Improved Extraction of Objects from Urine Microscopy Images with Unsupervised Thresholding and Supervised U-net Techniques

We propose a novel unsupervised method for extracting objects from urine microscopy images and also applied U-net for extracting these objects. We fused these proposed methods with a known edge thresholding technique from an existing work on segmentation of urine microscopic images. Comparison between our proposed methods and the existing work showed that for certain object types the proposed unsupervised method with or without edge thresholding outperforms the other methods, while in other cases the U-net method with or without edge thresholding outperforms the other methods. Overall the proposed unsupervised method along with edge thresholding worked the best by extracting maximum number of objects and minimum number of artifacts. On a test dataset, the artifact to object ratio for the proposed unsupervised method was 0.71, which is significantly better than that of 1.26 for the existing work. The proposed unsupervised method along with edge thresholding extracted 3208 objects as compared to 1608 by the existing work. To the best of our knowledge this is the first application of Deep Learning for extraction of clinically significant objects in urine microscopy images.

[1]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[2]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Wayne Niblack,et al.  An introduction to digital image processing , 1986 .

[4]  Yong-Ming Li,et al.  A new strategy for urinary sediment segmentation based on wavelet, morphology and combination method , 2006, Comput. Methods Programs Biomed..

[5]  Shi Zhang,et al.  Urinary Sediment Images Segmentation Based on Efficient Gabor flters , 2007, 2007 IEEE/ICME International Conference on Complex Medical Engineering.

[6]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Huilong Duan,et al.  Cellular Neural Network Based Urinary Image Segmentation , 2007, Third International Conference on Natural Computation (ICNC 2007).

[8]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[9]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[10]  Matti Pietikäinen,et al.  Adaptive document image binarization , 2000, Pattern Recognit..

[11]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[12]  Zhang Shi,et al.  Urinary Sediment Overlapping Cells Image Segmentation Based on Combination Strategy , 2008, 2008 International Symposium on Computational Intelligence and Design.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Sumeet Chourasiya,et al.  Automatic Red Blood Cell Counting using Watershed Segmentation , 2014 .

[17]  Keiichi Abe,et al.  Topological structural analysis of digitized binary images by border following , 1985, Comput. Vis. Graph. Image Process..

[18]  Hongwen Luo,et al.  Mumford-Shah Segmentation for Microscopic Image of the Urinary Sediment , 2007, 2007 1st International Conference on Bioinformatics and Biomedical Engineering.

[19]  Meng Kang,et al.  A Urinary Sediment Segmentation Algorithm of Cast and Epithelial Cells , 2013 .

[20]  S. Osher,et al.  Algorithms Based on Hamilton-Jacobi Formulations , 1988 .

[21]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[22]  Xian Jiang,et al.  Urine Sediment Image Segmentation Based on Level Set and Mumford-Shah Model , 2007, 2007 1st International Conference on Bioinformatics and Biomedical Engineering.

[23]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[24]  Jun Dong,et al.  Detection of Red Blood Cell in Urine Micrograph , 2009, 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

[25]  Lin Chen,et al.  Automatic detecting and recognition of casts in urine sediment images , 2009, 2009 International Conference on Wavelet Analysis and Pattern Recognition.

[26]  Jiang Shen,et al.  A Segmentation Method Based on Standard Difference Gradient with Dual-Threshold for Urinary Sediment Visible Components , 2017, 2017 4th International Conference on Information Science and Control Engineering (ICISCE).

[27]  Z. Chen,et al.  Segmentation of Complex Microscopic Cell Image Based on Contourlet and Level Set , 2012 .