{
  "id": 217048,
  "title": "EmbedSeg - Embedding-based Instance Segmentation of Microscopy Images",
  "url": "/competitions/hpa-single-cell-image-classification/discussion/217048",
  "author_name": "ilovescience",
  "post_date": "2021-02-05T02:46:51.833000",
  "votes": 7,
  "comment_count": 2,
  "views": 0,
  "content": "<p>A recent paper for segmenting cells in microscope images, may be helpful for this competition:</p>\n<h2>Embedding-based Instance Segmentation of Microscopy Images</h2>\n<blockquote>\n  <p>Automatic detection and segmentation of objects in microscopy images is important for many biological applications. In the domain of natural images, and in particular in the context of city street scenes, embedding-based instance segmentation leads to high-quality results. Inspired by this line of work, we introduce EmbedSeg, an end-to-end trainable deep learning method based on the work by Neven et al. While their approach embeds each pixel to the centroid of any given instance, in EmbedSeg, motivated by the complex shapes of biological objects, we propose to use the medoid instead. Additionally, we make use of a test-time augmentation scheme, and show that both suggested modifications improve the instance segmentation performance on biological microscopy datasets notably. We demonstrate that embedding-based instance segmentation achieves competitive results in comparison to state-of-the-art methods on diverse and biologically relevant microscopy datasets. Finally, we show that the overall pipeline has a small enough memory footprint to be used on virtually all CUDA enabled laptop hardware. Our open-source implementation is available at <a href=\"http://github.com/juglab/EmbedSeg\" target=\"_blank\">this http URL</a>.</p>\n</blockquote>\n<p><a href=\"https://arxiv.org/abs/2101.10033\" target=\"_blank\">Paper</a><br>\n<a href=\"http://github.com/juglab/EmbedSeg\" target=\"_blank\">GitHub</a>.</p>",
  "messages": [
    {
      "id": 1186745,
      "postDate": "2021-02-05T02:46:51.833Z",
      "content": "<p>A recent paper for segmenting cells in microscope images, may be helpful for this competition:</p>\n<h2>Embedding-based Instance Segmentation of Microscopy Images</h2>\n<blockquote>\n  <p>Automatic detection and segmentation of objects in microscopy images is important for many biological applications. In the domain of natural images, and in particular in the context of city street scenes, embedding-based instance segmentation leads to high-quality results. Inspired by this line of work, we introduce EmbedSeg, an end-to-end trainable deep learning method based on the work by Neven et al. While their approach embeds each pixel to the centroid of any given instance, in EmbedSeg, motivated by the complex shapes of biological objects, we propose to use the medoid instead. Additionally, we make use of a test-time augmentation scheme, and show that both suggested modifications improve the instance segmentation performance on biological microscopy datasets notably. We demonstrate that embedding-based instance segmentation achieves competitive results in comparison to state-of-the-art methods on diverse and biologically relevant microscopy datasets. Finally, we show that the overall pipeline has a small enough memory footprint to be used on virtually all CUDA enabled laptop hardware. Our open-source implementation is available at <a href=\"http://github.com/juglab/EmbedSeg\" target=\"_blank\">this http URL</a>.</p>\n</blockquote>\n<p><a href=\"https://arxiv.org/abs/2101.10033\" target=\"_blank\">Paper</a><br>\n<a href=\"http://github.com/juglab/EmbedSeg\" target=\"_blank\">GitHub</a>.</p>",
      "rawMarkdown": "A recent paper for segmenting cells in microscope images, may be helpful for this competition:\n\n## Embedding-based Instance Segmentation of Microscopy Images\n\n> Automatic detection and segmentation of objects in microscopy images is important for many biological applications. In the domain of natural images, and in particular in the context of city street scenes, embedding-based instance segmentation leads to high-quality results. Inspired by this line of work, we introduce EmbedSeg, an end-to-end trainable deep learning method based on the work by Neven et al. While their approach embeds each pixel to the centroid of any given instance, in EmbedSeg, motivated by the complex shapes of biological objects, we propose to use the medoid instead. Additionally, we make use of a test-time augmentation scheme, and show that both suggested modifications improve the instance segmentation performance on biological microscopy datasets notably. We demonstrate that embedding-based instance segmentation achieves competitive results in comparison to state-of-the-art methods on diverse and biologically relevant microscopy datasets. Finally, we show that the overall pipeline has a small enough memory footprint to be used on virtually all CUDA enabled laptop hardware. Our open-source implementation is available at [this http URL](http://github.com/juglab/EmbedSeg).\n\n[Paper](https://arxiv.org/abs/2101.10033)\n[GitHub](http://github.com/juglab/EmbedSeg).",
      "votes": 7
    },
    {
      "id": 1186763,
      "postDate": "2021-02-05T03:00:33.677Z",
      "content": "<p>I'm still reading about this competition, then i don't know what kind of task we are solving. Is this competition about <strong>image segmentation</strong>?</p>",
      "rawMarkdown": "I'm still reading about this competition, then i don't know what kind of task we are solving. Is this competition about **image segmentation**?"
    },
    {
      "id": 1187296,
      "postDate": "2021-02-05T10:56:27.037Z",
      "content": "<p>Very cool thanks for sharing!</p>",
      "rawMarkdown": "Very cool thanks for sharing!"
    }
  ],
  "comments": [
    {
      "id": 1186763,
      "author_name": "Hiram Coria 🧬",
      "author_url": "",
      "post_date": "2021-02-05T03:00:33.677000",
      "content": "<p>I'm still reading about this competition, then i don't know what kind of task we are solving. Is this competition about <strong>image segmentation</strong>?</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 1187296,
      "author_name": "Darien Schettler",
      "author_url": "",
      "post_date": "2021-02-05T10:56:27.037000",
      "content": "<p>Very cool thanks for sharing!</p>",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1186745": "A recent paper for segmenting cells in microscope images, may be helpful for this competition:\n\n## Embedding-based Instance Segmentation of Microscopy Images\n\n> Automatic detection and segmentation of objects in microscopy images is important for many biological applications. In the domain of natural images, and in particular in the context of city street scenes, embedding-based instance segmentation leads to high-quality results. Inspired by this line of work, we introduce EmbedSeg, an end-to-end trainable deep learning method based on the work by Neven et al. While their approach embeds each pixel to the centroid of any given instance, in EmbedSeg, motivated by the complex shapes of biological objects, we propose to use the medoid instead. Additionally, we make use of a test-time augmentation scheme, and show that both suggested modifications improve the instance segmentation performance on biological microscopy datasets notably. We demonstrate that embedding-based instance segmentation achieves competitive results in comparison to state-of-the-art methods on diverse and biologically relevant microscopy datasets. Finally, we show that the overall pipeline has a small enough memory footprint to be used on virtually all CUDA enabled laptop hardware. Our open-source implementation is available at [this http URL](http://github.com/juglab/EmbedSeg).\n\n[Paper](https://arxiv.org/abs/2101.10033)\n[GitHub](http://github.com/juglab/EmbedSeg).",
    "1186763": "I'm still reading about this competition, then i don't know what kind of task we are solving. Is this competition about **image segmentation**?",
    "1187296": "Very cool thanks for sharing!"
  }
}