Chest X-ray image analysis and classification for COVID-19 pneumonia detection using Deep CNN

  1. Terry Gao
  2. Grace Wang

Reviewed by

Read the full article

Listed in

Log in to save this article

Abstract

In order to speed up the discovery of COVID-19 disease mechanisms, this research developed a new diagnosis platform using deep convolutional neural network (CNN) which is able to assist radiologists with diagnosis by distinguishing COVID-19 pneumonia from non-COVID-19 pneumonia in patients at Middlemore Hospital based on chest X-rays classification and analysis. Such a tool can save time in interpreting chest X-rays and increase the accuracy and thereby enhance our medical capacity for detection and diagnosis COVID-19. The research idea is that a set of X-ray medical lung images (which include normal, infected by bacteria, infected by virus including COVID-19) were used to train a deep CNN which can be able to distinguish between the noise and the useful information and then uses this training to interpret new images by recognizing patterns that indicate certain diseases such as coronavirus infection in the individual images. The supervised learning method is used as the process of learning from the training dataset can be thought of as a doctor supervising the learning process. It becomes more accurate as the number of analyzed images growing. In this way, it imitates the training for a doctor, but the theory is that since it is capable of learning from a far larger set of images than any human, can have the potential of being more accurate.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.08.20.20178913: (What is this?)

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

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    The experiment and software are based on TensorFlow 2.1-GPU, Python 3.7 and CUDA 10.1 for accelerated training.
    TensorFlow
    suggested: (tensorflow, RRID:SCR_016345)
    Python
    suggested: (IPython, RRID:SCR_001658)

    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 10.1101/2020.08.20.20178913v2 on medRxiv
  3. Version published to 10.1101/2020.08.20.20178913v1 on medRxiv