{
  "id": 255491,
  "title": "Which label represents a COVID-19 case?",
  "url": "/competitions/siim-covid19-detection/discussion/255491",
  "author_name": "",
  "post_date": "2021-07-27T17:38:19.787520800Z",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi all,</p>\n<p>I've checked the attributes in the dicom files, the <code>train_study_level.csv</code> file, and the <code>train_image_level.csv</code> file, yet I still don't understand which labels represent a positive or negative COVID-19 case.</p>",
  "messages": [
    {
      "id": "1401987",
      "postDate": "07/27/2021 17:38:19",
      "content": "<p>Hi all,</p>\n<p>I've checked the attributes in the dicom files, the <code>train_study_level.csv</code> file, and the <code>train_image_level.csv</code> file, yet I still don't understand which labels represent a positive or negative COVID-19 case.</p>",
      "rawMarkdown": "Hi all,\n\nI've checked the attributes in the dicom files, the `train_study_level.csv` file, and the `train_image_level.csv` file, yet I still don't understand which labels represent a positive or negative COVID-19 case.",
      "votes": null
    },
    {
      "id": "1402122",
      "postDate": "07/27/2021 21:44:26",
      "content": "<p>I don't believe that we have that information. The goal is not to predict covid or not. The goal is to <code>image object detect</code> opacities (or none) bboxes in images and <code>image classify</code> four classes defined <a href=\"https://www.kaggle.com/c/siim-covid19-detection/discussion/240250\" target=\"_blank\">here</a> for each study. </p>\n<blockquote>\n  <p>Annotators did have access to the COVID status for each patient, but were asked to adhere to the grading system above irrespective of the status. As such, some patients who were COVID negative still had chest radiographs with typical appearances. Similarly, some patients who were COVID positive had atypical appearances, or were negative for pneumonia (no lung opacities), because the grading system is based off the chest radiographic findings alone.</p>\n</blockquote>",
      "rawMarkdown": "I don't believe that we have that information. The goal is not to predict covid or not. The goal is to `image object detect` opacities (or none) bboxes in images and `image classify` four classes defined [here][1] for each study. \n\n>Annotators did have access to the COVID status for each patient, but were asked to adhere to the grading system above irrespective of the status. As such, some patients who were COVID negative still had chest radiographs with typical appearances. Similarly, some patients who were COVID positive had atypical appearances, or were negative for pneumonia (no lung opacities), because the grading system is based off the chest radiographic findings alone.\n[1]: https://www.kaggle.com/c/siim-covid19-detection/discussion/240250",
      "votes": null
    },
    {
      "id": "1402143",
      "postDate": "07/27/2021 22:18:21",
      "content": "<p>Thank you.</p>",
      "rawMarkdown": "Thank you.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1402122,
      "author_name": "cdeotte",
      "author_url": "",
      "post_date": "07/27/2021 21:44:26",
      "content": "<p>I don't believe that we have that information. The goal is not to predict covid or not. The goal is to <code>image object detect</code> opacities (or none) bboxes in images and <code>image classify</code> four classes defined <a href=\"https://www.kaggle.com/c/siim-covid19-detection/discussion/240250\" target=\"_blank\">here</a> for each study. </p>\n<blockquote>\n  <p>Annotators did have access to the COVID status for each patient, but were asked to adhere to the grading system above irrespective of the status. As such, some patients who were COVID negative still had chest radiographs with typical appearances. Similarly, some patients who were COVID positive had atypical appearances, or were negative for pneumonia (no lung opacities), because the grading system is based off the chest radiographic findings alone.</p>\n</blockquote>",
      "votes": null,
      "replies": [
        {
          "id": 1402143,
          "author_name": "chigozirimifebi",
          "author_url": "",
          "post_date": "07/27/2021 22:18:21",
          "content": "<p>Thank you.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1401987": "Hi all,\n\nI've checked the attributes in the dicom files, the `train_study_level.csv` file, and the `train_image_level.csv` file, yet I still don't understand which labels represent a positive or negative COVID-19 case.",
    "1402122": "I don't believe that we have that information. The goal is not to predict covid or not. The goal is to `image object detect` opacities (or none) bboxes in images and `image classify` four classes defined [here][1] for each study. \n\n>Annotators did have access to the COVID status for each patient, but were asked to adhere to the grading system above irrespective of the status. As such, some patients who were COVID negative still had chest radiographs with typical appearances. Similarly, some patients who were COVID positive had atypical appearances, or were negative for pneumonia (no lung opacities), because the grading system is based off the chest radiographic findings alone.\n[1]: https://www.kaggle.com/c/siim-covid19-detection/discussion/240250",
    "1402143": "Thank you."
  },
  "source": "meta"
}