Automatic diagnostics of tuberculosis using convolutional neural networks analysis of MODS digital images

PloS One
Santiago Lopez-GarnierMirko Zimic

Abstract

Tuberculosis is an infectious disease that causes ill health and death in millions of people each year worldwide. Timely diagnosis and treatment is key to full patient recovery. The Microscopic Observed Drug Susceptibility (MODS) is a test to diagnose TB infection and drug susceptibility directly from a sputum sample in 7-10 days with a low cost and high sensitivity and specificity, based on the visual recognition of specific growth cording patterns of M. Tuberculosis in a broth culture. Despite its advantages, MODS is still limited in remote, low resource settings, because it requires permanent and trained technical staff for the image-based diagnostics. Hence, it is important to develop alternative solutions, based on reliable automated analysis and interpretation of MODS cultures. In this study, we trained and evaluated a convolutional neural network (CNN) for automatic interpretation of MODS cultures digital images. The CNN was trained on a dataset of 12,510 MODS positive and negative images obtained from three different laboratories, where it achieved 96.63 +/- 0.35% accuracy, and a sensitivity and specificity ranging from 91% to 99%, when validated across held-out laboratory datasets. The model's learned features resemble...Continue Reading

References

Feb 19, 2011·American Journal of Respiratory and Critical Care Medicine·Ming ZhangJacques H Grosset
Oct 19, 2011·The European Respiratory Journal·Marieke J van der WerfDavide Manissero
Mar 6, 2012·Neural Networks : the Official Journal of the International Neural Network Society·Dan CireşanJürgen Schmidhuber
May 23, 2012·International Journal of Health Services : Planning, Administration, Evaluation·Debabar Banerji
Jan 3, 2013·International Journal of Stroke : Official Journal of the International Stroke Society·Geoffrey A Donnan
Oct 11, 2013·IEEE Transactions on Medical Imaging·Stefan JaegerClement J McDonald
Dec 1, 2011·International Journal for Parasitology. Drugs and Drug Resistance·Jozef VercruysseBruno Levecke
Dec 1, 2011·International Journal for Parasitology. Drugs and Drug Resistance·Puji B S AsihJ Kevin Baird
Dec 3, 2014·Neural Networks : the Official Journal of the International Neural Network Society·Tara N SainathBhuvana Ramabhadran
Feb 27, 2015·Nature·Volodymyr MnihDemis Hassabis
May 29, 2015·Nature·Yann LeCunGeoffrey Hinton
Jan 7, 2016·Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society· Xiangyu Chen Jiang Liu
Jan 29, 2016·Nature·David SilverDemis Hassabis
Oct 22, 2016·The Lancet Global Health
Nov 4, 2016·ACG Case Reports Journal·Jose Melendez-RosadoFrank Lukens
Aug 12, 2017·Computers in Biology and Medicine·U K Lopes, J F Valiati
Oct 29, 2017·Proceedings of the National Academy of Sciences of the United States of America·Joshua BeckerDamon Centola
Apr 18, 2018·The International Journal of Tuberculosis and Lung Disease : the Official Journal of the International Union Against Tuberculosis and Lung Disease·J MelendezA Story

❮ Previous
Next ❯

Citations

Feb 14, 2020·Journal of Medical Internet Research·Yejin LeeAntoine Flahault
Mar 19, 2021·Frontiers in Artificial Intelligence·Ruihua GuoChakresh Kumar Jain
Jul 30, 2021·Computers in Biology and Medicine·Ángela Casado-GarcíaYolanda Sáenz
Jul 22, 2021·BMC Medical Informatics and Decision Making·Alison L AntesJames M DuBois

❮ Previous
Next ❯

Methods Mentioned

BETA
feature extraction
X-ray

Software Mentioned

Resc
Theano
AlexNet
RMSProp
GoogleNet
MODS
CNN
Zimic
Keras

Related Concepts

Related Feeds

Antitubercular Agents

Antitubercular agents are pharmacologic agents for treatment of tuberculosis. Discover the latest research on antitubercular agents here.

Antitubercular Agents (ASM)

Antitubercular agents are pharmacologic agents for treatment of tuberculosis. Discover the latest research on antitubercular agents here.