{
  "id": "2001.10155",
  "version": "v1",
  "published": "2020-01-28T03:56:42.000Z",
  "updated": "2020-01-28T03:56:42.000Z",
  "title": "An Unsupervised Learning Model for Medical Image Segmentation",
  "authors": [
    "Junyu Chen",
    "Eric C. Frey"
  ],
  "categories": [
    "cs.CV",
    "cs.LG",
    "eess.IV"
  ],
  "abstract": "For the majority of the learning-based segmentation methods, a large quantity of high-quality training data is required. In this paper, we present a novel learning-based segmentation model that could be trained semi- or un- supervised. Specifically, in the unsupervised setting, we parameterize the Active contour without edges (ACWE) framework via a convolutional neural network (ConvNet), and optimize the parameters of the ConvNet using a self-supervised method. In another setting (semi-supervised), the auxiliary segmentation ground truth is used during training. We show that the method provides fast and high-quality bone segmentation in the context of single-photon emission computed tomography (SPECT) image.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-01-28T03:56:42.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "medical image segmentation",
      "unsupervised learning model",
      "auxiliary segmentation ground truth",
      "high-quality bone segmentation",
      "convolutional neural network"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}