Automatic Detection and Characterization of Parasite Eggs using Deep Learning Methods
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 153-156
Abstract
Parasitic infection can be detected by analyzing the microscopic image of fecal slide. The number of parasite eggs found in the slide will be used to determine the degree of infection. Opisthorchis Vivertini (OV) and Minute Intestinal Flukes (MIF) are among the most common parasites found in southeast Asia. OV affects liver whereas MIF affect small intestine. The egg of both parasites have almost the same size and shape which make it difficult to discriminate between them, even for experts. The detection and classification of parasite eggs in the micro-scopic image of the fecal slides can be seen as object detection problem. This work investigates the application of state-of-the-art object detectors to this task. The experimental results show that these deep learning models are capable of correctly detecting and classifying the parasite eggs.Keywords
This publication has 10 references indexed in Scilit:
- CenterNet: Keypoint Triplets for Object Detection2019
- Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countriesCA: A Cancer Journal for Clinicians, 2018
- A deep learning framework to discern and count microscopic nematode eggsScientific Reports, 2018
- Focal Loss for Dense Object Detection2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image Recognition2016
- Detection and classification of parasite eggs for use in helminthic therapy2012
- An expert diagnosis system for classification of human parasite eggs based on multi-class SVMExpert Systems with Applications, 2009
- Automatic identification of human helminth eggs on microscopic fecal specimens using digital image processing and an artificial neural networkIEEE Transactions on Biomedical Engineering, 2001
- Visual pattern recognition by moment invariantsIRE Transactions on Information Theory, 1962