An End-to-End System for Automatic Urinary Particle Recognition with Convolutional Neural Network.

Journal: Journal of medical systems
Published Date:

Abstract

The urine sediment analysis of particles in microscopic images can assist physicians in evaluating patients with renal and urinary tract diseases. Manual urine sediment examination is labor-intensive, subjective and time-consuming, and the traditional automatic algorithms often extract the hand-crafted features for recognition. Instead of using the hand-crafted features, in this paper we propose to exploit convolutional neural network (CNN) to learn features in an end-to-end manner to recognize the urinary particle. We treat the urinary particle recognition as object detection and exploit two state-of-the-art CNN-based object detection methods, Faster R-CNN and single shot multibox detector (SSD), along with their variants for urinary particle recognition. We further investigate different factors involving these CNN-based methods to improve the performance of urinary particle recognition. We comprehensively evaluate these methods on a dataset consisting of 5,376 annotated images corresponding to 7 categories of urinary particle, i.e., erythrocyte, leukocyte, epithelial cell, crystal, cast, mycete, epithelial nuclei, and obtain a best mean average precision (mAP) of 84.1% while taking only 72 ms per image on a NVIDIA Titan X GPU.

Authors

  • Yixiong Liang
    School of Information Science and Engineering, Central South University, Changsha, China; Mobile Health Ministry of Education-China Mobile Joint Laboratory, Changsha, China. Electronic address: yxliang@csu.edu.cn.
  • Rui Kang
    School of Information Science and Engineering, Central South University, Changsha, 410083, China.
  • Chunyan Lian
    School of Information Science and Engineering, Central South University, Changsha, 410083, China.
  • Yuan Mao
    School of Information Science and Engineering, Central South University, Changsha, 410083, China.