A Path Towards Clinical Adaptation of Accelerated MRI

Michael S. Yao, Michael S. Hansen
Proceedings of the 2nd Machine Learning for Health symposium, PMLR 193:489-511, 2022.

Abstract

Accelerated MRI reconstructs images of clinical anatomies from sparsely sampled signal data to reduce patient scan times. While recent works have leveraged deep learning to accomplish this task, such approaches have often only been explored in simulated environments where there is no signal corruption or resource limitations. In this work, we explore augmentations to neural network MRI image reconstructors to enhance their clinical relevancy. Namely, we propose a ConvNet model for detecting sources of image artifacts that achieves a classifier $\mathit{F}_{2}$ score of 79.1%. We also demonstrate that training reconstructors on MR signal data with variable acceleration factors can improve their average performance during a clinical patient scan by up to 2%. We offer a loss function to overcome catastrophic forgetting when models learn to reconstruct MR images of multiple anatomies and orientations. Finally, we propose a method for using simulated phantom data to pre-train reconstructors in situations with limited clinically acquired datasets and compute capabilities. Our results provide a potential path forward for clinical adaptation of accelerated MRI.

Cite this Paper

BibTeX
@InProceedings{pmlr-v193-yao22a, title = {A Path Towards Clinical Adaptation of Accelerated MRI}, author = {Yao, Michael S. and Hansen, Michael S.}, booktitle = {Proceedings of the 2nd Machine Learning for Health symposium}, pages = {489--511}, year = {2022}, editor = {Parziale, Antonio and Agrawal, Monica and Joshi, Shalmali and Chen, Irene Y. and Tang, Shengpu and Oala, Luis and Subbaswamy, Adarsh}, volume = {193}, series = {Proceedings of Machine Learning Research}, month = {28 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v193/yao22a/yao22a.pdf}, url = {https://proceedings.mlr.press/v193/yao22a.html}, abstract = {Accelerated MRI reconstructs images of clinical anatomies from sparsely sampled signal data to reduce patient scan times. While recent works have leveraged deep learning to accomplish this task, such approaches have often only been explored in simulated environments where there is no signal corruption or resource limitations. In this work, we explore augmentations to neural network MRI image reconstructors to enhance their clinical relevancy. Namely, we propose a ConvNet model for detecting sources of image artifacts that achieves a classifier $\mathit{F}_{2}$ score of 79.1%. We also demonstrate that training reconstructors on MR signal data with variable acceleration factors can improve their average performance during a clinical patient scan by up to 2%. We offer a loss function to overcome catastrophic forgetting when models learn to reconstruct MR images of multiple anatomies and orientations. Finally, we propose a method for using simulated phantom data to pre-train reconstructors in situations with limited clinically acquired datasets and compute capabilities. Our results provide a potential path forward for clinical adaptation of accelerated MRI.} }
Endnote
%0 Conference Paper %T A Path Towards Clinical Adaptation of Accelerated MRI %A Michael S. Yao %A Michael S. Hansen %B Proceedings of the 2nd Machine Learning for Health symposium %C Proceedings of Machine Learning Research %D 2022 %E Antonio Parziale %E Monica Agrawal %E Shalmali Joshi %E Irene Y. Chen %E Shengpu Tang %E Luis Oala %E Adarsh Subbaswamy %F pmlr-v193-yao22a %I PMLR %P 489--511 %U https://proceedings.mlr.press/v193/yao22a.html %V 193 %X Accelerated MRI reconstructs images of clinical anatomies from sparsely sampled signal data to reduce patient scan times. While recent works have leveraged deep learning to accomplish this task, such approaches have often only been explored in simulated environments where there is no signal corruption or resource limitations. In this work, we explore augmentations to neural network MRI image reconstructors to enhance their clinical relevancy. Namely, we propose a ConvNet model for detecting sources of image artifacts that achieves a classifier $\mathit{F}_{2}$ score of 79.1%. We also demonstrate that training reconstructors on MR signal data with variable acceleration factors can improve their average performance during a clinical patient scan by up to 2%. We offer a loss function to overcome catastrophic forgetting when models learn to reconstruct MR images of multiple anatomies and orientations. Finally, we propose a method for using simulated phantom data to pre-train reconstructors in situations with limited clinically acquired datasets and compute capabilities. Our results provide a potential path forward for clinical adaptation of accelerated MRI.
APA
Yao, M.S. & Hansen, M.S.. (2022). A Path Towards Clinical Adaptation of Accelerated MRI. Proceedings of the 2nd Machine Learning for Health symposium, in Proceedings of Machine Learning Research 193:489-511 Available from https://proceedings.mlr.press/v193/yao22a.html.

Related Material