{
  "id": "1810.04898",
  "version": "v1",
  "published": "2018-10-11T08:36:30.000Z",
  "updated": "2018-10-11T08:36:30.000Z",
  "title": "Perfusion parameter estimation using neural networks and data augmentation",
  "authors": [
    "David Robben",
    "Paul Suetens"
  ],
  "comment": "Presented at the MICCAI 2018 SWITCH workshop (16 September 2018, Granada, Spain)",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Perfusion imaging plays a crucial role in acute stroke diagnosis and treatment decision making. Current perfusion analysis relies on deconvolution of the measured signals, an operation that is mathematically ill-conditioned and requires strong regularization. We propose a neural network and a data augmentation approach to predict perfusion parameters directly from the native measurements. A comparison on simulated CT Perfusion data shows that the neural network provides better estimations for both CBF and Tmax than a state of the art deconvolution method, and this over a wide range of noise levels. The proposed data augmentation enables to achieve these results with less than 100 datasets.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-10-11T08:36:30.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "neural network",
      "perfusion parameter estimation",
      "current perfusion analysis relies",
      "data augmentation enables",
      "acute stroke diagnosis"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}