Please wait a minute...
浙江大学学报(工学版)
J4  2009, Vol. 43 Issue (5): 832-838    DOI: 10.3785/j.issn.1008-973X.2009.05.009
自动化技术、计算机技术     
全自动尿液图像识别技术
张赞超,夏顺仁
（浙江大学 生物医学工程学系,浙江 杭州 310027）
Automatic urinary image processing
 ZHANG Zan-Chao, JIA Shun-Ren
(Department of Biomedical Engineering, Zhejiang University, Hangzhou 310027, China)
 全文: PDF(1316 KB)  
摘要：

提出了一种全自动的尿液显微图像处理方法.提出一种新的图像预处理方法,通过拉伸图像中各个像素的灰度值与局部灰度值之间的差来增强图像中目标的边界,通过对局部灰度均值的非线性变换来消除图像中光照不均匀的影响.设计恰当的细胞神经网络（CNN）模板分割图像,采用形态学操作和对边缘链码序列的操作,分离黏连细胞,得到分割的最终结果.在获取目标区域后,提取目标的各种形态学参数和纹理参数,采用多个多层感知（MLP）网络分层次地对目标进行分类,得到全自动的处理结果.通过对大量临床尿液样本图像的测试,该方法获得了良好的分割和自动识别结果,并已经集成到全自动尿液图像分析系统中应用于临床,取得了良好的效果.
关键词： 尿液;  图像分割;  细胞神经网络;  图像增强;  特征提取;  多层感知;  多分类器融合    
Abstract:

A novel approach for automatic urinary microscopic image processing was presented. First, an image preprocessing method enhances the edges of objects by stretching the  difference between every pixel and the local gray mean value, and eliminates the disequilibrium of illumination by nonlinear transform of the local gray mean value. Second, a  suitable template of cellular neural network (CNN) is designed to segment the images, and the morphology operation and the boundary direction code operation are carried out to  get final results. Third, the shape and texture features are extracted from the objects. Finally, a two-layer classifier is built to get the last classify results of the  objects, and each layer is combined by multiple multi-layer perceptron (MLP) networks. The experimental results with many clinical urinary images showed that this approach  provides good boundaries and accurate object identification results. The related algorithms have been successfully integrated into automatic urinalysis systems and gained good  results in clinical applications．
Key words: urine    image segmentation    cellular neural network (CNN)    image enhancement    feature extraction    multilayer perceptron (MLP)    multiple classifier combination
出版日期: 2009-06-01
:  TP391.4  
基金资助:

国家自然科学基金资助项目（60772092）.
通讯作者: 夏顺仁，男，教授，博导.     E-mail: srxia@zju.edu.cn
作者简介: 张赞超（1977－），男，湖南衡山人，博士生，主要从事图像处理和模式识别研究.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
张赞超
夏顺仁

引用本文:

张赞超, 夏顺仁. 全自动尿液图像识别技术[J]. J4, 2009, 43(5): 832-838.

ZHANG Zan-Chao, JIA Shun-Ren. Automatic urinary image processing. J4, 2009, 43(5): 832-838.

链接本文:

http://www.zjujournals.com/xueshu/eng/CN/10.3785/j.issn.1008-973X.2009.05.009    或    http://www.zjujournals.com/xueshu/eng/CN/Y2009/V43/I5/832

