An Automatic Computer-Based Method for Fast and Accurate Covid-19 Diagnosis

  1. Abdullah Al Jaid Jim
  2. Ibrahim Rafi
  3. Md. Sanaullah Chowdhury
  4. Niloy Sikder
  5. M. A. Parvez Mahmud
  6. Saeed Rubaiee
  7. Mehedi Masud
  8. Anupam Kumar Bairagi
  9. Kangkan Bhakta
  10. Abdullah-Al Nahid

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

At present, the whole world is witnessing a horrifying outbreak caused by the Coronavirus Disease 2019 (COVID-19). The virus responsible for this disease is called SARS-CoV-2. It affects its victims’ respiratory system and causes severe lung inflammation, making it harder for them to breathe. The virus is airborne, and so has a high infection rate. Originated in China last December, the virus has spread across seven continents, affecting the population of over 210 countries, making it one of the fiercest pandemics ever recorded. Despite multiple independent and collaborative attempts to develop a vaccine or a cure, an effective solution is yet to come out. While the disease has put the world in a standstill, detecting the positive subjects and isolating them from the others as soon as possible is the only way to minimize its spread. However, many countries are currently experiencing a massive shortage of diagnostic equipment and medical personals. This insufficiency inspired us to work on a computer-based automatic method for the diagnosis of COVID-19. In this paper, we proposed a sequential Convolutional Neural Network (CNN)-based model to detect COVID-19 through analyzing Computed Tomography (CT) scan images. The model is capable of identifying the disease with almost 92.5% accuracy. We believe the implementation of this model will help the physicians and pathologists all over the world to single out the victims quickly and thus reduce the prevalence of COVID-19.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.07.02.20136721: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    Institutional Review Board Statementnot detected.
    Randomizationnot detected.
    Blindingnot detected.
    Power Analysisnot detected.
    Sex as a biological variablenot detected.

    Table 2: Resources

    No key resources detected.

    Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).

    Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  2. Version published to 10.1101/2020.07.02.20136721v1 on medRxiv