README.rst

pl-CT-covidnet

Table of Contents

• Abstract
• Synopsis
• Description
• Arguments
• Models
• Local Build
• Run

Abstract

This ia an app to run COVID-Net CT models on chest CT images.

Synopsis

python ct_covidnet.py                                           \
    [-v <level>] [--verbosity <level>]                          \
    [--version]                                                 \
    [--man]                                                     \
    [--meta]                                                    \
    [--imagefile]                                               \
    <inputDir>
    <outputDir>

Description

ct_covidnet.py is a ChRIS-based plugin for the COVIDNet-UI that performs classification of COVID-19 from chest CT images. More details on the implementation can be found on the paper, COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest CT Images.

Arguments

[-v <level>] [--verbosity <level>]
Verbosity level for app. Not used currently.

[--version]
If specified, print version number.

[--man]
If specified, print (this) man page.

[--meta]
If specified, print plugin meta data.

[--imagefile]
required, name of the image file to be analyzed

Models

The COVID-Net CT-1 L model is downloaded from https://github.com/haydengunraj/COVIDNet-CT/blob/master/docs/models.md

Local Build

DOCKER_BUILDKIT=1 docker build -t local/pl-ct-covidnet .

Run

docker run --rm -v $PWD/in:/incoming -v $PWD/out:/outgoing    \
    darwinai/covidnet-pl-ct ct-covidnet                          \
        --imagefile ex-covid-ct.jpg /incoming /outgoing