Corpus ID: 211482404

Unsupervised learning of multimodal image registration using domain adaptation with projected Earth Move's discrepancies

@article{Heinrich2020UnsupervisedLO,
  title={Unsupervised learning of multimodal image registration using domain adaptation with projected Earth Move's discrepancies},
  author={M. Heinrich and L. Hansen},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.14107}
}
  • M. Heinrich, L. Hansen
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Multimodal image registration is a very challenging problem for deep learning approaches. Most current work focuses on either supervised learning that requires labelled training scans and may yield models that bias towards annotated structures or unsupervised approaches that are based on hand-crafted similarity metrics and may therefore not outperform their classical non-trained counterparts. We believe that unsupervised domain adaptation can be beneficial in overcoming the current limitations… CONTINUE READING

    References

    SHOWING 1-10 OF 17 REFERENCES
    Weakly-supervised convolutional neural networks for multimodal image registration
    • 118
    • PDF
    A Deep Metric for Multimodal Registration
    • 140
    • PDF
    Memory-efficient 2.5D convolutional transformer networks for multi-modal deformable registration with weak label supervision applied to whole-heart CT and MRI scans
    • 3
    Unpaired Multi-Modal Segmentation via Knowledge Distillation
    • 22
    • PDF
    Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
    • 461
    • Highly Influential
    • PDF
    Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation
    • 103
    • Highly Influential
    • PDF
    Evaluation of MRI to Ultrasound Registration Methods for Brain Shift Correction: The CuRIOUS2018 Challenge
    • 15
    • PDF
    Deep MR to CT Synthesis Using Unpaired Data
    • 288
    • PDF
    Diffusion Distance for Histogram Comparison
    • Haibin Ling, K. Okada
    • Mathematics, Computer Science
    • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
    • 2006
    • 258
    • Highly Influential
    • PDF