|本期目录/Table of Contents|

[1]褚晶辉,王星宇,吕卫.基于帧间相关性的乳腺MRI三维分割[J].天津大学学报(自然科学版),2017,(08):835-842.[doi:10.11784/tdxbz201605091]
 Chu Jinghui,Wang Xingyu,Lü Wei.3D Segmentation of Breast MRI Based on Inter-Frame Correlations[J].Journal of Tianjin University,2017,(08):835-842.[doi:10.11784/tdxbz201605091]
点击复制

基于帧间相关性的乳腺MRI三维分割()
分享到:

《天津大学学报(自然科学版)》[ISSN:0493-2137/CN:12-1127/N]

卷:
期数:
2017年08
页码:
835-842
栏目:
电气自动化与信息工程
出版日期:
2017-08-31

文章信息/Info

Title:
3D Segmentation of Breast MRI Based on Inter-Frame Correlations
文章编号:
0493-2137(2017)08-0835-08
作者:
褚晶辉 王星宇 吕卫
天津大学电气自动化与信息工程学院,天津 300072
Author(s):
Chu Jinghui Wang Xingyu Lü Wei
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
关键词:
乳腺磁共振图像 病灶分割 帧间相关性 超像素 水平集
Keywords:
breast magnetic resonance image lesion segmentation inter-frame correlation superpixel level set
分类号:
TP391.7
DOI:
10.11784/tdxbz201605091
文献标志码:
A
摘要:
针对乳腺磁共振图像序列的肿瘤分割问题, 提出一种基于超像素和改进C-V模型的三维全自动分割方法.该方法利用磁共振图像序列的帧间相关性, 约束相邻帧图像的分割轮廓.采用超像素算法提取肿瘤的大致轮廓, 再用改进的C-V水平集算法对可疑区域边缘进行优化, 使其更接近肿瘤的实际边缘. 将该方法及3种对比方法应用于89例乳腺MRI序列图像. 以手动分割的轮廓为基准, 该方法得到的平均重叠率为87.84% , 相比于C-V模型的58.90% 、超像素和水平集结合的76.36% 、K均值+C-V的83.62% , 有明显提升. 实验结果表明, 该方法的全自动分割结果对于肿瘤起始和终止帧图像具有较高的分割精度.
Abstract:
An automatic 3D segmentation method for tumor mass in breast magnetic resonance image(MRI) image sequence which uses superpixel segmentation and modified C-V model is proposed in this paper. The proposed method explores the inter-frame correlation in the MRI image sequence to constrain the contour in the adjacent frames. The SLIC0 superpixel method is adopted to extract the outline of masses,and then the modified C-V level set algorithm is adopted to refine the border of the suspicious area to approximate the real border. In experiments,the proposed method and three competitive methods were applied to 89 cases of breast MRI sequential images. Compared with the contour of manual segmentation,the average overlap rate of the proposed method is 87.84%,and it is 58.90% for C-V model,76.36% for superpixel combined with level set and 83.62% for K-means +C-V. It is also demonstrated that the automatic segmentation results of the proposed method have a higher accuracy for the start and the end frame of the breast mass.

参考文献/References:

