{
  "id": 252790,
  "title": "Notebook for detecting CXR anatomy with YOLOv5",
  "url": "/competitions/siim-covid19-detection/discussion/252790",
  "author_name": "",
  "post_date": "2021-07-13T18:47:05.550513700Z",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I made this model while exploring cropping techniques. It seems it's well suited for other things like ROI equalization or segmentation. So I thought I'd share it.</p>\n<p>Currently, it detects 10 classes. Left Lung, Right Lung, Left Clavicle, Right Clavicle, Left Humeral Head, Right Humeral Head, Trachea, Carina, Heart. The BB's are marked on the image and saved as text.</p>\n<p>Notebook: <a href=\"https://www.kaggle.com/davidbroberts/cxr-anatomy-detection-with-yolov5\" target=\"_blank\">https://www.kaggle.com/davidbroberts/cxr-anatomy-detection-with-yolov5</a></p>\n<p>Model Dataset: <a href=\"https://www.kaggle.com/davidbroberts/cxr-anatomy-detection\" target=\"_blank\">https://www.kaggle.com/davidbroberts/cxr-anatomy-detection</a></p>\n<p>I use it in my 'Smart Cropping' notebook: <br>\n<a href=\"https://www.kaggle.com/davidbroberts/smart-cropping-cxr-with-yolov5\" target=\"_blank\">https://www.kaggle.com/davidbroberts/smart-cropping-cxr-with-yolov5</a></p>",
  "messages": [
    {
      "id": "1386872",
      "postDate": "07/13/2021 18:47:05",
      "content": "<p>I made this model while exploring cropping techniques. It seems it's well suited for other things like ROI equalization or segmentation. So I thought I'd share it.</p>\n<p>Currently, it detects 10 classes. Left Lung, Right Lung, Left Clavicle, Right Clavicle, Left Humeral Head, Right Humeral Head, Trachea, Carina, Heart. The BB's are marked on the image and saved as text.</p>\n<p>Notebook: <a href=\"https://www.kaggle.com/davidbroberts/cxr-anatomy-detection-with-yolov5\" target=\"_blank\">https://www.kaggle.com/davidbroberts/cxr-anatomy-detection-with-yolov5</a></p>\n<p>Model Dataset: <a href=\"https://www.kaggle.com/davidbroberts/cxr-anatomy-detection\" target=\"_blank\">https://www.kaggle.com/davidbroberts/cxr-anatomy-detection</a></p>\n<p>I use it in my 'Smart Cropping' notebook: <br>\n<a href=\"https://www.kaggle.com/davidbroberts/smart-cropping-cxr-with-yolov5\" target=\"_blank\">https://www.kaggle.com/davidbroberts/smart-cropping-cxr-with-yolov5</a></p>",
      "rawMarkdown": "I made this model while exploring cropping techniques. It seems it's well suited for other things like ROI equalization or segmentation. So I thought I'd share it.\n\nCurrently, it detects 10 classes. Left Lung, Right Lung, Left Clavicle, Right Clavicle, Left Humeral Head, Right Humeral Head, Trachea, Carina, Heart. The BB's are marked on the image and saved as text.\n\nNotebook: https://www.kaggle.com/davidbroberts/cxr-anatomy-detection-with-yolov5\n\nModel Dataset: https://www.kaggle.com/davidbroberts/cxr-anatomy-detection\n\nI use it in my 'Smart Cropping' notebook: \nhttps://www.kaggle.com/davidbroberts/smart-cropping-cxr-with-yolov5",
      "votes": null
    },
    {
      "id": "1396867",
      "postDate": "07/22/2021 14:51:03",
      "content": "<p>I made a dataset and a train notebook for this model.</p>\n<p>Dataset -&gt; <a href=\"https://www.kaggle.com/davidbroberts/chest-anatomy-yolov5-train-set\" target=\"_blank\">https://www.kaggle.com/davidbroberts/chest-anatomy-yolov5-train-set</a><br>\nTrain notebook -&gt; <a href=\"https://www.kaggle.com/davidbroberts/chest-anatomy-detection-train\" target=\"_blank\">https://www.kaggle.com/davidbroberts/chest-anatomy-detection-train</a></p>\n<p>Feel free to use it as you wish. The images are from the SIIM-COVID19 dataset, so the original license applies.</p>",
      "rawMarkdown": "I made a dataset and a train notebook for this model.\n\nDataset -> https://www.kaggle.com/davidbroberts/chest-anatomy-yolov5-train-set\nTrain notebook -> https://www.kaggle.com/davidbroberts/chest-anatomy-detection-train\n\nFeel free to use it as you wish. The images are from the SIIM-COVID19 dataset, so the original license applies.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1396867,
      "author_name": "davidbroberts",
      "author_url": "",
      "post_date": "07/22/2021 14:51:03",
      "content": "<p>I made a dataset and a train notebook for this model.</p>\n<p>Dataset -&gt; <a href=\"https://www.kaggle.com/davidbroberts/chest-anatomy-yolov5-train-set\" target=\"_blank\">https://www.kaggle.com/davidbroberts/chest-anatomy-yolov5-train-set</a><br>\nTrain notebook -&gt; <a href=\"https://www.kaggle.com/davidbroberts/chest-anatomy-detection-train\" target=\"_blank\">https://www.kaggle.com/davidbroberts/chest-anatomy-detection-train</a></p>\n<p>Feel free to use it as you wish. The images are from the SIIM-COVID19 dataset, so the original license applies.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1386872": "I made this model while exploring cropping techniques. It seems it's well suited for other things like ROI equalization or segmentation. So I thought I'd share it.\n\nCurrently, it detects 10 classes. Left Lung, Right Lung, Left Clavicle, Right Clavicle, Left Humeral Head, Right Humeral Head, Trachea, Carina, Heart. The BB's are marked on the image and saved as text.\n\nNotebook: https://www.kaggle.com/davidbroberts/cxr-anatomy-detection-with-yolov5\n\nModel Dataset: https://www.kaggle.com/davidbroberts/cxr-anatomy-detection\n\nI use it in my 'Smart Cropping' notebook: \nhttps://www.kaggle.com/davidbroberts/smart-cropping-cxr-with-yolov5",
    "1396867": "I made a dataset and a train notebook for this model.\n\nDataset -> https://www.kaggle.com/davidbroberts/chest-anatomy-yolov5-train-set\nTrain notebook -> https://www.kaggle.com/davidbroberts/chest-anatomy-detection-train\n\nFeel free to use it as you wish. The images are from the SIIM-COVID19 dataset, so the original license applies."
  },
  "source": "meta"
}