［1］ MITSUYAMA S, MOTOIKE J, MATSUO H. Automatic classification of urinary sediment images by using a hierarchical modular neural network ［C］∥ Part of the SPIE Conference on  Image Processing. San Diego: SPIE, 1999．
［2］ LANGLOIS M R, DELANGHE J R, STEYAERT S R, et al. Automated flow cytometry compared with an automated dipstick reader for urinalysis ［J］. Clinical Chemistry, 1999, 45(1):  118122．
［3］ CHAN R W Y, SZETO C C. Advances in the clinical laboratory assessment of urinary sediment ［J］. Clinica Chimica Acta, 2004, 340(1/2): 6778．
［4］ LAKATOS J, BODOR T, ZIDARICS Z, et al. Data processing of digital recordings of microscopic examination of urinary sediment ［J］. Clinica Chimica Acta, 2000, 297(1/2):  225237．
［5］ 蔡永军,刘伟玲,虞启琏. 遗传神经网络在尿沉渣识别中的应用［J］. 医疗卫生装备, 2004(11): 12．
CAI Yong-jun, LIU Wei-ling, YU Qi-lian. Application of genetic neural network to recognition of urine sediment ［J］. Chinese Medical Equipment Journal, 2004(11): 12．
［6］ 沈美丽,陈殿仁. 支持向量机在尿沉渣有形成分分类中的应用［J］. 电子器件, 2006, 29(1): 98101．
SHEN Mei-li, CHEN Dian-ren. Application of support vector machine in the classification of the visible urine sediment components ［J］. Chinese Journal of Electron Devices, 
2006, 29(1): 98101．
［7］ LI Yong-ming, ZENG Xiao-ping. A new strategy for urinary sediment segmentation based on wavelet, morphology and combination method ［J］. Computer Methods and Program in  Biomedicine, 2006, 84(2/3): 162173．
［8］ 张赞超,夏顺仁,段会龙. 基于细胞神经网络的尿沉渣图像分割技术［J］. 浙江大学学报：工学版, 2008, 42(12): 21392144．
ZHANG Zan-chao, XIA Shun-ren, DUAN Hui-long. Cellular neural network based urinary sediment image sedimentation ［J］. Journal of Zhejiang University: Engineering Science, 2008,  42(12): 21392144．
［9］ CHUA L O, YANG L. Cellular neural networks: theory ［J］. IEEE Transactions on Circuits and Systems, 1988, 35(10): 12571272．
［10］ CHUA L O, YANG L. Cellular neural networks: applications ［J］. IEEE Transactions on Circuits and Systems, 1988, 35(10): 12731290．
［11］ GONZALEZ R C, WOODS R E. 数字图像处理学［M］. 北京：电子工业出版社, 2004: 523532．
［12］ SONG X, ABU-MOSTAFA Y, JOSEPH S, et al. Robust image recognition by fusion of contextual information ［J］. Information Fusion V3, 2002, 10(2): 277287．
［13］ SONKA M, HLAVAC V, BOYLE R. Image processing, analysis, and machine vision ［M］. Toronto: International Thomson Publishing, 2002．
［14］ HAGAN M T, DEMUTH H B, BEALE M. 神经网络设计［M］. 北京：机械工业出版社, 2002．
［15］ HAYKIN S. Neural networks: a comprehensive foundation ［M］.London: Prentice Hall, 2004．
［16］ ASOH H, OTSU N. Nonlinear data analysis and multilayer perceptions ［C］∥ International Joint Conference on Neural Networks. San Diego: IEEE, 1989: 411415．
［17］ BREIMAN L. Bagging predictors ［J］. Machine Learning, 1996, 24(2): 123140．
［18］ VAN MERIJN E, LOUIS V. An overview and comparison of voting methods for pattern recognition ［C］∥ Proceeding of the Eighth International Workshop on Frontiers in  Handwriting Recognition (IWFHR’02). Ontario: IEEE, 2002．
［19］ HSU C W, LIN C J. A comparison of methods for multiclass support vector machines ［J］. IEEE Transactions on Neural Networks, 2002, 13(2): 415425．
[1] 廖苗, 赵于前, 曾业战, 黄忠朝, 张丙奎, 邹北骥. 基于支持向量机和椭圆拟合的细胞图像自动分割[J]. 浙江大学学报(工学版), 2017, 51(4): 722-728.
[2] 张建廷,张立民. 新型自适应稳健双边滤波图像分割[J]. 浙江大学学报(工学版), 2016, 50(9): 1703-1710.
[3] 谭海龙, 刘康玲, 金鑫, 石向荣, 梁军. 基于μσ-DWC特征和树结构M-SVM的多维时间序列分类[J]. 浙江大学学报(工学版), 2015, 49(6): 1061-1069.
[4] 白帆, 郑慧峰, 沈平平, 王成, 喻桑桑. 基于花朵特征编码归类的植物种类识别方法[J]. 浙江大学学报(工学版), 2015, 49(10): 1902-1908.
[5] 胡祝华, 赵瑶池, 程杰仁, 彭金莲. 基于改进DRLSE的运动目标分割方法[J]. 浙江大学学报(工学版), 2014, 48(8): 1488-1495.
[6] 王蒙, 林兰芬, 王锋. 基于伪相关反馈的短文本扩展与分类[J]. 浙江大学学报(工学版), 2014, 48(5): 2-.
[7] 刘中, 陈伟海, 吴星明, 邹宇华, 王建华. 基于双目视觉的显著性区域检测[J]. J4, 2014, 48(2): 354-359.
[8] 王蒙, 林兰芬, 王锋. 基于伪相关反馈的短文本扩展与分类[J]. 浙江大学学报(工学版), 2014, 48(10): 1835-1842.
[9] 刘涛, 赵巨峰, 徐之海, 冯华君, 陈慧芳. 基于卡尔曼滤波的红外图像增强算法[J]. J4, 2012, 46(8): 1534-1539.
[10] 施锦河, 沈继忠, 王攀. 四类运动想象脑电信号特征提取与分类算法[J]. J4, 2012, 46(2): 338-344.
[11] 周水琴, 应义斌, 商德胜. 基于形态学的香梨褐变核磁共振成像无损检测[J]. J4, 2012, 46(12): 2141-2145.
[12] 许雪梅, 李丽娴, 张键洋, 倪兰, 黄征宇, 曹建. 透明液体药剂中可见异物跟踪算法[J]. J4, 2012, 46(10): 1822-1830.
[13] 李光廷, 禹卫东. 马尔可夫随机场SAR图像分割的快速实现技术[J]. J4, 2012, 46(10): 1810-1815.
[14] 刘晨彬,潘颖,张海石,黄峰平,夏顺仁. 基于磁共振图像的脑瘤MGMT表达状况检测算法[J]. J4, 2012, 46(1): 170-176.
[15] 吴一全,张晓杰,吴诗婳,张生伟. 基于混沌PSO或分解的二维最小误差阈值分割[J]. J4, 2011, 45(7): 1198-1205.