{
  "id": 377100,
  "title": "Mediolateral oblique(MLO) view vs Cranial caudal (CC) view and Left laterality vs Right laterality",
  "url": "/competitions/rsna-breast-cancer-detection/discussion/377100",
  "author_name": "dhinesh",
  "post_date": "2023-01-09T21:28:40.448000",
  "votes": 4,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I noticed there are at least 4 acquisition per patient</p>\n<ol>\n<li>Mediolateral oblique(MLO)</li>\n<li>Cranial caudal (CC) </li>\n<li>Left laterality</li>\n<li>Right laterality<br>\nA brief overview about different modalities is given in this article: <a href=\"https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/369262\" target=\"_blank\">https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/369262</a></li>\n</ol>\n<p>My questions are:</p>\n<ol>\n<li>When I training a model, is it advisable to consider only one of the view(MLO/CC) or I should consider both or build two different models for each of the views?</li>\n<li>During training, it is advisable to flight either of the laterality of a standard position. Will this generate erroneous results?</li>\n</ol>\n<p>I strongly believe mishandling of this will cause conflict during training. Any thoughts.</p>\n<p>Thank you.</p>",
  "messages": [
    {
      "id": 2093204,
      "postDate": "2023-01-09T21:28:40.447Z",
      "content": "<p>I noticed there are at least 4 acquisition per patient</p>\n<ol>\n<li>Mediolateral oblique(MLO)</li>\n<li>Cranial caudal (CC) </li>\n<li>Left laterality</li>\n<li>Right laterality<br>\nA brief overview about different modalities is given in this article: <a href=\"https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/369262\" target=\"_blank\">https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/369262</a></li>\n</ol>\n<p>My questions are:</p>\n<ol>\n<li>When I training a model, is it advisable to consider only one of the view(MLO/CC) or I should consider both or build two different models for each of the views?</li>\n<li>During training, it is advisable to flight either of the laterality of a standard position. Will this generate erroneous results?</li>\n</ol>\n<p>I strongly believe mishandling of this will cause conflict during training. Any thoughts.</p>\n<p>Thank you.</p>",
      "rawMarkdown": "I noticed there are at least 4 acquisition per patient\n1. Mediolateral oblique(MLO)\n2. Cranial caudal (CC) \n3. Left laterality\n4. Right laterality\nA brief overview about different modalities is given in this article: https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/369262\n\nMy questions are:\n1. When I training a model, is it advisable to consider only one of the view(MLO/CC) or I should consider both or build two different models for each of the views?\n2. During training, it is advisable to flight either of the laterality of a standard position. Will this generate erroneous results?\n\nI strongly believe mishandling of this will cause conflict during training. Any thoughts.\n\nThank you.\n",
      "votes": 4
    },
    {
      "id": 2127506,
      "postDate": "2023-02-03T00:00:08.967Z",
      "content": "<p>The tissue represented by MLO and CC projection does not fully overlap. So, these two projections complement each other to some extent.</p>",
      "rawMarkdown": "The tissue represented by MLO and CC projection does not fully overlap. So, these two projections complement each other to some extent.",
      "replies": [
        {
          "id": 2135151,
          "postDate": "2023-02-08T13:35:28.367Z",
          "content": "<p>See figures in this paper: <a href=\"https://doi.org/10.1148/rg.e33\" target=\"_blank\">https://doi.org/10.1148/rg.e33</a></p>",
          "rawMarkdown": "See figures in this paper: https://doi.org/10.1148/rg.e33"
        }
      ]
    }
  ],
  "comments": [
    {
      "id": 2127506,
      "author_name": "Antti Isosalo",
      "author_url": "",
      "post_date": "2023-02-03T00:00:08.967000",
      "content": "<p>The tissue represented by MLO and CC projection does not fully overlap. So, these two projections complement each other to some extent.</p>",
      "votes": 0,
      "replies": [
        {
          "id": 2135151,
          "author_name": "Antti Isosalo",
          "author_url": "",
          "post_date": "2023-02-08T13:35:28.367000",
          "content": "<p>See figures in this paper: <a href=\"https://doi.org/10.1148/rg.e33\" target=\"_blank\">https://doi.org/10.1148/rg.e33</a></p>",
          "votes": 0,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2093204": "I noticed there are at least 4 acquisition per patient\n1. Mediolateral oblique(MLO)\n2. Cranial caudal (CC) \n3. Left laterality\n4. Right laterality\nA brief overview about different modalities is given in this article: https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/369262\n\nMy questions are:\n1. When I training a model, is it advisable to consider only one of the view(MLO/CC) or I should consider both or build two different models for each of the views?\n2. During training, it is advisable to flight either of the laterality of a standard position. Will this generate erroneous results?\n\nI strongly believe mishandling of this will cause conflict during training. Any thoughts.\n\nThank you.\n",
    "2127506": "The tissue represented by MLO and CC projection does not fully overlap. So, these two projections complement each other to some extent."
  }
}