基于图像块匹配的肾小球基底膜自动分割

doi:10.11772/j.issn.1001-9081.2016.11.3201

计算机应用 ›› 2016, Vol. 36 ›› Issue (11): 3201-3206.DOI: 10.11772/j.issn.1001-9081.2016.11.3201

基于图像块匹配的肾小球基底膜自动分割

李创权¹, 路艳蒙², 李穆¹, 李明强¹, 李然¹, 曹蕾¹

1. 南方医科大学生物医学工程学院, 广州 510515;
2. 南方医科大学基础医学院, 广州 510515

收稿日期:2016-04-22 修回日期:2016-05-26 出版日期:2016-11-10 发布日期:2016-11-12
通讯作者: 曹蕾
作者简介:李创权(1990-),男,广东东莞人,硕士研究生,主要研究方向:图像分割;路艳蒙(1970-),女,内蒙古呼和浩特人,副教授,博士,主要研究方向:超微形态学、组织工程学;李穆(1990-),女,湖北天门人,硕士研究生,主要研究方向:图像处理;李明强(1992-),男,安徽阜阳人,主要研究方向:图像处理;李然(1992-),男,河南驻马店人,主要研究方向:图像处理;曹蕾(1974-),女,湖南沅江人,副教授,博士,主要研究方向:图像处理、软件工程。

Automatic segmentation of glomerular basement membrane based on image patch matching

LI Chuangquan¹, LU Yanmeng², LI Mu¹, LI Mingqiang¹, LI Ran¹, CAO Lei¹

1. College of Biomedical Engineering, Southern Medical University, Guangzhou Guangdong 510515, China;
2. College of Basic Medical Sciences, Southern Medical University, Guangzhou Guangdong 510515, China

Received:2016-04-22 Revised:2016-05-26 Online:2016-11-10 Published:2016-11-12

摘要/Abstract

摘要： 为了实现肾小球基底膜的自动分割，提出了一种基于图像块匹配策略的图像自动分割方法。首先，针对肾小球基底膜的特点，将块匹配算法的搜索范围从一幅参考图像扩展到多幅参考图像，并采用了一种改进的搜索方式提高匹配效率；然后，开始搜索最优的图像匹配块；最后，提取最优匹配块对应的标记匹配块进行加权，重组为肾小球基底膜的初始分割结果，经形态学处理后即可得到基底膜最终的分割结果。在采集到的肾小球透射电（TEM）图像上进行测试，算法分割结果与病理专家手动分割结果之间的Jaccard相似系数最低为83%，最高为95%。实验结果表明所提方法能取得精度较高的分割结果。

关键词: 图像分割, 块匹配, 相似性, 透射电镜, 肾小球基底膜

Abstract: An automatic segmentation method based on image patch matching strategy was proposed to realize the automatic segmentation of glomerular basement membrane automatically. First of all, according to the characteristics of the glomerular basement membrane, the search range was extended from a reference image to multiple reference images, and an improved searching method was adopted to improve matching efficiency. Then,the optimal patches were searched out and the label image patches corresponding to the optimal patches were extracted, which were weighted by matching similarity. Finally, the weighted label patches were rearranged as the initial segmentation of glomerular basement membrane, from which the final segmentation could be obtained after morphological processing. On the glomerular Transmission Electron Microscopy (TEM) dataset, the Jaccard coefficient is between 83% and 95%. The experimental results show that the proposed method can achieve higher accuracy.

Key words: image segmentation, patch matching, similarity, transmission electron microscopy, glomerular basement membrane

中图分类号:

TP391.41

李创权, 路艳蒙, 李穆, 李明强, 李然, 曹蕾. 基于图像块匹配的肾小球基底膜自动分割[J]. 计算机应用, 2016, 36(11): 3201-3206.

LI Chuangquan, LU Yanmeng, LI Mu, LI Mingqiang, LI Ran, CAO Lei. Automatic segmentation of glomerular basement membrane based on image patch matching[J]. Journal of Computer Applications, 2016, 36(11): 3201-3206.

