{
  "id": 178105,
  "title": "I feel lost about using the images for a model",
  "url": "/competitions/osic-pulmonary-fibrosis-progression/discussion/178105",
  "author_name": "",
  "post_date": "2020-08-28T16:18:06.743505100Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hello! This is my first competition and I have never worked with images (I have only done basic ML projects and I have used some NN). <br>\nI searched on the discussion page but I didn't found too much information about how to use DICOM images for a model.<br>\nI have already done an extensive analysis and EDA of the data, but I don't know how to continue.<br>\nAnyone can recommend me some article or some paper to get started with my model?</p>\n<p>Thank you!</p>",
  "messages": [
    {
      "id": "989215",
      "postDate": "08/28/2020 16:18:06",
      "content": "<p>Hello! This is my first competition and I have never worked with images (I have only done basic ML projects and I have used some NN). <br>\nI searched on the discussion page but I didn't found too much information about how to use DICOM images for a model.<br>\nI have already done an extensive analysis and EDA of the data, but I don't know how to continue.<br>\nAnyone can recommend me some article or some paper to get started with my model?</p>\n<p>Thank you!</p>",
      "rawMarkdown": "Hello! This is my first competition and I have never worked with images (I have only done basic ML projects and I have used some NN). \nI searched on the discussion page but I didn't found too much information about how to use DICOM images for a model.\nI have already done an extensive analysis and EDA of the data, but I don't know how to continue.\nAnyone can recommend me some article or some paper to get started with my model?\n\nThank you!",
      "votes": null
    },
    {
      "id": "989242",
      "postDate": "08/28/2020 16:42:41",
      "content": "<p>You can take a look at this summary provided by <a href=\"https://www.kaggle.com/sandorkonya\" target=\"_blank\">@sandorkonya</a>. First try and use basic features like mean, std, median, kurtosis obtained from the dicom images. Then you can try lung volume calculation and estimating chest height and things like that later on.</p>\n<p><a href=\"url\" target=\"_blank\">https://www.kaggle.com/c/osic-pulmonary-fibrosis-progression/discussion/165727</a></p>",
      "rawMarkdown": "You can take a look at this summary provided by @sandorkonya. First try and use basic features like mean, std, median, kurtosis obtained from the dicom images. Then you can try lung volume calculation and estimating chest height and things like that later on.\n\n[https://www.kaggle.com/c/osic-pulmonary-fibrosis-progression/discussion/165727](url)",
      "votes": null
    },
    {
      "id": "989243",
      "postDate": "08/28/2020 16:43:37",
      "content": "<p><a href=\"https://www.kaggle.com/carlossouza/osic-autoencoder-training\" target=\"_blank\">This</a> is a great notebook, explaining how to use an auto encoder to make tabular data from the scans.</p>",
      "rawMarkdown": "[This](https://www.kaggle.com/carlossouza/osic-autoencoder-training) is a great notebook, explaining how to use an auto encoder to make tabular data from the scans.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 989242,
      "author_name": "yovinyahathugoda",
      "author_url": "",
      "post_date": "08/28/2020 16:42:41",
      "content": "<p>You can take a look at this summary provided by <a href=\"https://www.kaggle.com/sandorkonya\" target=\"_blank\">@sandorkonya</a>. First try and use basic features like mean, std, median, kurtosis obtained from the dicom images. Then you can try lung volume calculation and estimating chest height and things like that later on.</p>\n<p><a href=\"url\" target=\"_blank\">https://www.kaggle.com/c/osic-pulmonary-fibrosis-progression/discussion/165727</a></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 989243,
      "author_name": "humphreymunn",
      "author_url": "",
      "post_date": "08/28/2020 16:43:37",
      "content": "<p><a href=\"https://www.kaggle.com/carlossouza/osic-autoencoder-training\" target=\"_blank\">This</a> is a great notebook, explaining how to use an auto encoder to make tabular data from the scans.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "989215": "Hello! This is my first competition and I have never worked with images (I have only done basic ML projects and I have used some NN). \nI searched on the discussion page but I didn't found too much information about how to use DICOM images for a model.\nI have already done an extensive analysis and EDA of the data, but I don't know how to continue.\nAnyone can recommend me some article or some paper to get started with my model?\n\nThank you!",
    "989242": "You can take a look at this summary provided by @sandorkonya. First try and use basic features like mean, std, median, kurtosis obtained from the dicom images. Then you can try lung volume calculation and estimating chest height and things like that later on.\n\n[https://www.kaggle.com/c/osic-pulmonary-fibrosis-progression/discussion/165727](url)",
    "989243": "[This](https://www.kaggle.com/carlossouza/osic-autoencoder-training) is a great notebook, explaining how to use an auto encoder to make tabular data from the scans."
  },
  "source": "meta"
}