基于矢量量化的三维图像自适应分割方法及其应用

近年来对图像处理的研究已从二维(2D)向三维(3D)及更高维方向发展。但对3D图像分割的研究目前尚不够深入，仍以基于2D图像的分割方法为主。提出了一种可有效利用空间信息的3D图像自适应分割方法：先进行层间插值、空间子块的边缘与非边缘模式分类；并对非边缘模式子块进行基于矢量量化的分割，同时设计出一种最优码本求取方法来自适应确定分割的数目；再对边缘模式子块根据非边缘模式子块的分割结果进行逐点检测和划分。文中利用IBSR医学图像库的仿真人脑数据和实际人脑核磁共振成像(MRI)样本进行实验，验证了该方法的有效性。同时通过对同一病患不同时期的MRI数据样本进行实验，得到了诸如不同时间病灶部位的体积变化情况等十分有价值的临床医学信息。

Abstract

In recent years, the research of image processing is developed from traditional two dimensions (2D) to three dimensions (3D) or even more dimensions. However, the existing segmentation methods are mainly based on 2D image processing, and more effective 3D image segmentation methods are expected. An adaptive 3D image segmentation method based on vector quantization (VQ) that can effectively utilize the spatial information of the volume data of the 3D image is proposed. In the method, a preprocessing is conducted on the 3D image, including volume interpolation, dividing of the 3D image into small sub-cubic blocks (sub-cubes), and classification of the sub- cubes into two patterns, the edge pattern and non- edge pattern. The non- edge pattern sub- cubes are segmented by using the VQ technique and the edge pattern sub- cubes are classified in pixel based on the segmentation results of non-edge pattern sub-cubes. In order to determine the segmentation number adaptively, an optimal codebook searching algorithm is designed for the VQ approach. Experiments are conducted by using both the simulation samples and real human brain magnetic resonance imaging (MRI) images from the IBSR database and the effectiveness of the proposed method is validated by the experimental results. The experiments are also performed on the MRI images of the same patient in different treatment periods, which can provide the varied 3D information about the focus parts in different times that is valuable for clinical diagnosis in medical practice.

参考文献

[1] 高晓亮, 王志良, 刘冀伟, 等. 基于灰度特征统计的可变区域图像分割算法[J]. 光学学报, 2011, 31(1): 0115003.

Gao Xiaoliang, Wang Zhiliang, Liu Jiwei, et al.. Algorithm for image segmentation using statistical models based on intensity features[J]. Acta Optica Sinica, 2011, 31(1): 0115003.

[2] 吴艳, 肖平, 王昌明, 等. 基于Contourlet域持续性和聚集性的合成孔径雷达图像融合分割算法[J]. 光学学报, 2010, 30(7): 1977-1983.

Wu Yan, Xiao Ping, Wang Changming, et al.. Segmentation algorithm for SAR images based on the persistence and clustering in the contourlet domain[J]. Acta Optica Sinica, 2010, 30(7): 1977-1983.

[3] 宋昱, 吴一全, 毕硕本. 边缘修正ＣＶ模型的卫星遥感云图分割方法[J]. 光学学报, 2014, 34(9): 0901004.

Song Yu, Wu Yiquan, Bi Shuoben. Satellite remote sensing cloud image segmentation using edge corrected CV mode[J]. Acta Optica Sinica, 2014, 34(9): 0901004.

[4] 郭亚晶, 唐顺兴, 季来林. 基于激光近场和图像分割技术的复合波长诱导熔石英损伤实验研究[J]. 光学学报, 2013, 33(1): 0114001.

Guo Yajing, Tang Shunxing, Ji Lailin. Experimental study of multiple wavelength laser-induced damage in SiO2 based on near field and image segmentation[J]. Acta Optica Sinica, 2013, 33(1): 0114001.

[5] 郑倩, 卢振泰, 陈超, 等. 基于邻域信息和高斯加权卡方距离的脊椎MR 图像分割[J]. 中国生物医学工程学报, 2011, 30(3): 358-362.

Zhang Qian, Lu Zhentai, Chen Chao, et al.. Spinal MRI segmentation based on local neighborhood information and gaussian weighted chi-square distance[J]. Chinese Journal of Biomedical Engineering, 2011, 30(3): 358-362.

[6] 刘玮. 脑MRI图像分割方法的研究与实现[D]. 广州: 华南理工大学, 2012: 23-33.

Liu Wei. Research on the Segmentation Methods and the Implementation of the Brain MRI Image[D]. Guangzhou: South China University of Technology, 2012: 23-33.

[7] 彭希帅. CT肿瘤序列图像的分割[D]. 南京理工大学, 2013: 36-42.

Peng Xishuai. Segmentation of CT Tumor Volume Images[D]. Nabjing: Nanjing University of Science and Technology, 2013: 36-42.

[8] Li C, Wang X Y, Eberl S, et al.. A likelihood and local constraint level set model for liver tumor segmentation from CT volumes[J]. IEEE Transactions on Biomedical Engineering, 2013, 60(10): 2967-2977.

[9] Ortiz A, Gorriz J M, Ramirez J, et al.. Two fully-unsupervised methods for MR brain image segmentation using SOM-based strategies [J]. Applied Soft Computing, 2013, 13(1): 2668-2682.

[10] 田沄. 医学体数据场可视化关键技术研究[D]. 西安: 西北工业大学, 2007: 35-55.

Tian Yun. Studying on the Key Techniques of Volume Visualization in Medicine[D]. Xi′an: Northwestern Polytechnical University, 2007: 35-55.

