Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/135507
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: DeepWL: Robust EPID based Winston-Lutz analysis using deep learning, synthetic image generation and optical path-tracing
Author: Douglass, M.J.J.
Keal, J.A.
Citation: Physica Medica: an international journal devoted to the applications of physics to medicine and biology, 2021; 89:306-316
Publisher: Elsevier BV
Issue Date: 2021
ISSN: 1120-1797
1724-191X
Statement of
Responsibility: 
Michael John James Douglass, James Alan Keal
Abstract: Radiation therapy requires clinical linear accelerators to be mechanically and dosimetrically calibrated to a high standard. One important quality assurance test is the Winston-Lutz test which localises the radiation isocentre of the linac. In the current work we demonstrate a novel method of analysing EPID based Winston-Lutz QA images using a deep learning model trained only on synthetic image data. In addition, we propose a novel method of generating the synthetic WL images and associated ‘ground-truth’ masks using an optical path-tracing engine to ‘fake’ megavoltage EPID images. The model called DeepWL was trained on 1500 synthetic WL images using data augmentation techniques for 180 epochs. The model was built using Keras with a TensorFlow backend on an Intel Core i5-6500T CPU and trained in approximately 15 h. DeepWL was shown to produce ball bearing and multi-leaf collimator field segmentations with a mean dice coefficient of 0.964 and 0.994 respectively on previously unseen synthetic testing data. When DeepWL was applied to WL data measured on an EPID, the predicted mean displacements were shown to be statistically similar to the Canny Edge detection method. However, the DeepWL predictions for the ball bearing locations were shown to correlate better with manual annotations compared with the Canny edge detection algorithm. DeepWL was demonstrated to analyse Winston-Lutz images with an accuracy suitable for routine linac quality assurance with some statistical evidence that it may outperform Canny Edge detection methods in terms of segmentation robustness and the resultant displacement predictions.
Keywords: Deep learning; Radiation oncology; Quality assurance; Synthetic data
Rights: © 2021 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.
DOI: 10.1016/j.ejmp.2021.08.012
Published version: http://dx.doi.org/10.1016/j.ejmp.2021.08.012
Appears in Collections:Aurora harvest 4
Physics publications

Files in This Item:
File Description SizeFormat 
hdl_135507.pdfSubmitted version3.51 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.