Szmul, Adam;
Taylor, Sabrina;
Lim, Pei;
Cantwell, Jessica;
Moreira, Isabel;
Zhang, Ying;
D'Souza, Derek;
... Veiga, Catarina; + view all
(2023)
Deep learning based synthetic CT from cone beam CT generation for abdominal paediatric radiotherapy.
Physics in Medicine & Biology
10.1088/1361-6560/acc921.
(In press).
Preview |
Text
Szmul_+et+al_2023_Phys._Med._Biol._10.1088_1361-6560_acc921.pdf Download (4MB) | Preview |
Abstract
Objective: Adaptive radiotherapy workflows require images with the quality of computed tomography (CT) for re-calculation and re-optimisation of radiation doses. In this work we aim to improve quality of cone beam CT (CBCT) images for dose calculation using deep learning. / Approach: We propose a novel framework for CBCT-to-CT synthesis using cycle-consistent Generative 10 Adversarial Networks (cycleGANs). The framework was tailored for paediatric abdominal patients, a challenging application due to the inter-fractional variability in bowel filling and smaller patient numbers. We introduced the concept of global residuals only learning to the networks and modified the cycleGAN loss function to explicitly promote structural consistency between source and synthetic images. Finally, to compensate for the anatomical variability and address the difficulties in collecting large datasets in the 15 paediatric population, we applied a smart 2D slice selection based on the common field-of-view across the dataset (abdomen). This acted as a weakly paired data approach that allowed us to take advantage of scans from patients treated for a variety of malignancies (thoracic-abdominal-pelvic) for training purposes. We first optimised the proposed framework and benchmarked its performance on a development dataset. Later, a comprehensive quantitative evaluation was performed on an unseen 20 dataset, which included calculating global image similarity metrics, segmentation-based measures and proton therapy-specific metrics. / Main results: We found improved performance, compared to a baseline implementation, on imagesimilarity metrics such as Mean Absolute Error calculated for a matched virtual CT (55.0±16.6 proposed vs 58.9±16.8 baseline). There was also a higher level of structural agreement for gastrointestinal gas 25 between source and synthetic images measured through dice similarity overlap (0.872±0.053 proposed vs 0.846±0.052 baseline). Differences found in water-equivalent thickness metrics were also smaller for our method (3.3±2.4% proposed vs 3.7±2.8% baseline). / Significance: Our findings indicate that our innovations to the cycleGAN framework improved the quality and structure consistency of the synthetic CTs generated.
Type: | Article |
---|---|
Title: | Deep learning based synthetic CT from cone beam CT generation for abdominal paediatric radiotherapy |
Location: | England |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1088/1361-6560/acc921 |
Publisher version: | https://doi.org/10.1088/1361-6560/acc921 |
Language: | English |
Additional information: | As the Version of Record of this article is going to be / has been published on a gold open access basis under a CC BY 4.0 licence, this Accepted Manuscript is available for reuse under a CC BY 4.0 licence immediately. Everyone is permitted to use all or part of the original content in this article, provided that they adhere to all the terms of the licence (https://creativecommons.org/licences/by/4.0). Although reasonable endeavours have been taken to obtain all necessary permissions from third parties to include their copyrighted content within this article, their full citation and copyright line may not be present in this Accepted Manuscript version. Before using any content from this article, please refer to the Version of Record on IOPscience once published for full citation and copyright details, as permissions may be required. All third party content is fully copyright protected and is not published on a gold open access basis under a CC BY licence, unless that is specifically stated in the figure caption in the Version of Record. |
Keywords: | Cone-beam computed tomography (CBCT), computer tomography (CT), cycle-consistent generative adversarial networks (cycleGANs), synthetic images, childhood cancer, abdominal neuroblastoma, paediatric radiotherapy |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng |
URI: | https://discovery.ucl.ac.uk/id/eprint/10167640 |
Archive Staff Only
View Item |