In:
PLOS ONE, Public Library of Science (PLoS), Vol. 16, No. 5 ( 2021-5-7), p. e0250952-
Abstract:
The development of medical assisting tools based on artificial intelligence advances is essential in the global fight against COVID-19 outbreak and the future of medical systems. In this study, we introduce ai-corona , a radiologist-assistant deep learning framework for COVID-19 infection diagnosis using chest CT scans. Our framework incorporates an EfficientNetB3-based feature extractor. We employed three datasets; the CC-CCII set, the MasihDaneshvari Hospital (MDH) cohort, and the MosMedData cohort. Overall, these datasets constitute 7184 scans from 5693 subjects and include the COVID-19, non-COVID abnormal (NCA), common pneumonia (CP), non-pneumonia, and Normal classes. We evaluate ai-corona on test sets from the CC-CCII set, MDH cohort, and the entirety of the MosMedData cohort, for which it gained AUC scores of 0.997, 0.989, and 0.954, respectively. Our results indicates ai-corona outperforms all the alternative models. Lastly, our framework’s diagnosis capabilities were evaluated as assistant to several experts. Accordingly, We observed an increase in both speed and accuracy of expert diagnosis when incorporating ai-corona ’s assistance.
Type of Medium:
Online Resource
ISSN:
1932-6203
DOI:
10.1371/journal.pone.0250952
DOI:
10.1371/journal.pone.0250952.g001
DOI:
10.1371/journal.pone.0250952.g002
DOI:
10.1371/journal.pone.0250952.g003
DOI:
10.1371/journal.pone.0250952.g004
DOI:
10.1371/journal.pone.0250952.g005
DOI:
10.1371/journal.pone.0250952.g006
DOI:
10.1371/journal.pone.0250952.g007
DOI:
10.1371/journal.pone.0250952.t001
DOI:
10.1371/journal.pone.0250952.t002
DOI:
10.1371/journal.pone.0250952.t003
DOI:
10.1371/journal.pone.0250952.s001
DOI:
10.1371/journal.pone.0250952.s002
DOI:
10.1371/journal.pone.0250952.s003
DOI:
10.1371/journal.pone.0250952.s004
DOI:
10.1371/journal.pone.0250952.s005
DOI:
10.1371/journal.pone.0250952.s006
DOI:
10.1371/journal.pone.0250952.s007
DOI:
10.1371/journal.pone.0250952.s008
DOI:
10.1371/journal.pone.0250952.s009
DOI:
10.1371/journal.pone.0250952.s010
DOI:
10.1371/journal.pone.0250952.s011
DOI:
10.1371/journal.pone.0250952.r001
DOI:
10.1371/journal.pone.0250952.r002
DOI:
10.1371/journal.pone.0250952.r003
DOI:
10.1371/journal.pone.0250952.r004
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2021
detail.hit.zdb_id:
2267670-3
Permalink