DSpace Repository

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

Show simple item record

dc.contributor.author Lopez-Garnier, Santiago
dc.contributor.author Sheen Cortavarria, Patricia
dc.contributor.author Zimic-Peralta, Mirko Juan
dc.date.accessioned 2019-07-04T16:59:21Z
dc.date.available 2019-07-04T16:59:21Z
dc.date.issued 2019
dc.identifier.uri https://hdl.handle.net/20.500.12866/6728
dc.description.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 visual cues used by expert diagnosticians to interpret MODS cultures, suggesting that our model may have the ability to generalize and scale. It performed robustly when validated across held-out laboratory datasets and can be improved upon with data from new laboratories. This CNN can assist laboratory personnel, in low resource settings, and is a step towards facilitating automated diagnostics access to critical areas in developing countries. en_US
dc.language.iso eng
dc.publisher Public Library of Science
dc.relation.ispartofseries PLoS ONE
dc.rights info:eu-repo/semantics/restrictedAccess
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
dc.subject Antitubercular Agents en_US
dc.subject Article en_US
dc.subject artificial neural network en_US
dc.subject automation en_US
dc.subject Automation en_US
dc.subject computer assisted diagnosis en_US
dc.subject controlled study en_US
dc.subject convolutional neural network en_US
dc.subject developing country en_US
dc.subject diagnostic accuracy en_US
dc.subject diagnostic imaging en_US
dc.subject diagnostic test accuracy study en_US
dc.subject digital imaging en_US
dc.subject drug sensitivity en_US
dc.subject human en_US
dc.subject Humans en_US
dc.subject image processing en_US
dc.subject Image Processing, Computer-Assisted en_US
dc.subject laboratory en_US
dc.subject laboratory personnel en_US
dc.subject microscopic observed drug susceptibility en_US
dc.subject microscopy en_US
dc.subject Microscopy en_US
dc.subject Neural Networks (Computer) en_US
dc.subject nonhuman en_US
dc.subject procedures en_US
dc.subject sensitivity and specificity en_US
dc.subject tuberculosis en_US
dc.subject Tuberculosis en_US
dc.subject tuberculostatic agent en_US
dc.title Automatic diagnostics of tuberculosis using convolutional neural networks analysis of MODS digital images en_US
dc.type info:eu-repo/semantics/article
dc.identifier.doi https://doi.org/10.1371/journal.pone.0212094
dc.subject.ocde https://purl.org/pe-repo/ocde/ford#3.02.07
dc.relation.issn 1932-6203


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

info:eu-repo/semantics/restrictedAccess Except where otherwise noted, this item's license is described as info:eu-repo/semantics/restrictedAccess

Search DSpace


Browse

My Account

Statistics