{
  "id": 250880,
  "title": "Yet Another Processing Notebook - Filters",
  "url": "/competitions/siim-covid19-detection/discussion/250880",
  "author_name": "",
  "post_date": "2021-07-05T00:29:16.884848700Z",
  "votes": 2,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I noticed a lot of the opacities in this dataset, like pleural effusions, seem to resemble some of the more significant pneumonias (infiltrates) when crunched down to sizes suitable for CNNs. They all become white blobs.</p>\n<p>I found a few sklearn.filters that might help separate the lung tissue a little better. I thought I'd share and see if it helps anyone.</p>\n<p><a href=\"https://www.kaggle.com/davidbroberts/applying-filters-to-chest-x-rays\" target=\"_blank\">https://www.kaggle.com/davidbroberts/applying-filters-to-chest-x-rays</a></p>",
  "messages": [
    {
      "id": "1376212",
      "postDate": "07/05/2021 00:29:16",
      "content": "<p>I noticed a lot of the opacities in this dataset, like pleural effusions, seem to resemble some of the more significant pneumonias (infiltrates) when crunched down to sizes suitable for CNNs. They all become white blobs.</p>\n<p>I found a few sklearn.filters that might help separate the lung tissue a little better. I thought I'd share and see if it helps anyone.</p>\n<p><a href=\"https://www.kaggle.com/davidbroberts/applying-filters-to-chest-x-rays\" target=\"_blank\">https://www.kaggle.com/davidbroberts/applying-filters-to-chest-x-rays</a></p>",
      "rawMarkdown": "I noticed a lot of the opacities in this dataset, like pleural effusions, seem to resemble some of the more significant pneumonias (infiltrates) when crunched down to sizes suitable for CNNs. They all become white blobs.\n\nI found a few sklearn.filters that might help separate the lung tissue a little better. I thought I'd share and see if it helps anyone.\n\nhttps://www.kaggle.com/davidbroberts/applying-filters-to-chest-x-rays",
      "votes": null
    },
    {
      "id": "1376396",
      "postDate": "07/05/2021 05:31:50",
      "content": "<p>Interesting insights 💯👍</p>",
      "rawMarkdown": "Interesting insights 💯👍",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1376396,
      "author_name": "praneshrajendrakumar",
      "author_url": "",
      "post_date": "07/05/2021 05:31:50",
      "content": "<p>Interesting insights 💯👍</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1376212": "I noticed a lot of the opacities in this dataset, like pleural effusions, seem to resemble some of the more significant pneumonias (infiltrates) when crunched down to sizes suitable for CNNs. They all become white blobs.\n\nI found a few sklearn.filters that might help separate the lung tissue a little better. I thought I'd share and see if it helps anyone.\n\nhttps://www.kaggle.com/davidbroberts/applying-filters-to-chest-x-rays",
    "1376396": "Interesting insights 💯👍"
  },
  "source": "meta"
}