| Autor: |
Wajid Arshad Abbasi, Syed Ali Abbas, Saiqa Andleeb, Ghafoor ul Islam, Syeda Adin Ajaz, Kinza Arshad, Sadia Khalil, Asma Anjam, Kashif Ilyas, Mohsib Saleem, Jawad Chughtai, Ayesha Abbas |
| Jazyk: |
angličtina |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
Informatics in Medicine Unlocked, Vol 23, Iss , Pp 100540- (2021) |
| Druh dokumentu: |
article |
| ISSN: |
2352-9148 |
| DOI: |
10.1016/j.imu.2021.100540 |
| Popis: |
Early diagnosis of Coronavirus disease 2019 (COVID-19) is significantly important, especially in the absence or inadequate provision of a specific vaccine, to stop the surge of this lethal infection by advising quarantine. This diagnosis is challenging as most of the patients having COVID-19 infection stay asymptomatic while others showing symptoms are hard to distinguish from patients having different respiratory infections such as severe flu and Pneumonia. Due to cost and time-consuming wet-lab diagnostic tests for COVID-19, there is an utmost requirement for some alternate, non-invasive, rapid, and discounted automatic screening system. A chest CT scan can effectively be used as an alternative modality to detect and diagnose the COVID-19 infection. In this study, we present an automatic COVID-19 diagnostic and severity prediction system called COVIDC (COVID-19 detection using CT scans) that uses deep feature maps from the chest CT scans for this purpose. Our newly proposed system not only detects COVID-19 but also predicts its severity by using a two-phase classification approach (COVID vs non-COVID, and COVID-19 severity) with deep feature maps and different shallow supervised classification algorithms such as SVMs and random forest to handle data scarcity. We performed a stringent COVIDC performance evaluation not only through 10-fold cross-validation and an external validation dataset but also in a real setting under the supervision of an experienced radiologist. In all the evaluation settings, COVIDC outperformed all the existing state-of-the-art methods designed to detect COVID-19 with an F1 score of 0.94 on the validation dataset and justified its use to diagnose COVID-19 effectively in the real setting by classifying correctly 9 out of 10 COVID-19 CT scans. We made COVIDC openly accessible through a cloud-based webserver and python code available at https://sites.google.com/view/wajidarshad/software and https://github.com/wajidarshad/covidc. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
