Cycle-Consistent Adversarial Transformers for Unpaired MR Image Translation

Onat Dalmaz, Mahmut Yurt, Salman Ul Hassan Dar, Tolga ÇukurProceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2023 · DOI

Abstract

Translating acquired sequences to missing ones in multi-contrast MRI protocols can dramatically reduce scan costs. Neural network models devised for this purpose are characteristically trained on paired datasets, which can be difficult to compile. Moreover, these models exclusively rely on convolutional operators with undesirable biases towards feature locality and spatial invariance. Here, we present a cycle-consistent translation model, ResViT, to enable training on unpaired datasets. ResViT combines localization power of convolution operators with contextual sensitivity of transformers. Demonstrations on multi-contrast MRI datasets indicate the superiority of ResViT against state-of-the-art translation models.
BibTeX
@inproceedings{dalmaz2023cycle,
  author = {Onat Dalmaz and Mahmut Yurt and Salman Ul Hassan Dar and Tolga Çukur},
  title = {{Cycle-Consistent Adversarial Transformers for Unpaired MR Image Translation}},
  booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
  year = {2023},
  doi = {10.58530/2022/0552},
}

Loading related content...

Figure