Diffusion Models for Contrast Harmonization of Magnetic Resonance Images

Alicia Durrer, Julia Wolleb, Florentin Bieder, Tim Sinnecker, Matthias Weigel, Robin Sandkuehler, Cristina Granziera, Özgür Yaldizli, Philippe C. Cattin
Medical Imaging with Deep Learning, PMLR 227:526-551, 2024.

Abstract

Magnetic resonance (MR) images from multiple sources often show differences in image contrast related to acquisition settings or the used scanner type. For long-term studies, longitudinal comparability is essential but can be impaired by these contrast differences, leading to biased results when using automated evaluation tools. This study presents a diffusion model-based approach for contrast harmonization. We use a data set consisting of scans of 18 Multiple Sclerosis patients and 22 healthy controls. Each subject was scanned in two MR scanners of different magnetic field strengths (1.5 T and 3 T), resulting in a paired data set that shows scanner-inherent differences. We map images from the source contrast to the target contrast for both directions, from 3 T to 1.5 T and from 1.5 T to 3 T. As we only want to change the contrast, not the anatomical information, our method uses the original image to guide the image-to-image translation process by adding structural information. The aim is that the mapped scans display increased comparability with scans of the target contrast for downstream tasks. We evaluate this method for the task of segmentation of cerebrospinal fluid, grey matter and white matter. Our method achieves good and consistent results for both directions of the mapping.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-durrer24a, title = {Diffusion Models for Contrast Harmonization of Magnetic Resonance Images}, author = {Durrer, Alicia and Wolleb, Julia and Bieder, Florentin and Sinnecker, Tim and Weigel, Matthias and Sandkuehler, Robin and Granziera, Cristina and Yaldizli, \"Ozg\"ur and Cattin, Philippe C.}, booktitle = {Medical Imaging with Deep Learning}, pages = {526--551}, 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/durrer24a/durrer24a.pdf}, url = {https://proceedings.mlr.press/v227/durrer24a.html}, abstract = {Magnetic resonance (MR) images from multiple sources often show differences in image contrast related to acquisition settings or the used scanner type. For long-term studies, longitudinal comparability is essential but can be impaired by these contrast differences, leading to biased results when using automated evaluation tools. This study presents a diffusion model-based approach for contrast harmonization. We use a data set consisting of scans of 18 Multiple Sclerosis patients and 22 healthy controls. Each subject was scanned in two MR scanners of different magnetic field strengths (1.5 T and 3 T), resulting in a paired data set that shows scanner-inherent differences. We map images from the source contrast to the target contrast for both directions, from 3 T to 1.5 T and from 1.5 T to 3 T. As we only want to change the contrast, not the anatomical information, our method uses the original image to guide the image-to-image translation process by adding structural information. The aim is that the mapped scans display increased comparability with scans of the target contrast for downstream tasks. We evaluate this method for the task of segmentation of cerebrospinal fluid, grey matter and white matter. Our method achieves good and consistent results for both directions of the mapping.} }
Endnote
%0 Conference Paper %T Diffusion Models for Contrast Harmonization of Magnetic Resonance Images %A Alicia Durrer %A Julia Wolleb %A Florentin Bieder %A Tim Sinnecker %A Matthias Weigel %A Robin Sandkuehler %A Cristina Granziera %A Özgür Yaldizli %A Philippe C. Cattin %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-durrer24a %I PMLR %P 526--551 %U https://proceedings.mlr.press/v227/durrer24a.html %V 227 %X Magnetic resonance (MR) images from multiple sources often show differences in image contrast related to acquisition settings or the used scanner type. For long-term studies, longitudinal comparability is essential but can be impaired by these contrast differences, leading to biased results when using automated evaluation tools. This study presents a diffusion model-based approach for contrast harmonization. We use a data set consisting of scans of 18 Multiple Sclerosis patients and 22 healthy controls. Each subject was scanned in two MR scanners of different magnetic field strengths (1.5 T and 3 T), resulting in a paired data set that shows scanner-inherent differences. We map images from the source contrast to the target contrast for both directions, from 3 T to 1.5 T and from 1.5 T to 3 T. As we only want to change the contrast, not the anatomical information, our method uses the original image to guide the image-to-image translation process by adding structural information. The aim is that the mapped scans display increased comparability with scans of the target contrast for downstream tasks. We evaluate this method for the task of segmentation of cerebrospinal fluid, grey matter and white matter. Our method achieves good and consistent results for both directions of the mapping.
APA
Durrer, A., Wolleb, J., Bieder, F., Sinnecker, T., Weigel, M., Sandkuehler, R., Granziera, C., Yaldizli, Ö. & Cattin, P.C.. (2024). Diffusion Models for Contrast Harmonization of Magnetic Resonance Images. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:526-551 Available from https://proceedings.mlr.press/v227/durrer24a.html.

Related Material