[11] De A L, Guo C A. An adaptive vector quantization approach for image segmentation based on SOM network[J]. Neurocomputing, 2015, 149: 48-58.

[12] 郑丽芳. 三维超声图像分割方法的研究与实现[D]. 广州: 华南理工大学, 2012: 30-46.

Deng Lifang. The Research and Implementation of Three-Dimensional Ultrasound Image Segmentation Methods[D]. Guangzhou: South China University of Technology, 2012: 30-46.

[13] 邹永宁. 工业CT三维图像重建与分割算法研究[D]. 重庆: 重庆大学, 2014: 95-111.

Zou Yongning. Study on Industrial CT 3D Image Reconstruction and Segmentation Algorithm[D]. Chongqing: Chongqing University, 2014: 95-111.

[14] Luciano N, Giuseppe M. Automatic 3D Image Segmentation Using Adaptive k-means on Brain MRI[M]. Berlin Heidelberg: Springer Press, Communications in Computer and Information Science, 2011: 171-183.

[15] 石峰. 三维医学图像精准分割算法研究[D]. 上海: 上海交通大学, 2009: 41-59.

Shi Feng. Study on Accurate Segmentation Algorithm on 3D Medical Images[D]. Shanghai: Shanghai Jiao Tong University, 2009: 41-59.

[16] 彭小朋. 一种脑MRI图像的混合分割模型[D]. 上海: 上海交通大学, 2010: 44-61.

Peng Xiaopeng. A Hybrid Model for Brain MRI Image Segmentation[D]. Shanghai: Shanghai Jiao Tong University, 2010: 44-61.

[17] Vijay J, Subhashini J. An efficient brain tumor detection methodology using k-means clustering algorithm[C]. International Conference on Communication and Signal Processing, 2013: 653-657.

[18] 廖振宇. 多功能纳米载体的构建及其在肿瘤MRI成像和靶向治疗中的初步应用[D]. 天津: 天津大学, 2012: 11-14.

Liao Zhenyu. Design and Fabrication of Multifunctional Nanocarriers and its Preliminary Application in Both Cancer MR Imaging and Targeted Therapy[D]. Tianjin: Tianjin University, 2012: 11-14.

[19] 杨玲, 侯小叶, 王中科, 等. 局部信息约束的形状导向水平集算法对下颌管的分割[J]. 中国生物医学工程学报, 2012, 31(2): 161-166.

Yang Ling, Hou Xiaoye, Wang Zhongke, et al.. Mandibular canal segmentation based on shape-driven level-set algorithm restrained by local information[J]. Chinese Journal of Biomedical Engineering, 2012, 31(2): 161-166.

[20] 胡军. 医学图像的层间插值和三维重建系统中图像分割的研究[D]. 南京: 南京航空航天大学, 2010: 25-31.

Hu Jun. Research on Interpolation of Medical Image and Image Segmentation in 3D Reconstruction System[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2010: 25-31.

[21] 吴良武, 侯建华. 基于物质灰度正态分布的CT断层图像匹配插值[J]. 中国生物医学工程学报, 2012, 31(2): 231-236.

Wu Liangwu, Hou Jianhua. Matching interpolation of CT slices based on intensity normal distribution of matters[J]. Chinese Journal of Biomedical Engineering, 2012, 31(2): 231-236.

[22] 孔维华. 基于多方向3维插值的序列医学影像交互分割重建算法的研究与实现[D]. 合肥: 合肥工业大学, 2010: 19-30.

Kong Weihua. The Research and Implementation of Interactive Medical Image Sequences Segmentation Based on 3D Multidirectional Interpolation Algorithm[D]. Hefei: Hefei University of Technology, 2010: 19-30.

[23] Luo Z Z, Shen H X. Hermite interpolation-based wavelet transform modulus maxima reconstruction algorithm’s application to EMG denoising[J]. Journal of Electronics & Information Technology, 2009, 31(1): 857-860.

[24] Liu B, Huang L J. Multi-scale fusion of well logging data based on wavelet modulus maximum[J]. Journal of China Coal Society, 2010, 35(4): 645-649.

[25] Gray R M. Vector quantization[J]. ASSP Magazine IEEE, 1984, 1(2): 4-29.

[26] 陈善学. 矢量量化技术及其在图像信号处理中的应用研究[D]. 成都: 电子科技大学, 2009: 21-26.

Chen Shanxue. Vector Quantization and Its Application to Image Processing[D]. Chengdu: University of Electronic Science and Technology, 2009: 21-26.

[27] Anuj S, Shantanu H J, Washington M, et al.. Statistical shape analysis: Clustering, learning, and testing[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2005, 27(1): 590-602.

[28] Figueiredo M A T, Jain A K. Unsupervised learning of finite mixture modelsm[J]. IEEE Trans Pattern Analysis and Machine Intelligence. 2002, 24(1): 381-396.

[29] Zhang Yajing, Li Minzan, Qiao Jun, et al.. Segmentation algorithm for apple recognition using image features and artificial neural network [J]. Acta Optica Sinica, 2008, 28(11): 2104-2108.

德爱玲, 郭成安. 基于矢量量化的三维图像自适应分割方法及其应用[J]. 光学学报, 2015, 35(10): 1001002. De Ailing, Guo Cheng′an. A Vector Quantization Based Adaptive Three dimensional Image Segmentation Method and Its Applications[J]. Acta Optica Sinica, 2015, 35(10): 1001002.

基于矢量量化的三维图像自适应分割方法及其应用

关于本站 Cookie 的使用提示

全站搜索

基于矢量量化的三维图像自适应分割方法及其应用

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索