument, 2012, 33(4): 870-877.(in Chinese)
[8] Belaid A, Boukerroui D, Maingourd Y,et al. Phase-based level set segmentation of ultrasound images [J]. IEEE Transactions on Information Technology in Biomedicine, 2011, 15(1): 138-147.
[9] Kovesi P D. Phase congruency: a low-level image invariant [J]. Psychological Research, 2000, 64(2): 136-148.
[10] Yu Y, Scott T A. Speckle reducing anisotropic diffusion [J]. IEEE Transactions on Image Processing, 2002, 11(11): 1260-1270.
[11] Chan T, Vese L. Active contours without edges [J]. IEEE Transactions on Image Processing, 2001, 10(2): 266-277.
[12] Caselles V, Kimmel R, Sapiro G. Geodesic active contour [J]. International Journal of Computer Vision, 1997, 22(1): 61-79.

备注/Memo

备注/Memo:
作者简介: 粟华(1989—),女,硕士生;舒华忠(联系人),男,博士,教授,博士生导师,shu.list@seu.edu.cn.
基金项目: 国家重点基础研究发展计划(973计划)资助项目(2011CB707904)、国家自然科学基金资助项目(31100713,60911130370,61073138,61271312,81101104)、教育部博士点基金资助项目(20110092110023)、江苏省自然科学基金资助项目(BK2012743)、江苏省“六大人才高峰”资助项目.
引文格式: 粟华,杨冠羽,胡轶宁,等.基于相位的C-V模型乳腺超声图像分割方法[J].东南大学学报:自然科学版,2013,43(3):494-497. [doi:10.3969/j.issn.1001-0505.2013.03.009]
更新日期/Last Update: 2013-05-20