{
  "fetched_at": "2026-10-24T16:49:04Z",
  "source_url": "https://www.kaggle.com/competitions/convolutional-neural-network-cnn-practice/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Context\nThe whole world is suffering from COVID-19 disease and its proper and timely diagnosis is the need of the hour. So for building an efficient AI-based diagnostic system we have collected Chest ray images from different sources so that we can train our CNN model for automating the whole diagnosis method. Therefore we have collected Chest ray images from different sources and research papers and combined them to create one comprehensive dataset that can be used by research community.\n\nThis dataset is also used in COVID Lite paper which has shown significant results by building novel CNN based solution.\n\n\n## Content\nThis dataset consists of a posteroanterior (PA) view of chest X-ray images comprising Normal, Viral, and CVOID-19 affected patients. There are total 1823 CXR images.\n\n\n## Acknowledgements\nPlease cite these papers if you are using it for any scientific purpose:\n\n   D. Kermany, K. Zhang, M. Goldbaum, Large dataset of labeled optical coherence tomography (oct) and chest x-ray images, Mendeley Data, v3\n    http://dx. doi. org/10.17632/rscbjbr9sj 3 (2018).\n    C. J. P, P. Morrison, D. L, Covid-19 image data collection, arxiv, arXiv preprint arXiv:2003.11597 (2020). URL https://github.com/ieee8023/covid-chestxray-dataset\n    Z.-H. Chen, Mask-rcnn detection of covid-19 pneumonia symptoms by employing stacked autoencoders in deep unsupervised learning on low-dose\n    high resolution ct (2020). doi:10.21227/4kcm-m312.URL http://dx.doi.org/10.21227/4kcm-m312\n    D. S. et.al, Covid19action-radiology-cxr (2020). doi:10.21227/s7pw-jr18.\n    URL http://dx.doi.org/10.21227/s7pw-jr18\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "This is the home page of the competition. In this section, you should aim to succinctly introduce the competition.\ndsldfs;dlfks;lf\nAll of the content on Kaggle is written in [markdown](https://github.com/showdownjs/showdown/wiki/Showdown's-Markdown-syntax). If you are copy-pasting from another application, like Word or your browser, you may need to clean up the markdown or html for things to display properly.\n\nIf this is your first time creating a competition, please refer to our [Getting Started Guide](https://www.kaggle.com/docs/competitions-setup) for help. Here is a handy link to [Kaggle's competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on submitting predictions.\n\n**Goal:** When you write this section, try to summarize your competition’s goal. It will help your participants quickly understand their objective.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}