MTSR-MRI: Combined Modality Translation and Super-Resolution of Magnetic Resonance Images

Avirup Dey, Mehran Ebrahimi
Medical Imaging with Deep Learning, PMLR 227:743-757, 2024.

Abstract

Magnetic resonance imaging (MRI) is a common non-invasive imaging technique with high soft tissue contrast. Different MRI modalities are used for the diagnosis of various conditions including T1-weighted and T2-weighted MRI. In this paper, we introduce MTSR-MRI, a novel method that can not only upscale low-resolution scans but also translates between the T1-weighted and T2-weighted modalities. This will potentially reduce the scan time or repeat scans by taking low-resolution inputs in one modality and returning plausible high-resolution output in another modality. Due to the ambiguity that persists in image-to-image translation tasks, we consider the distribution of possible outputs in a conditional generative setting. The mapping is distilled in a low-dimensional latent distribution which can be randomly sampled at test time, thus allowing us to generate multiple plausible high-resolution outputs from a given low-resolution input. We validate the proposed method on the BraTS-18 dataset qualitatively and quantitatively using a variety of similarity measures. The implementation of this work will be available at https://github.com/AvirupJU/MTSR-MRI .

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-dey24a, title = {MTSR-MRI: Combined Modality Translation and Super-Resolution of Magnetic Resonance Images}, author = {Dey, Avirup and Ebrahimi, Mehran}, booktitle = {Medical Imaging with Deep Learning}, pages = {743--757}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/dey24a/dey24a.pdf}, url = {https://proceedings.mlr.press/v227/dey24a.html}, abstract = {Magnetic resonance imaging (MRI) is a common non-invasive imaging technique with high soft tissue contrast. Different MRI modalities are used for the diagnosis of various conditions including T1-weighted and T2-weighted MRI. In this paper, we introduce MTSR-MRI, a novel method that can not only upscale low-resolution scans but also translates between the T1-weighted and T2-weighted modalities. This will potentially reduce the scan time or repeat scans by taking low-resolution inputs in one modality and returning plausible high-resolution output in another modality. Due to the ambiguity that persists in image-to-image translation tasks, we consider the distribution of possible outputs in a conditional generative setting. The mapping is distilled in a low-dimensional latent distribution which can be randomly sampled at test time, thus allowing us to generate multiple plausible high-resolution outputs from a given low-resolution input. We validate the proposed method on the BraTS-18 dataset qualitatively and quantitatively using a variety of similarity measures. The implementation of this work will be available at https://github.com/AvirupJU/MTSR-MRI .} }
Endnote
%0 Conference Paper %T MTSR-MRI: Combined Modality Translation and Super-Resolution of Magnetic Resonance Images %A Avirup Dey %A Mehran Ebrahimi %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-dey24a %I PMLR %P 743--757 %U https://proceedings.mlr.press/v227/dey24a.html %V 227 %X Magnetic resonance imaging (MRI) is a common non-invasive imaging technique with high soft tissue contrast. Different MRI modalities are used for the diagnosis of various conditions including T1-weighted and T2-weighted MRI. In this paper, we introduce MTSR-MRI, a novel method that can not only upscale low-resolution scans but also translates between the T1-weighted and T2-weighted modalities. This will potentially reduce the scan time or repeat scans by taking low-resolution inputs in one modality and returning plausible high-resolution output in another modality. Due to the ambiguity that persists in image-to-image translation tasks, we consider the distribution of possible outputs in a conditional generative setting. The mapping is distilled in a low-dimensional latent distribution which can be randomly sampled at test time, thus allowing us to generate multiple plausible high-resolution outputs from a given low-resolution input. We validate the proposed method on the BraTS-18 dataset qualitatively and quantitatively using a variety of similarity measures. The implementation of this work will be available at https://github.com/AvirupJU/MTSR-MRI .
APA
Dey, A. & Ebrahimi, M.. (2024). MTSR-MRI: Combined Modality Translation and Super-Resolution of Magnetic Resonance Images. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:743-757 Available from https://proceedings.mlr.press/v227/dey24a.html.

Related Material