{
  "id": 318328,
  "title": "Dataset: Images converted to PNG with metadata in .csv",
  "url": "/competitions/unifesp-x-ray-body-part-classifier/discussion/318328",
  "author_name": "",
  "post_date": "2022-04-11T20:00:13.447623500Z",
  "votes": 16,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I converted all the images to PNG format, 512pixels, and add the metadata extracted from the image files in a single dataset:</p>\n<p><a href=\"https://www.kaggle.com/datasets/ibombonato/xray-body-images-in-png-unifesp-competion\" target=\"_blank\">https://www.kaggle.com/datasets/ibombonato/xray-body-images-in-png-unifesp-competion</a></p>\n<p>This can speed up the train time from hours to minutes, since the DICOM files are very slow to read.</p>\n<p>I also publish a starter notebook using the images with Fast.ai:</p>\n<p><a href=\"https://www.kaggle.com/code/ibombonato/x-ray-body-part-fastai-with-png-images-starter\" target=\"_blank\">https://www.kaggle.com/code/ibombonato/x-ray-body-part-fastai-with-png-images-starter</a></p>",
  "messages": [
    {
      "id": "1752500",
      "postDate": "04/11/2022 20:00:13",
      "content": "<p>I converted all the images to PNG format, 512pixels, and add the metadata extracted from the image files in a single dataset:</p>\n<p><a href=\"https://www.kaggle.com/datasets/ibombonato/xray-body-images-in-png-unifesp-competion\" target=\"_blank\">https://www.kaggle.com/datasets/ibombonato/xray-body-images-in-png-unifesp-competion</a></p>\n<p>This can speed up the train time from hours to minutes, since the DICOM files are very slow to read.</p>\n<p>I also publish a starter notebook using the images with Fast.ai:</p>\n<p><a href=\"https://www.kaggle.com/code/ibombonato/x-ray-body-part-fastai-with-png-images-starter\" target=\"_blank\">https://www.kaggle.com/code/ibombonato/x-ray-body-part-fastai-with-png-images-starter</a></p>",
      "rawMarkdown": "I converted all the images to PNG format, 512pixels, and add the metadata extracted from the image files in a single dataset:\n\nhttps://www.kaggle.com/datasets/ibombonato/xray-body-images-in-png-unifesp-competion\n\nThis can speed up the train time from hours to minutes, since the DICOM files are very slow to read.\n\nI also publish a starter notebook using the images with Fast.ai:\n\nhttps://www.kaggle.com/code/ibombonato/x-ray-body-part-fastai-with-png-images-starter",
      "votes": null
    },
    {
      "id": "2033427",
      "postDate": "11/17/2022 09:00:55",
      "content": "<p>Hi, can you share the exact code that you used to convert dicom to png? I need to know it to reproduce the results </p>",
      "rawMarkdown": "Hi, can you share the exact code that you used to convert dicom to png? I need to know it to reproduce the results",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2033427,
      "author_name": "kyuheejo",
      "author_url": "",
      "post_date": "11/17/2022 09:00:55",
      "content": "<p>Hi, can you share the exact code that you used to convert dicom to png? I need to know it to reproduce the results </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1752500": "I converted all the images to PNG format, 512pixels, and add the metadata extracted from the image files in a single dataset:\n\nhttps://www.kaggle.com/datasets/ibombonato/xray-body-images-in-png-unifesp-competion\n\nThis can speed up the train time from hours to minutes, since the DICOM files are very slow to read.\n\nI also publish a starter notebook using the images with Fast.ai:\n\nhttps://www.kaggle.com/code/ibombonato/x-ray-body-part-fastai-with-png-images-starter",
    "2033427": "Hi, can you share the exact code that you used to convert dicom to png? I need to know it to reproduce the results"
  },
  "source": "meta"
}