{
  "id": 183742,
  "title": "Question on labels negative_exam_for_pe and pe_present_on_image",
  "url": "/competitions/rsna-str-pulmonary-embolism-detection/discussion/183742",
  "author_name": "Catadanna",
  "post_date": "2020-09-17T22:42:43.397000",
  "votes": 0,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hallo,</p>\n<p>In the competition documentation is written : </p>\n<pre><code>pe_present_on_image - image-level, notes whether any form of PE is present on the image.\nnegative_exam_for_pe - exam-level, whether there are any images in the study that have PE present.\n</code></pre>\n<p>This means to me that negative_exam_for_pe==True, for one study, if at least pe_present_on_image==True for the study.</p>\n<p>Then in the diagram, it is written that for <code>negative_exam_for_pe ==False</code> and <code>Indeterminate==False</code> must have <code>At least one image with pe_present_on_image</code>. </p>\n<p>This is inconsistent with the previous statement, as <code>pe_present_on_image==True</code> when <code>negative_exam_for_pe==True</code>.</p>\n<p>Can someone explain ? Did I misss something ? </p>",
  "messages": [
    {
      "id": 1015085,
      "postDate": "2020-09-17T23:17:56.773Z",
      "content": "<p>More discussion on this can be found here - <br>\n<a href=\"https://www.kaggle.com/c/rsna-str-pulmonary-embolism-detection/discussion/182251\" target=\"_blank\">https://www.kaggle.com/c/rsna-str-pulmonary-embolism-detection/discussion/182251</a></p>",
      "rawMarkdown": "More discussion on this can be found here - \nhttps://www.kaggle.com/c/rsna-str-pulmonary-embolism-detection/discussion/182251"
    },
    {
      "id": 1015076,
      "postDate": "2020-09-17T23:13:37.507Z",
      "content": "<p>Hello! </p>\n<p>if 'negative_exam_for_pe' == True, I think it means that this study does not have PE. So, for this study, all values of 'pe_present_on_image' will be set to 0. </p>\n<p>Therefore, if 'negative_exam_for_pe' == False, that means this exam has some evidence for PE, and for at least one image 'pe_present_on_image' will be set to 1. </p>\n<p>Hope this helps.  </p>",
      "rawMarkdown": "Hello! \n\nif 'negative_exam_for_pe' == True, I think it means that this study does not have PE. So, for this study, all values of 'pe_present_on_image' will be set to 0. \n\nTherefore, if 'negative_exam_for_pe' == False, that means this exam has some evidence for PE, and for at least one image 'pe_present_on_image' will be set to 1. \n\nHope this helps.  "
    },
    {
      "id": 1015054,
      "postDate": "2020-09-17T22:42:43.397Z",
      "content": "<p>Hallo,</p>\n<p>In the competition documentation is written : </p>\n<pre><code>pe_present_on_image - image-level, notes whether any form of PE is present on the image.\nnegative_exam_for_pe - exam-level, whether there are any images in the study that have PE present.\n</code></pre>\n<p>This means to me that negative_exam_for_pe==True, for one study, if at least pe_present_on_image==True for the study.</p>\n<p>Then in the diagram, it is written that for <code>negative_exam_for_pe ==False</code> and <code>Indeterminate==False</code> must have <code>At least one image with pe_present_on_image</code>. </p>\n<p>This is inconsistent with the previous statement, as <code>pe_present_on_image==True</code> when <code>negative_exam_for_pe==True</code>.</p>\n<p>Can someone explain ? Did I misss something ? </p>",
      "rawMarkdown": "Hallo,\n\nIn the competition documentation is written : \n\n```\npe_present_on_image - image-level, notes whether any form of PE is present on the image.\nnegative_exam_for_pe - exam-level, whether there are any images in the study that have PE present.\n```\n\nThis means to me that negative_exam_for_pe==True, for one study, if at least pe_present_on_image==True for the study.\n\nThen in the diagram, it is written that for `negative_exam_for_pe ==False` and `Indeterminate==False` must have `At least one image with pe_present_on_image`. \n\nThis is inconsistent with the previous statement, as `pe_present_on_image==True` when `negative_exam_for_pe==True`.\n\nCan someone explain ? Did I misss something ? "
    }
  ],
  "comments": [
    {
      "id": 1015085,
      "author_name": "Deepta Rajan",
      "author_url": "",
      "post_date": "2020-09-17T23:17:56.773000",
      "content": "<p>More discussion on this can be found here - <br>\n<a href=\"https://www.kaggle.com/c/rsna-str-pulmonary-embolism-detection/discussion/182251\" target=\"_blank\">https://www.kaggle.com/c/rsna-str-pulmonary-embolism-detection/discussion/182251</a></p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 1015076,
      "author_name": "Deepta Rajan",
      "author_url": "",
      "post_date": "2020-09-17T23:13:37.507000",
      "content": "<p>Hello! </p>\n<p>if 'negative_exam_for_pe' == True, I think it means that this study does not have PE. So, for this study, all values of 'pe_present_on_image' will be set to 0. </p>\n<p>Therefore, if 'negative_exam_for_pe' == False, that means this exam has some evidence for PE, and for at least one image 'pe_present_on_image' will be set to 1. </p>\n<p>Hope this helps.  </p>",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1015085": "More discussion on this can be found here - \nhttps://www.kaggle.com/c/rsna-str-pulmonary-embolism-detection/discussion/182251",
    "1015076": "Hello! \n\nif 'negative_exam_for_pe' == True, I think it means that this study does not have PE. So, for this study, all values of 'pe_present_on_image' will be set to 0. \n\nTherefore, if 'negative_exam_for_pe' == False, that means this exam has some evidence for PE, and for at least one image 'pe_present_on_image' will be set to 1. \n\nHope this helps.  ",
    "1015054": "Hallo,\n\nIn the competition documentation is written : \n\n```\npe_present_on_image - image-level, notes whether any form of PE is present on the image.\nnegative_exam_for_pe - exam-level, whether there are any images in the study that have PE present.\n```\n\nThis means to me that negative_exam_for_pe==True, for one study, if at least pe_present_on_image==True for the study.\n\nThen in the diagram, it is written that for `negative_exam_for_pe ==False` and `Indeterminate==False` must have `At least one image with pe_present_on_image`. \n\nThis is inconsistent with the previous statement, as `pe_present_on_image==True` when `negative_exam_for_pe==True`.\n\nCan someone explain ? Did I misss something ? "
  }
}