参考文献

[1] HAAS M. A reevaluation of routine electron microscopy in the examination of native renal biopsies[J]. Journal of the American Society of Nephrology, 1997, 8(1):70-76.
[2] 尚瑜,尹爱萍.5000例肾脏疾病患者肾组织活检临床病理资料分析[J].中国慢性病预防与控制,2011,19(3):289-291.(SHANG Y,YIN A P.Analysis on clinical pathological data of 5000 cases undergoing renal biopsy[J].Chinese Journal of Prevention and Control of Chronic Diseases,2011,19(3):289-291.)
[3] 丛日华,靳蕊霞.69例膜性肾病临床特点与病理资料分析[J],解放军医学院报,2004,35(10):996-999.(CONG R H,JIN R X.Clinical and pathology features of membranous nephropathy:an analysis of 69 cases[J]. Academic Journal of Chinese Pla Medical School,2004,35(10):996-999.)
[4] ONG S H, GIAM S T, SINNIAH R,et al.Adaptive window-based tracking for the detection of membrane structures in kidney electron micrographs[J]. Machine Vision and Applications,1993,6(4):215-223.
[5] KAMENETSKY I, RANGAYYAN R M, BENEDIKTSSON H. Analysis of the glomerular basement membrane in images of renal biopsies using the split-and-merge method:a pilot study[J]. Journal of Digital Imaging, 2010,23(4):463-474.
[6] RANGAYYAN R M, KAMENETSKY I, BENEDIKTSSON H. Segmentation and analysis of the glomerular basement membrane in renal biopsy samples using active contours:a pilot study[J]. Journal of Digital Imaging,2010,23(3):323-331.
[7] LIU J. Implementation of a semi-automatic tool for analysis of TEM images of kidney samples[D].Uppsala:Uppsala University,2012.
[8] WU H S, DIKMAN S. Segmentation and thickness measurement of glomerular basement membranes from electron microscopy images[J].Journal of Electron Microscopy,2010,59(5):409-418.
[9] OURSELIN S, ROCHE A, PRIMA S, et al. Block matching:a general framework to improve robustness of rigid registration of medical images[C]//Proceedings of the 3rd International Conference on Medical Image Computing and Computer. London:Springer-Verlag, 2000:557-566.
[10] 王敏尤,秦斌杰.基于图像块匹配和测地线活动轮廓模型的肿瘤自动检测[J].中国生物医学工程学报,2007,26(6):951-954.(WANG M Y,QIN B J.Automatic tumor detection based on block matching and geodesic active contour[J]. Chinese Journal of Biomedical Engineering,2007,26(6):951-954.)
[11] 佘广南,陈莹胤,钟丽明,等.基于密集特征匹配的胸片肺野自动分割[J]. 南方医科大学学报,2016,36(1):61-66.(SHE G N, CHEN Y Y, ZHONG L M,et al.Automatic segmentation of lung fields in chest radiographs based on dense matching of local features[J]. Journal of Southern Medical University, 2016,36(1):61-66.)
[12] BARNES C, SHECHTMAN E, FINKELSTEIN A, et al. PatchMatch:a randomized correspondence algorithm for structural image editing[J]. ACM Transactions on Graphics, 2009,28(3):341-352.
[13] BARNES C, SHECHTMAN E, GOLDMAN D B, et al. The generalized patchmatch correspondence algorithm[C]//Proceedings of the 11th European Conference on Computer Vision, LNCS 6316. Berlin:Springer, 2010:29-43.
[14] 山海涛,郭建星,耿则勋.影像匹配中的几种相似性测度的分析[J]. 测绘信息与工程,2003,28(4):11-13.(SHAN H T,GUO J X,DENG Z X.Analysis of several similarity measures on image matching[J]. Journal of Geomatics, 2003,28(4):11-13.)

[1]	杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.
[2]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[3]	沈雪雯, 王晓东, 姚宇. 基于空间分频的超声图像分割注意力网络[J]. 计算机应用, 2021, 41(6): 1828-1835.
[4]	黄梨, 卢龙. 基于长距离依赖编码与深度残差U-Net的缺血性卒中病灶分割[J]. 计算机应用, 2021, 41(6): 1820-1827.
[5]	杨蒙蒙, 张爱华. 基于灰度共生矩阵和同步正交匹配追踪的分形图像压缩[J]. 计算机应用, 2021, 41(5): 1445-1449.
[6]	罗琴, 王艳. 无需初始轮廓的图像分割模型[J]. 计算机应用, 2021, 41(4): 1179-1183.
[7]	董阳, 潘海为, 崔倩娜, 边晓菲, 滕腾, 王邦菊. 面向多模态磁共振脑瘤图像的小样本分割方法[J]. 计算机应用, 2021, 41(4): 1049-1054.
[8]	胡屹杉, 秦品乐, 曾建潮, 柴锐, 王丽芳. 基于特征融合和动态多尺度空洞卷积的超声甲状腺分割网络[J]. 计算机应用, 2021, 41(3): 891-897.
[9]	袁芊芊, 邓洪敏, 王晓航. 基于超像素快速模糊C均值聚类与支持向量机的柑橘病虫害区域分割[J]. 计算机应用, 2021, 41(2): 563-570.
[10]	胡立华, 左威健, 聂瑶瑶. 基于加权相似性度量的特征匹配方法[J]. 计算机应用, 2021, 41(2): 511-516.
[11]	周玉彬, 肖红, 王涛, 姜文超, 熊梦, 贺忠堂. 基于动作周期退化相似性度量的机械轴健康指标构建与剩余寿命预测[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3192-3199.
[12]	原泉, 王艳, 李玉先. 距离保持水平集演化模型的快速实现算法[J]. 计算机应用, 2020, 40(9): 2743-2747.
[13]	高海军, 曾祥银, 潘大志, 郑伯川. 基于U-Net改进模型的直肠肿瘤分割方法[J]. 计算机应用, 2020, 40(8): 2392-2397.
[14]	李卫中. 基于场景局部特征的多曝光图像融合[J]. 计算机应用, 2020, 40(8): 2365-2371.
[15]	朱琳, 于海涛, 雷新宇, 刘静, 王若凡. 基于MRI图像的阿尔茨海默症患者脑网络特征识别算法[J]. 计算机应用, 2020, 40(8): 2455-2459.

基于图像块匹配的肾小球基底膜自动分割

Automatic segmentation of glomerular basement membrane based on image patch matching

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics