Abstract
State of the art magnetic resonance (MR) image super-resolution methods (ISR) using convolutional neural networks (CNNs) leverage limited contextual information due to the limited spatial coverage of CNNs. Vision transformers (ViT) learn better global context that is helpful in generating superior quality HR images. We combine local information of CNNs and global information from ViTs for image super resolution and output super resolved images that have superior quality than those produced by state of the art methods. We include extra constraints through multiple novel loss functions that preserve structure and texture information from the low resolution to high resolution images.
Original language | English |
---|---|
Title of host publication | 5th International Conference on Medical Imaging with Deep Learning, MIDL 2022 |
Editors | Ender Konukoglu, Bjoern Menze, Archana Venkataraman, Christian F. Baumgartner, Qi Dou, Shadi Albarqouni |
Place of Publication | London UK |
Publisher | Proceedings of Machine Learning Research (PMLR) |
Pages | 858-878 |
Number of pages | 21 |
Volume | 172 |
Publication status | Published - 2022 |
Event | International Conference on Medical Imaging with Deep Learning 2022 - Zurich, Switzerland Duration: 6 Jul 2022 → 8 Jul 2022 Conference number: 5th https://proceedings.mlr.press/v172/ (Published Proceedings) |
Conference
Conference | International Conference on Medical Imaging with Deep Learning 2022 |
---|---|
Abbreviated title | MIDL 2022 |
Country/Territory | Switzerland |
City | Zurich |
Period | 6/07/22 → 8/07/22 |
Internet address |
|
Keywords
- CNN
- disentanglement
- MRI
- super resolution
- ViT