Abstract #0413

Uncertainty Estimation of subject-specific Local SAR assessment by Bayesian Deep Learning

E.F. Meliadò^1,2,3, A.J.E. Raaijmakers^1,2,4, M. Maspero^2,5, M.H.F. Savenije^2,5, P.R. Luijten¹, and C.A.T. van den Berg^2,5

¹Department of Radiology, University Medical Center Utrecht, Utrecht, Netherlands, ²Computational Imaging Group for MR diagnostics & therapy, Center for Image Sciences, University Medical Center Utrecht, Utrecht, Netherlands, ³Tesla Dynamic Coils BV, Zaltbommel, Netherlands, ⁴Biomedical Image Analysis, Dept. Biomedical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands, ⁵Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Utrecht, Netherlands

Residual error/uncertainty is always present in the estimated local SAR, therefore it is essential to investigate and understand the magnitude of the main sources of error/uncertainty. Last year we presented a Bayesian deep learning approach to map the relation between subject-specific complex B₁⁺-maps and the corresponding local SAR distribution, and to predict the spatial distribution of uncertainty at the same time. The preliminary results showed the feasibility of the proposed approach. In this study, we show its ability to reliably capture the main sources of uncertainty and detect deviations in the MR examination scenario not included in the training samples.

This abstract and the presentation materials are available to members only; a login is required.

Join Here