Rxivist logo

Rapid COVID-19 Diagnosis Using Deep Learning of the Computerized Tomography Scans

By Hamed Tabrizchi, Amir Mosavi, Akos Szabo-Gali, Laszlo Nadai

Posted 23 Dec 2020
medRxiv DOI: 10.1101/2020.12.20.20248582

Several studies suggest that COVID-19 may be accompanied by symptoms such as a dry cough, muscle aches, sore throat, and mild to moderate respiratory illness. The symptoms of this disease indicate the fact that COVID-19 causes noticeable negative effects on the lungs. Therefore, considering the health status of the lungs using X-rays and CT scans of the chest can significantly help diagnose COVID-19 infection. Due to the fact that most of the methods that have been proposed to COVID-19 diagnose deal with the lengthy testing time and also might give more false positive and false negative results, this paper aims to review and implement artificial intelligence (AI) image-based diagnosis methods in order to detect coronavirus infection with zero or near to zero false positives and false negatives rates. Besides the already existing AI image-based medical diagnosis method for the other well-known disease, this study aims on finding the most accurate COVID-19 detection method among AI methods such as machine learning (ML) and artificial neural network (ANN), ensemble learning (EL) methods.

Download data

  • Downloaded 153 times
  • Download rankings, all-time:
    • Site-wide: 120,337
    • In epidemiology: 4,950
  • Year to date:
    • Site-wide: 36,362
  • Since beginning of last month:
    • Site-wide: 46,437

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide