{
  "id": 147333,
  "title": "meaning of training_label_masks",
  "url": "/competitions/prostate-cancer-grade-assessment/discussion/147333",
  "author_name": "lazy_tiger",
  "post_date": "2020-04-30T09:17:08.646000",
  "votes": 0,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi guys,</p>\n\n<p>Can anyone explain the meaning of files in train_label_maksks? I think the pixels with positive values are pixels of interest, but what is the meaning of different positive values?</p>\n\n<p>Thanks</p>",
  "messages": [
    {
      "id": 827428,
      "postDate": "2020-04-30T09:39:06.857Z",
      "content": "<p>It depends a bit on the data provider. </p>\n\n<p>For Radboud, the positive pixels &gt; 1 are epithelium (the cell type from which this cancer type arises) and you also get the Gleason pattern from which the ISUP-grade is calculated. See <a href=\"https://www.kaggle.com/c/prostate-cancer-grade-assessment/overview/additional-resources\">https://www.kaggle.com/c/prostate-cancer-grade-assessment/overview/additional-resources</a> under <strong>ISUP grade</strong>.</p>\n\n<p>Stroma is always benign tissue, the cancer type of interest in this challenge does not arise from the stroma.  </p>\n\n<p>Please note these masks are inherently noisy.</p>\n\n<p>Quote from <a href=\"https://www.kaggle.com/c/prostate-cancer-grade-assessment/data\">https://www.kaggle.com/c/prostate-cancer-grade-assessment/data</a>:\n&gt; \nRadboud: Prostate glands are individually labelled. Valid values are:\n0: background (non tissue) or unknown\n1: stroma (connective tissue, non-epithelium tissue)\n2: healthy (benign) epithelium\n3: cancerous epithelium (Gleason 3)\n4: cancerous epithelium (Gleason 4)\n5: cancerous epithelium (Gleason 5)</p>\n\n<p>&gt; \nKarolinska: Regions are labelled. Valid values are:\n1: background (non tissue) or unknown\n2: benign tissue (stroma and epithelium combined)\n3: cancerous tissue (stroma and epithelium combined)</p>",
      "rawMarkdown": "It depends a bit on the data provider. \n\nFor Radboud, the positive pixels &gt; 1 are epithelium (the cell type from which this cancer type arises) and you also get the Gleason pattern from which the ISUP-grade is calculated. See https://www.kaggle.com/c/prostate-cancer-grade-assessment/overview/additional-resources under **ISUP grade**.\n\nStroma is always benign tissue, the cancer type of interest in this challenge does not arise from the stroma.  \n\nPlease note these masks are inherently noisy.\n\nQuote from https://www.kaggle.com/c/prostate-cancer-grade-assessment/data:\n&gt; \nRadboud: Prostate glands are individually labelled. Valid values are:\n0: background (non tissue) or unknown\n1: stroma (connective tissue, non-epithelium tissue)\n2: healthy (benign) epithelium\n3: cancerous epithelium (Gleason 3)\n4: cancerous epithelium (Gleason 4)\n5: cancerous epithelium (Gleason 5)\n\n&gt; \nKarolinska: Regions are labelled. Valid values are:\n1: background (non tissue) or unknown\n2: benign tissue (stroma and epithelium combined)\n3: cancerous tissue (stroma and epithelium combined)\n",
      "votes": 2,
      "replies": [
        {
          "id": 827459,
          "postDate": "2020-04-30T10:02:22.173Z",
          "content": "<p>I somehow overlook the description. Thanks for pointing it out.</p>",
          "rawMarkdown": "I somehow overlook the description. Thanks for pointing it out."
        }
      ]
    },
    {
      "id": 827403,
      "postDate": "2020-04-30T09:17:08.647Z",
      "content": "<p>Hi guys,</p>\n\n<p>Can anyone explain the meaning of files in train_label_maksks? I think the pixels with positive values are pixels of interest, but what is the meaning of different positive values?</p>\n\n<p>Thanks</p>",
      "rawMarkdown": "Hi guys,\n\nCan anyone explain the meaning of files in train_label_maksks? I think the pixels with positive values are pixels of interest, but what is the meaning of different positive values?\n\nThanks"
    }
  ],
  "comments": [
    {
      "id": 827428,
      "author_name": "Hans Pinckaers",
      "author_url": "",
      "post_date": "2020-04-30T09:39:06.857000",
      "content": "<p>It depends a bit on the data provider. </p>\n\n<p>For Radboud, the positive pixels &gt; 1 are epithelium (the cell type from which this cancer type arises) and you also get the Gleason pattern from which the ISUP-grade is calculated. See <a href=\"https://www.kaggle.com/c/prostate-cancer-grade-assessment/overview/additional-resources\">https://www.kaggle.com/c/prostate-cancer-grade-assessment/overview/additional-resources</a> under <strong>ISUP grade</strong>.</p>\n\n<p>Stroma is always benign tissue, the cancer type of interest in this challenge does not arise from the stroma.  </p>\n\n<p>Please note these masks are inherently noisy.</p>\n\n<p>Quote from <a href=\"https://www.kaggle.com/c/prostate-cancer-grade-assessment/data\">https://www.kaggle.com/c/prostate-cancer-grade-assessment/data</a>:\n&gt; \nRadboud: Prostate glands are individually labelled. Valid values are:\n0: background (non tissue) or unknown\n1: stroma (connective tissue, non-epithelium tissue)\n2: healthy (benign) epithelium\n3: cancerous epithelium (Gleason 3)\n4: cancerous epithelium (Gleason 4)\n5: cancerous epithelium (Gleason 5)</p>\n\n<p>&gt; \nKarolinska: Regions are labelled. Valid values are:\n1: background (non tissue) or unknown\n2: benign tissue (stroma and epithelium combined)\n3: cancerous tissue (stroma and epithelium combined)</p>",
      "votes": 2,
      "replies": [
        {
          "id": 827459,
          "author_name": "lazy_tiger",
          "author_url": "",
          "post_date": "2020-04-30T10:02:22.173000",
          "content": "<p>I somehow overlook the description. Thanks for pointing it out.</p>",
          "votes": 0,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "827428": "It depends a bit on the data provider. \n\nFor Radboud, the positive pixels &gt; 1 are epithelium (the cell type from which this cancer type arises) and you also get the Gleason pattern from which the ISUP-grade is calculated. See https://www.kaggle.com/c/prostate-cancer-grade-assessment/overview/additional-resources under **ISUP grade**.\n\nStroma is always benign tissue, the cancer type of interest in this challenge does not arise from the stroma.  \n\nPlease note these masks are inherently noisy.\n\nQuote from https://www.kaggle.com/c/prostate-cancer-grade-assessment/data:\n&gt; \nRadboud: Prostate glands are individually labelled. Valid values are:\n0: background (non tissue) or unknown\n1: stroma (connective tissue, non-epithelium tissue)\n2: healthy (benign) epithelium\n3: cancerous epithelium (Gleason 3)\n4: cancerous epithelium (Gleason 4)\n5: cancerous epithelium (Gleason 5)\n\n&gt; \nKarolinska: Regions are labelled. Valid values are:\n1: background (non tissue) or unknown\n2: benign tissue (stroma and epithelium combined)\n3: cancerous tissue (stroma and epithelium combined)\n",
    "827403": "Hi guys,\n\nCan anyone explain the meaning of files in train_label_maksks? I think the pixels with positive values are pixels of interest, but what is the meaning of different positive values?\n\nThanks"
  }
}