Pham, Tuan D.
2020-10-13T15:29:58Z
2020-10-13T15:29:58Z
2020
2045-2322
https://doi.org/10.1038/s41598-020-74164-z
http://hdl.handle.net/20.500.12010/14377
The use of imaging data has been reported to be useful for rapid diagnosis of COVID-19.Although
computed tomography (CT) scans show a variety of signs caused by the viral infection, given a large
amount of images, these visual features are difcult and can take a long time to be recognized by
radiologists.Artifcial intelligence methods for automated classifcation of COVID-19 on CT scans
have been found to be very promising. However, current investigation of pretrained convolutional
neural networks (CNNs) for COVID-19 diagnosis using CT data is limited.This study presents an
investigation on 16 pretrained CNNs for classifcation of COVID-19 using a large public database of CT
scans collected from COVID-19 patients and non-COVID-19 subjects.The results show that, using only
6 epochs for training, the CNNs achieved very high performance on the classifcation task.Among the
16 CNNs, DenseNet-201, which is the deepest net, is the best in terms of accuracy, balance between
sensitivity and specifcity, F1 score, and area under curve. Furthermore, the implementation of
transfer learning with the direct input of whole image slices and without the use of data augmentation
provided better classifcation rates than the use of data augmentation. Such a fnding alleviates the
task of data augmentation and manual extraction of regions of interest on CT images, which are
adopted by current implementation of deep-learning models for COVID-19 classifcation.
8 páginas
application/pdf
eng
Scientific reports
reponame:Expeditio Repositorio Institucional UJTL
instname:Universidad de Bogotá Jorge Tadeo Lozano
Comprehensive study on classifcation
COVID‑19
Computed tomography
A comprehensive study on classifcation of COVID‐19 on computed tomography with pretrained convolutional neural networks
Artículo
Síndrome respiratorio agudo grave
COVID-19
SARS-CoV-2
Coronavirus
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/acceptedVersion
Abierto (Texto Completo)
https://doi.org/10.1038/s41598-020-74164-z
http://purl.org/coar/resource_type/c_2df8fbb1