{
  "id": 453958,
  "title": "Surface DSC (Dice Similarity Coefficient)",
  "url": "/competitions/blood-vessel-segmentation/discussion/453958",
  "author_name": "Gunes Evitan",
  "post_date": "2023-11-08T11:10:56.090000",
  "votes": 33,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I found this paper that proposes the metric used in this competition. <a href=\"https://arxiv.org/pdf/1809.04430.pdf\" target=\"_blank\">https://arxiv.org/pdf/1809.04430.pdf</a></p>\n<p><strong>Edit:</strong> I just read the paper and I really liked the selection of this metric. As the paper states \"The principal factor that determines whether or not automatic segmentation is time-saving during the radiotherapy workflow is the degree to which automated segmentations require<br>\ncorrection by oncologists.\". This metric basically gives less score to predictions that require more time to fix.</p>\n<p><img src=\"https://i.ibb.co/n1x6fpL/Screenshot-from-2023-11-08-14-07-55.png\" alt=\"metric\"></p>",
  "messages": [
    {
      "id": 2517294,
      "postDate": "2023-11-08T11:10:56.090Z",
      "content": "<p>I found this paper that proposes the metric used in this competition. <a href=\"https://arxiv.org/pdf/1809.04430.pdf\" target=\"_blank\">https://arxiv.org/pdf/1809.04430.pdf</a></p>\n<p><strong>Edit:</strong> I just read the paper and I really liked the selection of this metric. As the paper states \"The principal factor that determines whether or not automatic segmentation is time-saving during the radiotherapy workflow is the degree to which automated segmentations require<br>\ncorrection by oncologists.\". This metric basically gives less score to predictions that require more time to fix.</p>\n<p><img src=\"https://i.ibb.co/n1x6fpL/Screenshot-from-2023-11-08-14-07-55.png\" alt=\"metric\"></p>",
      "rawMarkdown": "I found this paper that proposes the metric used in this competition. https://arxiv.org/pdf/1809.04430.pdf\n\n**Edit:** I just read the paper and I really liked the selection of this metric. As the paper states \"The principal factor that determines whether or not automatic segmentation is time-saving during the radiotherapy workflow is the degree to which automated segmentations require\ncorrection by oncologists.\". This metric basically gives less score to predictions that require more time to fix.\n\n![metric](https://i.ibb.co/n1x6fpL/Screenshot-from-2023-11-08-14-07-55.png)",
      "votes": 33
    },
    {
      "id": 2527969,
      "postDate": "2023-11-17T02:31:22.737Z",
      "rawMarkdown": "",
      "isDeleted": true
    }
  ],
  "comments": [
    {
      "id": 2527969,
      "author_name": "",
      "author_url": "",
      "post_date": "2023-11-17T02:31:22.737000",
      "content": "",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2517294": "I found this paper that proposes the metric used in this competition. https://arxiv.org/pdf/1809.04430.pdf\n\n**Edit:** I just read the paper and I really liked the selection of this metric. As the paper states \"The principal factor that determines whether or not automatic segmentation is time-saving during the radiotherapy workflow is the degree to which automated segmentations require\ncorrection by oncologists.\". This metric basically gives less score to predictions that require more time to fix.\n\n![metric](https://i.ibb.co/n1x6fpL/Screenshot-from-2023-11-08-14-07-55.png)",
    "2527969": ""
  }
}