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
    
Automatic urinary image processing
 ZHANG Zan-Chao, JIA Shun-Ren
(Department of Biomedical Engineering, Zhejiang University, Hangzhou 310027, China)
Download:   PDF(1316KB) HTML
Export: BibTeX | EndNote (RIS)      

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．

Published: 18 November 2009
CLC:  TP391.4  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

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

URL:

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


全自动尿液图像识别技术

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.

［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] XU Shu-Chang, ZHANG San-Yuan, ZHANG Yin. Estimation of skin pigment concentration by simulating skin color[J]. J4, 2009, 43(6): 983-986.
[2] CHEN Shuo, ZHANG Feng, CHEN Mo-Wei. Brightness perceptive user model based on simultaneous brightness contrast phenomena[J]. J4, 2009, 43(5): 822-826.