This is a repeat challenge from Phase 3 of DLAI3: (https://www.kaggle.com/c/dlai3-phase3). Please watch out for another challenge from DLAI5 soon.

------------

This is the Phase 3 challenge from the Hackathon of the 3rd Deep Learning and AI Summer/Winter School (DLAI3). More details about the previous challenge can be found at https://www.kaggle.com/c/dlai3/.

Medical image analysis has continually been an area of prominent and growing importance, in both the research and application aspects. However, it is important to realize that the algorithms, methodology, as well as the source of data, need to be strictly scrutinized. Phase 3 is a challenge that provides a mixed dataset of publicly available COVID-19 chest x-ray images from various sources, a pneumonia dataset obtained from a study on children, partially verified thorax CXR images of adults from NIH, and unverified no-finding images from NIH. See below for the sources of these data.
Goal
The goal is to provide the participants a chance to test their skills to come up with a good performance model in turns of the macro F1 score to classify COVID-19 chest x-ray images. The Phase 3 DLAI3 Hackathon will award the top three entries that have a full paper submission to the 11th International Conference on Computational Systems-Biology and Bioinformatics (
[CSBio2020](http://www.csbio.org/2020/)
), under the theme of CHAT-2020 (COVID-19 Health, Analytics, and Technologies). The top three individuals/teams will be provided with complimentary registration for their full paper submission to the ACM ICPS Proceedings of CSBio2020 and will be invited to submit an extended work to a post-conference journal special issue.
Dataset citation
Please cite the kaggle dataset as follows: Jonathan H. Chan, “DLAI3 Hackathon Phase3 COVID-19 CXR Challenge.” Kaggle, doi: [10.34740/KAGGLE/DSV/1347344](https://doi.org/10.34740/KAGGLE/DSV/1347344).
Acknowledgments
The following are the sources and related publications for this dataset:

1) Pneumonia CXR images of children retrieved from Mendeley at:
[https://data.mendeley.com/datasets/rscbjbr9sj/2
](https://data.mendeley.com/datasets/rscbjbr9sj/2)
Related publication:
https://www.cell.com/cell/fulltext/S0092-8674(18)30154-5

2) Cropped COVID-19 + selected images from the following (retrieved July 17, 2020):
[https://github.com/agchung/Actualmed-COVID-chestxray-dataset
](https://github.com/agchung/Actualmed-COVID-chestxray-dataset)
Related publication:
[https://arxiv.org/abs/2003.09871
](https://arxiv.org/abs/2003.09871)v4 Mon, 11 May 2020

3) COVID-19 chest x-ray images from:
[https://github.com/ieee8023/covid-chestxray-dataset
](https://github.com/ieee8023/covid-chestxray-dataset)(Retrieved July 13, 2020)

Images:
[https://github.com/ieee8023/covid-chestxray-dataset/blob/master/images
](https://github.com/ieee8023/covid-chestxray-dataset/blob/master/images)
Metadata:
[https://github.com/ieee8023/covid-chestxray-dataset/blob/master/metadata.csv
](https://github.com/ieee8023/covid-chestxray-dataset/blob/master/metadata.csv)
4) Selected images from:
[https://nihcc.app.box.com/v/ChestXray-NIHCC
](https://nihcc.app.box.com/v/ChestXray-NIHCC)
Publication:
ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on
Weakly-Supervised Classification and Localization of Common Thorax Diseases

[https://arxiv.org/abs/1705.02315
](https://arxiv.org/abs/1705.02315)[v5] Thu, 14 Dec 2017

Semi-verified by:
[https://lukeoakdenrayner.wordpress.com/2017/12/18/the-chestxray14-dataset-problems/comment-page-1/](https://lukeoakdenrayner.wordpress.com/2017/12/18/the-chestxray14-dataset-problems/comment-page-1/)