Urine Sediment Detection Based on Deep Learning

Particle urinary sediment analysis in microscopic images can help doctors assess patients with kidney and urinary tract disease. Manual urine sediment inspection is labor intensive, subjective and time consuming, and traditional automated algorithms often extract handcrafted identification features. In this paper, instead of using manual extraction of features, we use CNN to learn features in an end-to-end manner to identify urine particles. In this paper, urine particle recognition is used as object detection processing, and other advanced target detection algorithms, Faster R-cnn, SSD, and deep learning frameworks such as RestNet and DenseNet, are used to study a new target detection method for urine particle recognition.

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

[2]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[6]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  H. Yalcin,et al.  The comparison of automated urine analyzers with manual microscopic examination for urinalysis automated urine analyzers and manual urinalysis , 2016, Practical laboratory medicine.

[8]  Walter Hofmann,et al.  European Urinalysis Guidelines , 2000, Scandinavian journal of clinical and laboratory investigation. Supplementum.

[9]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

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

[11]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[12]  Abdul Aziz,et al.  Improved Extraction of Objects from Urine Microscopy Images with Unsupervised Thresholding and Supervised U-net Techniques , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

[14]  A. Eltom,et al.  Thyroglobulin in serum as an indicator of iodine status during pregnancy. , 2000, Scandinavian journal of clinical and laboratory investigation.

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

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

[17]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[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.