Potential of Deep Learning in Quantitative Magnetic Resonance Imaging for Personalized Radiotherapy

Oliver J Gurney-Champion; Guillaume Landry; Kathrine Røe Redalen; Daniela Thorwarth

doi:10.1016/j.semradonc.2022.06.007

Potential of Deep Learning in Quantitative Magnetic Resonance Imaging for Personalized Radiotherapy

Semin Radiat Oncol. 2022 Oct;32(4):377-388. doi: 10.1016/j.semradonc.2022.06.007.

Authors

Oliver J Gurney-Champion¹, Guillaume Landry², Kathrine Røe Redalen³, Daniela Thorwarth⁴

Affiliations

¹ Department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.
² Department of Radiation Oncology, University Hospital, LMU Munich, Munich, Germany; German Cancer Consortium (DKTK), Munich, Germany.
³ Department of Physics, Norwegian University of Science and Technology, Trondheim, Norway.
⁴ Section for Biomedical Physics, Department of Radiation Oncology, University of Tübingen, Tübingen, Germany; German Cancer Consortium (DKTK), Partner site Tübingen, German Cancer Research Center (DKFZ), Heidelberg, Germany. Electronic address: daniela.thorwarth@med.uni-tuebingen.de.

PMID: 36202440
DOI: 10.1016/j.semradonc.2022.06.007

Abstract

Quantitative magnetic resonance imaging (qMRI) has been shown to provide many potential advantages for personalized adaptive radiotherapy (RT). Deep learning models have proven to increase efficiency, robustness and speed for different qMRI tasks. Therefore, this article discusses the current state-of-the-art and potential future opportunities as well as challenges related to the use of deep learning in qMRI for target contouring, quantitative parameter estimation and also the generation of synthetic computerized tomography (CT) data based on MRI in personalized RT.

Publication types

Review
Research Support, Non-U.S. Gov't

MeSH terms

Deep Learning*
Humans
Magnetic Resonance Imaging / methods
Tomography, X-Ray Computed