[1] Liu Y, Liu H, Zhao Z, et al. A new active contour model-based segmentation approach for accurate extraction of the lesion from breast DCE-MRI[C] // IEEE International Conference on Image Processing. Melbourne, Australia, 2013:1140-1143.
[2] Ricalde L. Critique of the American cancer society guide-lines for breast cancer screening:Update 2003[J]. Journal of the American Association of Nurse Practitioners, 2004, 16(8):322-325.
[3] Dorrius M D, Weide J V D, Ooijen P M A V, et al. Computer-aided detection in breast MRI:A systematic review and meta-analysis[J]. European Radiology, 2011, 21(8):1600-1608.
[4] Fooladivanda A, Shokouhi S B, Ahmadinejad N, et al. Automatic segmentation of breast and fibroglandular tissue in breast MRI using local adaptive thresholding [C]// Biomedical Engineering IEEE. Gulfport, USA, 2014.
[5] Ali Qusay A F, Umi Kalthum N, Isa N A M, et al. Computer-aided segmentation system for breast MRI tumour using modified automatic seeded region growing(BMRI-MASRG)[J]. Journal of Digital Imaging, 2014, 27(1):133-144.
[6] Madhukumar S, Santhiyakumari N. Evaluation of K-means and fuzzy C-means segmentation on MR images of brain[J]. Egyptian Journal of Radiology and Nuclear Medicine, 2015, 1(2):475-479.
[7] Moftah H M, Azar A T, Al-Shammari E T, et al. Adaptive k-means clustering algorithm for MR breast image segmentation[J]. Neural Computing and Applications, 2014, 24(7/8):1917-1928.
[8] Aslam A, Khan E, Beg M M S. Improved edge detection algorithm for brain tumor segmentation[J]. Procedia Computer Science, 2015, 58:430-437.
[9] Bahreini L, Fatemizadeh E, Gity M. Gradient vector flow snake segmentation of breast lesions in dynamic contrast-enhanced MR images[C]// Biomedical Engineering. Innsbruck, Austria, 2010:1-4.
[10] Yao J, Chen J, Chow C. Breast tumor analysis in dynamic contrast enhanced MRI using texture features and wavelet transform[J]. IEEE Journal of Selected Topics in Signal Processing, 2009, 3(1):94-100.
[11] Torbati N, Ayatollahi A, Kermani A. An efficient neural network based method for medical image segmentation[J]. Computers in Biology and Medicine, 2014, 44:76-87.
[12] 曹沛彩, 刘晨彬, 张海时, 等. 基于C-V模型和MRF的脑部MRI分割[J]. 计算机工程, 2014, 40(3):262-265.
Cao Peicai, Liu Chenbin, Zhang Haishi, et al. Brain MRI segmentation based on C-V model and MRF[J]. Computer Engineering, 2014, 40(3):262-265(in Chinese).
[13] Khalifa I, Youssif A, Youssry H. MRI brain image segmentation based on wavelet and FCM algorithm[J]. International Journal of Computer Applications, 2012, 47(16):32-39.
[14] Achanta R, Shaji A, Smith K, et al. SLIC superpixels
[EB/OL]. http://ivrlwww.epfl.ch/supplementary_mate-rial/RK_SLICSuperpixels/index.html, 2010-01-01.
[15] Li C, Xu C, Gui C, et al. Distance regularized level set evolution and its application to image segmentation.
[J]. IEEE Transactions on Image Processing, 2010, 19(12):3243-3254.
[16] Chu J, Hang M, Li L, et al. A novel computer aided breast mass detection scheme based on morphological enhancement and SLIC superpixel segmentation[J]. Medical Physics, 2015, 42(7):3859-3869.
[17] Thompson D R, Mandrake L, Gilmore M S, et al. Superpixel endmember detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(11):4023-4033.
[18] Chan T F, Vese L A. Active contours without edges[J]. IEEE Transactions on Image Processing, 2001, 10(2):266-277.
[19] Wang X F, Huang D S, Xu H. An efficient local Chan-Vese model for image segmentation[J]. Pattern Recognition, 2010, 43(3):603-618.
[20] 张承杰, 厉力华. 基于空间FCM与MRF方法的乳腺MRI序列三维病灶分割研究[J]. 中国生物医学工程学报, 2014, 33(2):202-211.
Zhang Chengjie, Li Lihua. 3D Segmentation of breast DCE-MRI sequence using spatial FCM-MRF method [J]. Chinese Journal of Biomedical Engineering, 2014, 33(2):202-211(in Chinese).
[21] Dong Yan, Gao Xinbo, Wang Ying, et al. A top-hat based calcilfications detection method in mammograms [J]. Journal of Image and Graphics, 2006, 11(12):1839-1843.
[22] Hartigan J A, Wong M A. Algorithm AS 136:A K-means clustering algorithm[J]. Applied Statistics, 1979, 28(1):100-108.
[23] Bouchefra H. Breast Lesions Segmentation in Dynamic Contrast-Enhanced MR Images[EB/OL]. https:// dspace. library. uu. nl/handle/1874/318911, 2015-01-01.
[24] Boegel M, Hoelter P, Redel T, et al. A fully-automatic locally adaptive thresholding algorithm for blood vessel segmentation in 3D digital subtraction angiography[J]. Engineering in Medicine and Biology Society, 2015(6):2006-2009.

备注/Memo

备注/Memo:
收稿日期: 2016-05-24; 修回日期: 2016-10-10.
作者简介: 褚晶辉(1969—), 女, 博士, 副教授, cjh@tju.edu.cn.
通讯作者: 吕卫, luwei@tju.edu.cn.
基金项目: 国家自然科学基金资助项目(61271069).
Supported by the National Natural Science Foundation of China(No. 61271069).
更新日期/Last Update: 2017-08-10