Deep learning in MRI-guided radiation therapy: A systematic review

Abstract

Recent advances in MRI-guided radiation therapy (MRgRT) and deep learning techniques encourage fully adaptive radiation therapy (ART), real-time MRI monitoring, and the MRI-only treatment planning workflow. Given the rapid growth and emergence of new state-of-the-art methods in these fields, we systematically review 197 studies written on or before December 31, 2022, and categorize the studies into the areas of image segmentation, image synthesis, radiomics, and real time MRI. Building from the underlying deep learning methods, we discuss their clinical importance and current challenges in facilitating small tumor segmentation, accurate x-ray attenuation information from MRI, tumor characterization and prognosis, and tumor motion tracking. In particular, we highlight the recent trends in deep learning such as the emergence of multi-modal, visual transformer, and diffusion models.

Keywords: MRI-guided; deep learning; radiation therapy; radiotherapy; review.

FIGURE 1

An MRI‐only workflow for prostate cancer. From top to bottom, a diagnostic MRI is taken to determine the sites of the target volume and organs at risk (OARS) which can be aided by segmentation models and prognostic radiomics models. Simultaneously, sCT enables x‐ray attenuation information. Finally, fiducial markers (FMs) are identified to define the prostate position which can be monitored during treatment with real time MRI. Reprinted by permission from Elsevier: Clinical Oncology, Magnetic Resonance Imaging only Workflow for Radiotherapy Simulation and Planning in Prostate Cancer by Kerkmeijer et al. 2018.

FIGURE 2

Number of deep learning studies with applications towards MRgRT per year by category including references 161–277 in Supporting Information.

FIGURE 3

Technical trends in deep learning.

FIGURE 4

Expert (red) versus proposed auto‐segmented (green dashed) prostate and DIL contours on axial MRI. From left to right: prostate manual and auto‐segmented contours overlaid on MRI, and two DIL manual and auto‐segmented contours overlaid on MRI. The upper and lower rows are representative of two patients. Reprinted by permission from John Wiley and Sons: Medical Physics, MRI‐based prostate and dominant lesion segmentation using cascaded scoring convolutional neural network by Eidex et al. © 2022.

FIGURE 5

Traverse, sagittal, and coronal images of a representative patient. MRI, CT, and sCT images and the HU difference map between CT and sCT are presented. The CT (solid line) and sCT (dashed line) voxel‐based HU profiles of the traverse images are compared in the lowermost panel. Reprinted by permission from British Journal of Radiology, MRI‐based treatment planning for liver stereotactic body radiotherapy: validation of a deep learning‐based synthetic CT generation method by Liu et al.¹⁰⁸© 2019.

FIGURE 6

Contours of segmented pelvic organs for two representative patients. Ground truth contours are overlaid onto CBCT. The predicted contours of the proposed method are overlaid on CBCT and sMRI. Red arrows highlight regions in which CBCT and sMRI provide complementary information for bony structure and soft tissue segmentation. Reprinted by permission from John Wiley and Sons: Medical Physics, Pelvic multi‐organ segmentation on cone‐beam CT for prostate adaptive radiotherapy by Fu et al. © 2020.