Lesion-preserving unpaired image-to-image translation between MRI and CT from ischemic stroke patients.

Journal: International journal of computer assisted radiology and surgery
Published Date:

Abstract

PURPOSE: Multiple medical imaging modalities are used for clinical follow-up ischemic stroke analysis. Mixed-modality datasets are challenging, both for clinical rating purposes and for training machine learning models. While image-to-image translation methods have been applied to harmonize stroke patient images to a single modality, they have only been used for paired data so far. In the more common unpaired scenario, the standard cycle-consistent generative adversarial network (CycleGAN) method is not able to translate the stroke lesions properly. Thus, the aim of this work was to develop and evaluate a novel image-to-image translation regularization approach for unpaired 3D follow-up stroke patient datasets.

Authors

  • Alejandro Gutierrez
    Department of Radiology, University of Calgary, Calgary, AB, Canada.
  • Anup Tuladhar
    Department of Radiology, University of Calgary, Calgary, Alberta, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada. Electronic address: anup.tuladhar@ucalgary.ca.
  • Matthias Wilms
    Department of Radiology, University of Calgary, Calgary, AB, Canada.
  • Deepthi Rajashekar
    Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada.
  • Michael D Hill
    Calgary Stroke Program, Departments of Clinical Neurosciences, Radiology, Community Health Sciences, Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada.
  • Andrew Demchuk
    Department of Radiology, University of Calgary, 3330 Hospital Drive NW, Calgary, AB, T2N 4N1, Canada.
  • Mayank Goyal
    Department of Diagnostic Imaging, University of Calgary, Calgary, Alberta, Canada.
  • Jens Fiehler
    Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.
  • Nils D Forkert
    Department of Radiology, University of Calgary, Calgary, Canada. nils.forkert@ucalgary.ca.