Deakin University
Browse

File(s) not publicly available

Deep Neural Network detection and clinical staging of covid-19 chest x-rays

conference contribution
posted on 2021-10-21, 00:00 authored by Peter RileyPeter Riley
Wolfram and other image classifier deep neural networks (DNNs) were adapted to differentiate covid-19 from normal and other viral pneumonia chest x-rays, giving up to 100% accuracy on 3x1200 training images. Another DNN gave an initial covid-19 clinical staging accuracy of 80% on just 80 images (work in progress). Methods to improve the training data by employing routine and AI-assisted Quality Assurance are discussed and assessed.

History

Event

Wolfram Virtual Technology Conference 2021

Publisher

Wolfram Research Inc

Location

virtual

Place of publication

https://www.wolfram.com/broadcast/video.php?c=104&disp=list&v=3488&p=2

Start date

2021-10-12

End date

2021-10-16

Publication classification

E3 Extract of paper

Editor/Contributor(s)

Dr ElmBanna

Title of proceedings

Neural Networks

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC