{
  "id": 19522,
  "title": "Some outputs of my model",
  "url": "/competitions/second-annual-data-science-bowl/writeups/ryan-munion-some-outputs-of-my-model",
  "author_name": "",
  "post_date": "2016-03-15T01:44:35.593Z",
  "votes": 2,
  "comment_count": 2,
  "views": 495,
  "content": "<p>I imagine there are going to be a lot of innovative solutions to this competition.  I wanted to post a few outputs of my neural network as I thought they were interesting. The output are volume estimates at 1mm intervals along the long axis of the left ventricle.  Left ventricle ROI was determined by cross-section of 4Ch and 2Ch views.</p>\n\n<p>First some good results:</p>\n\n<p><img src=\"http://i.imgur.com/Efvy7R5.gif\" alt=\"701\" title> <img src=\"http://i.imgur.com/msoBmuH.gif\" alt=\"1081\" title> <img src=\"http://i.imgur.com/yE1QYI6.gif\" alt=\"1031\" title> <img src=\"http://i.imgur.com/MehFshO.gif\" alt=\"812\" title></p>\n\n<p>Here are a few failure cases:\nBad Left Ventricle ROI:</p>\n\n<p><img src=\"http://i.imgur.com/VTJzaJ3.gif\" alt=\"921\" title></p>\n\n<p>Last Sax Slice not within 10mm of end of heart:</p>\n\n<p><img src=\"http://i.imgur.com/79HuRFy.gif\" alt=\"931\" title></p>\n\n<p>I hand labeled 200 of the hearts and then used that data to bootstrap to the entire 1-700 hearts.  I will post a blog about the method at some other point.  I think this method has a lot of room for improvement.</p>",
  "messages": [
    {
      "id": "111508",
      "postDate": "03/15/2016 01:44:35",
      "content": "<p>I imagine there are going to be a lot of innovative solutions to this competition.  I wanted to post a few outputs of my neural network as I thought they were interesting. The output are volume estimates at 1mm intervals along the long axis of the left ventricle.  Left ventricle ROI was determined by cross-section of 4Ch and 2Ch views.</p>\n\n<p>First some good results:</p>\n\n<p><img src=\"http://i.imgur.com/Efvy7R5.gif\" alt=\"701\" title> <img src=\"http://i.imgur.com/msoBmuH.gif\" alt=\"1081\" title> <img src=\"http://i.imgur.com/yE1QYI6.gif\" alt=\"1031\" title> <img src=\"http://i.imgur.com/MehFshO.gif\" alt=\"812\" title></p>\n\n<p>Here are a few failure cases:\nBad Left Ventricle ROI:</p>\n\n<p><img src=\"http://i.imgur.com/VTJzaJ3.gif\" alt=\"921\" title></p>\n\n<p>Last Sax Slice not within 10mm of end of heart:</p>\n\n<p><img src=\"http://i.imgur.com/79HuRFy.gif\" alt=\"931\" title></p>\n\n<p>I hand labeled 200 of the hearts and then used that data to bootstrap to the entire 1-700 hearts.  I will post a blog about the method at some other point.  I think this method has a lot of room for improvement.</p>",
      "rawMarkdown": "I imagine there are going to be a lot of innovative solutions to this competition.  I wanted to post a few outputs of my neural network as I thought they were interesting. The output are volume estimates at 1mm intervals along the long axis of the left ventricle.  Left ventricle ROI was determined by cross-section of 4Ch and 2Ch views.\r\n\r\nFirst some good results:\r\n\r\n![701][1] ![1081][2] ![1031][3] ![812][4]\r\n\r\nHere are a few failure cases:\r\nBad Left Ventricle ROI:\r\n\r\n![921][5]\r\n\r\nLast Sax Slice not within 10mm of end of heart:\r\n\r\n![931][6]\r\n\r\nI hand labeled 200 of the hearts and then used that data to bootstrap to the entire 1-700 hearts.  I will post a blog about the method at some other point.  I think this method has a lot of room for improvement.\r\n\r\n\r\n  [1]: http://i.imgur.com/Efvy7R5.gif\r\n  [2]: http://i.imgur.com/msoBmuH.gif\r\n  [3]: http://i.imgur.com/yE1QYI6.gif\r\n  [4]: http://i.imgur.com/MehFshO.gif\r\n  [5]: http://i.imgur.com/VTJzaJ3.gif\r\n  [6]: http://i.imgur.com/79HuRFy.gif",
      "votes": null
    },
    {
      "id": "111517",
      "postDate": "03/15/2016 04:12:18",
      "content": "<p>@Ryan, I am looking forward to your report: Have you used Spatially Sparse Networks?</p>",
      "rawMarkdown": "Ryan, I am looking forward to your report: Have you used Spatially Sparse Networks?",
      "votes": null
    },
    {
      "id": "111608",
      "postDate": "03/15/2016 18:01:53",
      "content": "<p>I used Spatially Sparse Networks again.  Though it was mostly because I was most familiar with the architecture and didn't have much time to implement.  In fact, I didn't submit earlier simply because I had never even evaluated 501-700 until three days ago.</p>",
      "rawMarkdown": "I used Spatially Sparse Networks again.  Though it was mostly because I was most familiar with the architecture and didn't have much time to implement.  In fact, I didn't submit earlier simply because I had never even evaluated 501-700 until three days ago.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 111517,
      "author_name": "esorar",
      "author_url": "",
      "post_date": "03/15/2016 04:12:18",
      "content": "<p>@Ryan, I am looking forward to your report: Have you used Spatially Sparse Networks?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 111608,
      "author_name": "iamthep",
      "author_url": "",
      "post_date": "03/15/2016 18:01:53",
      "content": "<p>I used Spatially Sparse Networks again.  Though it was mostly because I was most familiar with the architecture and didn't have much time to implement.  In fact, I didn't submit earlier simply because I had never even evaluated 501-700 until three days ago.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "111508": "I imagine there are going to be a lot of innovative solutions to this competition.  I wanted to post a few outputs of my neural network as I thought they were interesting. The output are volume estimates at 1mm intervals along the long axis of the left ventricle.  Left ventricle ROI was determined by cross-section of 4Ch and 2Ch views.\r\n\r\nFirst some good results:\r\n\r\n![701][1] ![1081][2] ![1031][3] ![812][4]\r\n\r\nHere are a few failure cases:\r\nBad Left Ventricle ROI:\r\n\r\n![921][5]\r\n\r\nLast Sax Slice not within 10mm of end of heart:\r\n\r\n![931][6]\r\n\r\nI hand labeled 200 of the hearts and then used that data to bootstrap to the entire 1-700 hearts.  I will post a blog about the method at some other point.  I think this method has a lot of room for improvement.\r\n\r\n\r\n  [1]: http://i.imgur.com/Efvy7R5.gif\r\n  [2]: http://i.imgur.com/msoBmuH.gif\r\n  [3]: http://i.imgur.com/yE1QYI6.gif\r\n  [4]: http://i.imgur.com/MehFshO.gif\r\n  [5]: http://i.imgur.com/VTJzaJ3.gif\r\n  [6]: http://i.imgur.com/79HuRFy.gif",
    "111517": "Ryan, I am looking forward to your report: Have you used Spatially Sparse Networks?",
    "111608": "I used Spatially Sparse Networks again.  Though it was mostly because I was most familiar with the architecture and didn't have much time to implement.  In fact, I didn't submit earlier simply because I had never even evaluated 501-700 until three days ago."
  },
  "source": "meta"
}