Identification of Tuberculosis Bacilli in ZN-Stained Sputum Smear Images: A Deep Learning Approach

Moumen El-Melegy, Doaa Mohamed, Tarek ElMelegy, Mostafa Abdelrahman; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0

Abstract


Tuberculosis (TB) is a serious infectious disease that remains a global health problem with an enormous burden of disease. TB spreads widely in low and middle income countries, which depend primarily on ZN-stained sputum smear test using conventional light microscopy in disease diagnosis. In this paper we propose a new deep-learning approach for bacilli localization and classification in conventional ZN-stained microscopic images. The new approach is based on the state of the art Faster Region-based Convolutional Neural Network (RCNN) framework, followed by a CNN to reduce false positive rate. This is the first time to apply this framework to this problem. Our experimental results show significant improvement by the proposed approach compared to existing methods, which will help in accurate disease diagnosis.

Related Material


[pdf]
[bibtex]
@InProceedings{El-Melegy_2019_CVPR_Workshops,
author = {El-Melegy, Moumen and Mohamed, Doaa and ElMelegy, Tarek and Abdelrahman, Mostafa},
title = {Identification of Tuberculosis Bacilli in ZN-Stained Sputum Smear Images: A Deep Learning Approach},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}