#### Overview COVID X-Ray detection deep neural networks and open datasets
### Overview COVID X-Ray detection deep neural networks and open datasets
Author: Jenia Jitsev, 29.04.2019\
Author: Jenia Jitsev (initiated 29.04.2019)\
(Helmholtz AI Local "Information", Juelich Supercomputing Center (JSC))
Further contributors:
#### Relevant work and papers
General remark: Datasets available are either X-Ray scans or CT scans
##### COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images
* paper: https://arxiv.org/abs/2003.09871
...
...
@@ -22,14 +28,21 @@ The COVID-19 pandemic continues to have a devastating effect on the health and w
- 183 COVID-19 X-Ray images in total (152 train, 31 test)
* Created as a combination and modification of three open access data repositories
- University Montreal Dataset (Joseph Paul Cohen) : COVID-19 Image Data Collection, https://arxiv.org/abs/2003.11597; https://github.com/ieee8023/covid-chestxray-dataset
Project Summary: To build a public open dataset of chest X-ray and CT images of patients which are positive or suspected of COVID-19 or other viral and bacterial pneumonias (MERS, SARS, and ARDS.). Data will be collected from public sources as well as through indirect collection from hospitals and physicians. All images and data will be released publicly in this GitHub repo.
- Joseph Paul Cohen. Postdoctoral Fellow, Mila, University of Montreal
Persons / instituions involved:
- Joseph Paul Cohen. Postdoctoral Fellow, Mila, University of Montreal
- University Waterloo, DarwinAI Corp Dataset (authors of the COVID-net paper): https://github.com/agchung/Figure1-COVID-chestxray-dataset
- related : https://github.com/aildnont/covid-cxr
Related :
- https://github.com/aildnont/covid-cxr
- Data from Radiological Society of North America. RSNA pneumonia detection challenge. https://www.kaggle.com/c/rsna-pneumonia-detection-challenge/data
##### Towards an Efficient Deep Learning Model for COVID-19 Patterns Detection in X-ray Images
* paper: https://arxiv.org/abs/2004.05717
* using EfficientNet Architecture - evolved by Neural Architecture Search (see below for details)
Confronting the pandemic of COVID-19 caused by the new coronavirus, the SARS-CoV-2, is nowadays one of the most prominent challenges of the human species. A key factor in slowing down the virus propagation is rapid diagnosis and isolation of infected patients. Nevertheless, the standard method for COVID-19 identification, the RT-PCR, is time-consuming and in short supply due to the pandemic.
...
...
@@ -38,7 +51,7 @@ Researchers around the world have been trying to find alternative screening meth
* UFOP, Computer Science Department, University of Outro Preto, Brazil
* Network architecture based on EfficientNet - derived from Neural Architecture Search by Google Brain group
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, https://arxiv.org/abs/1905.11946
...
...
@@ -46,7 +59,9 @@ Researchers around the world have been trying to find alternative screening meth
To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.4% top-1 / 97.1% top-5 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet. Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters. Source code is at this https URL.
