Abstract
PurposeTo quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)‐guided prostate external‐beam radiotherapy.MethodsFive prostate cancer patients underwent 20 fractions of image‐guided external‐beam radiotherapy on a 1.5 T MR‐Linac system. For each patient, a pretreatment T2‐weighted three‐dimensional (3D) MR imaging (MRI) scan was used to delineate the clinical target volume (CTV) contours. The same scan was repeated during each fraction, with the CTV contour being manually adapted if necessary. A convolutional neural network (CNN) was trained for combined image registration and contour propagation. The network estimated the propagated contour and a deformation field between the two input images. The training set consisted of a synthetically generated ground truth of randomly deformed images and prostate segmentations. We performed a leave‐one‐out cross‐validation on the five patients and propagated the prostate segmentations from the pretreatment to the fraction scans. Three variants of the CNN, aimed at investigating supervision based on optimizing segmentation overlap, optimizing the registration, and a combination of the two were compared to results of the open‐source deformable registration software package Elastix.ResultsThe neural networks trained on segmentation overlap or the combined objective achieved significantly better Hausdorff distances between predicted and ground truth contours than Elastix, at the much faster registration speed of 0.5 s. The CNN variant trained to optimize both the prostate overlap and deformation field, and the variant trained to only maximize the prostate overlap, produced the best propagation results.ConclusionsA CNN trained on maximizing prostate overlap and minimizing registration errors provides a fast and accurate method for deformable contour propagation for prostate MR‐guided radiotherapy.
Highlights
External-beam radiotherapy is one of the standard treatments for prostate cancer.[1]
The network architecture that we propose is based on previous work on registration of pulmonary computed tomography (CT) inhale-to-exhale registration,[36,37] which showed that complex deformable registration can be accomplished end-to-end with supervised convolutional neural networks (CNNs)
We show five boxes: red boxes represent the metrics without propagation, gray boxes represent Elastix’ propagation results, and green, blue, and purple boxes represent the results of the overlap, deformation and hybrid networks, respectively
Summary
External-beam radiotherapy is one of the standard treatments for prostate cancer.[1] Because of the superior soft-tissue contrast, magnetic resonance imaging (MRI) is increasingly used in planning and guiding prostate radiotherapy.[2,3] Extreme hypofractionation with stereotactic body radiotherapy (SBRT) in prostate cancer leads to low genitourinary (GU) and gastrointestinal (GI) toxicity.[4] Recently, MR-guided radiotherapy (MRgRT) has become viable,[5,6,7] resulting in even lower GU and GI toxicity.[8] In MRgRT, a pretreatment MRI is used to delineate the clinical target volume (CTV), prior to the daily fractions of radiotherapy. At the start of each fraction, the pretreatment scan is registered to the daily fraction scan. The CTV contour is propagated by deforming it according to the registration and, if necessary, it is manually adjusted. Registration and the manual adjustment of contours are time-consuming and hinder the effectiveness of the treatment due to potential intra-fraction motion of the prostate
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.