ai-corona: Radiologist-assistant deep learning framework for COVID-19 diagnosis in chest CT scans.
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..
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:16 |
|---|---|
| Enthalten in: |
PLoS ONE - 16(2021), 5, p e0250952 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Mehdi Yousefzadeh [VerfasserIn] |
|---|
| Links: |
doi.org [kostenfrei] |
|---|
| Themen: |
|---|
| doi: |
10.1371/journal.pone.0250952 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
DOAJ005358140 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | DOAJ005358140 | ||
| 003 | DE-627 | ||
| 005 | 20230503144417.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1371/journal.pone.0250952 |2 doi | |
| 035 | |a (DE-627)DOAJ005358140 | ||
| 035 | |a (DE-599)DOAJf9e22fccb33a4e7d9572dea87cee99ed | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 0 | |a Mehdi Yousefzadeh |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a ai-corona: Radiologist-assistant deep learning framework for COVID-19 diagnosis in chest CT scans. |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a 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. | ||
| 653 | 0 | |a Medicine | |
| 653 | 0 | |a R | |
| 653 | 0 | |a Science | |
| 653 | 0 | |a Q | |
| 700 | 0 | |a Parsa Esfahanian |e verfasserin |4 aut | |
| 700 | 0 | |a Seyed Mohammad Sadegh Movahed |e verfasserin |4 aut | |
| 700 | 0 | |a Saeid Gorgin |e verfasserin |4 aut | |
| 700 | 0 | |a Dara Rahmati |e verfasserin |4 aut | |
| 700 | 0 | |a Atefeh Abedini |e verfasserin |4 aut | |
| 700 | 0 | |a Seyed Alireza Nadji |e verfasserin |4 aut | |
| 700 | 0 | |a Sara Haseli |e verfasserin |4 aut | |
| 700 | 0 | |a Mehrdad Bakhshayesh Karam |e verfasserin |4 aut | |
| 700 | 0 | |a Arda Kiani |e verfasserin |4 aut | |
| 700 | 0 | |a Meisam Hoseinyazdi |e verfasserin |4 aut | |
| 700 | 0 | |a Jafar Roshandel |e verfasserin |4 aut | |
| 700 | 0 | |a Reza Lashgari |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i In |t PLoS ONE |d Public Library of Science (PLoS), 2007 |g 16(2021), 5, p e0250952 |w (DE-627)DOAJ000113018 |x 19326203 |7 nnns |
| 773 | 1 | 8 | |g volume:16 |g year:2021 |g number:5, p e0250952 |
| 856 | 4 | 0 | |u https://doi.org/10.1371/journal.pone.0250952 |z kostenfrei |
| 856 | 4 | 0 | |u https://doaj.org/article/f9e22fccb33a4e7d9572dea87cee99ed |z kostenfrei |
| 856 | 4 | 0 | |u https://doi.org/10.1371/journal.pone.0250952 |z kostenfrei |
| 856 | 4 | 2 | |u https://doaj.org/toc/1932-6203 |y Journal toc |z kostenfrei |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_DOAJ | ||
| 912 | |a SSG-OLC-PHA | ||
| 951 | |a AR | ||
| 952 | |d 16 |j 2021 |e 5, p e0250952 | ||