Overview
On Dec 31 the World Health Organisation was made aware of an illness showing similarities to respiratory pneumonia with symptoms that include a fever, cough and shortness of breath . The origins of this virus is believed to be in Wuhan City, the Hubei Province of China and is officially known as COVID-19. The virus belongs to a genome (the genetic material of an organism), that includes SARS Severe Acute Respiratory Syndrome and MERS Middle East Respiratory Syndrome. Given the almost exponential rise of infection rates world wide , early detection of the disease's presence is essential not only to ensure prompt treatment but also to help with the management and control of infection rates in the public domain.
The high infection rates and the shortage of Covid-19 test kits available, increases the necessity of the implementation of an automatic recognition system as a quick alternative to curb the infection rates Thus we propose the use of AI based CT image analysis to detect the virus under Project Treatise of Medical Image Processing v0.2.0.
Learn More
Number of CT Scans collected world-wide, we are continously collecting CT Scans as they become available
Number of X-Ray Scans collected in Asia, EU and US
Machine Learning models ChexNet, DenseNet, ResNet18, ResNet50 and VGGNet are used for transfer learning as pre-trained models
Sponsors Africa Business Integration and Intel Corporation
Machine Learning
We propose the use of Deep Neural Networks. As an initial experiment the CheXNeXt Pneumonia Detection Model was used as a baseline architecture where transfer learning was used to detect pneumonia. Secondly three different convolutional neural network architectures (ResNet50, VGGNet and DenseNet) was used to detect Coronavirus infected patients via chest X-rays.
CheXNeXt
CheXNeXt is a Deep Learning algorithm to concurrently detect 14 clinically important diseases in chest radiographs - by Stanford ML Group
VGGNet
VGGNet (Visual Geometry Group Neural Network) is a convolutional neural network for large-scale visual recognition - by Visual Geometry Group University of Oxford
Deep Learning Frameworks
Project TMIP 2019-nCoV makes use of open source deep learning frameworks to build COVID-19 classification algorithms
Collaboration
Project TMIP 2019-nCoV Detection welcomes contributors and collaboration opportunities. Data sets and software contributions will help us scale the project throughout the world.
Scalability
2019-nCoV AI Cloud is built on Intel Xeon Scalable Processors for accelerated deep learning and inference workloads in the Cloud.
Contact Us
TMIP 2019-nCoV
Treatise of Medical Image Processing (TMIP) is an Open source project initiated by Intel Software Innovators. The project is licensed under the MIT License
Cape Town
South Africa
info@4ir-abi.co.za