{
  "id": "2204.03804",
  "version": "v1",
  "published": "2022-04-08T01:35:19.000Z",
  "updated": "2022-04-08T01:35:19.000Z",
  "title": "A Learnable Variational Model for Joint Multimodal MRI Reconstruction and Synthesis",
  "authors": [
    "Wanyu Bian",
    "Qingchao Zhang",
    "Xiaojing Ye",
    "Yunmei Chen"
  ],
  "comment": "12 pages",
  "categories": [
    "eess.IV",
    "cs.CV",
    "cs.LG",
    "math.OC"
  ],
  "abstract": "Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and synthesis of multi-modal MRI using incomplete k-space data of several source modalities as inputs. The output of our model includes reconstructed images of the source modalities and high-quality image synthesized in the target modality. Our proposed model is formulated as a variational problem that leverages several learnable modality-specific feature extractors and a multimodal synthesis module. We propose a learnable optimization algorithm to solve this model, which induces a multi-phase network whose parameters can be trained using multi-modal MRI data. Moreover, a bilevel-optimization framework is employed for robust parameter training. We demonstrate the effectiveness of our approach using extensive numerical experiments.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-04-08T01:35:19.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "joint multimodal mri reconstruction",
      "learnable variational model",
      "source modalities",
      "anatomy enriches diagnostic information",
      "multi-modal mri data"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 12,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}