@inproceedings{DBLP:conf/miccai/QiuQFHSR19,
  author    = {Huaqi Qiu and
               Chen Qin and
               Lo{\"{\i}}c Le Folgoc and
               Benjamin Hou and
               Jo Schlemper and
               Daniel Rueckert},
  title     = {Deep Learning for Cardiac Motion Estimation: Supervised vs. Unsupervised
               Training},
  booktitle = {STACOM@MICCAI},
  series    = {Lecture Notes in Computer Science},
  volume    = {12009},
  pages     = {186--194},
  publisher = {Springer},
  year      = {2019},
  doi = {10.1007/978-3-030-39074-7\_20},
  url = {https://doi.org/10.1007/978-3-030-39074-7\_20},
  abstract = {Deep learning registration methods can provide competitive accuracy with substantially shorter runtimes than traditional registration. This work directly compares supervised training, in which a model regresses to generated ground-truth deformation, with unsupervised training, in which the model optimizes similarity between registered images. Tests on real cardiac MRI show that supervised training produces more regular deformation, while unsupervised training more accurately captures the deformation of anatomical structures in cardiac motion.},
}