dc.contributor.author | Kalantar, R | |
dc.contributor.author | Messiou, C | |
dc.contributor.author | Winfield, JM | |
dc.contributor.author | Renn, A | |
dc.contributor.author | Latifoltojar, A | |
dc.contributor.author | Downey, K | |
dc.contributor.author | Sohaib, A | |
dc.contributor.author | Lalondrelle, S | |
dc.contributor.author | Koh, D-M | |
dc.contributor.author | Blackledge, MD | |
dc.date.accessioned | 2021-09-21T11:44:26Z | |
dc.date.available | 2021-09-21T11:44:26Z | |
dc.date.issued | 2021-07-30 | |
dc.identifier.citation | Frontiers in oncology, 2021, 11 pp. 665807 - ? | |
dc.identifier.issn | 2234-943X | |
dc.identifier.uri | https://repository.icr.ac.uk/handle/internal/4816 | |
dc.identifier.eissn | 2234-943X | |
dc.identifier.doi | 10.3389/fonc.2021.665807 | |
dc.description.abstract | BACKGROUND: Computed tomography (CT) and magnetic resonance imaging (MRI) are the mainstay imaging modalities in radiotherapy planning. In MR-Linac treatment, manual annotation of organs-at-risk (OARs) and clinical volumes requires a significant clinician interaction and is a major challenge. Currently, there is a lack of available pre-annotated MRI data for training supervised segmentation algorithms. This study aimed to develop a deep learning (DL)-based framework to synthesize pelvic T1-weighted MRI from a pre-existing repository of clinical planning CTs. METHODS: MRI synthesis was performed using UNet++ and cycle-consistent generative adversarial network (Cycle-GAN), and the predictions were compared qualitatively and quantitatively against a baseline UNet model using pixel-wise and perceptual loss functions. Additionally, the Cycle-GAN predictions were evaluated through qualitative expert testing (4 radiologists), and a pelvic bone segmentation routine based on a UNet architecture was trained on synthetic MRI using CT-propagated contours and subsequently tested on real pelvic T1 weighted MRI scans. RESULTS: In our experiments, Cycle-GAN generated sharp images for all pelvic slices whilst UNet and UNet++ predictions suffered from poorer spatial resolution within deformable soft-tissues (e.g. bladder, bowel). Qualitative radiologist assessment showed inter-expert variabilities in the test scores; each of the four radiologists correctly identified images as acquired/synthetic with 67%, 100%, 86% and 94% accuracy. Unsupervised segmentation of pelvic bone on T1-weighted images was successful in a number of test cases. CONCLUSION: Pelvic MRI synthesis is a challenging task due to the absence of soft-tissue contrast on CT. Our study showed the potential of deep learning models for synthesizing realistic MR images from CT, and transferring cross-domain knowledge which may help to expand training datasets for 21 development of MR-only segmentation models. | |
dc.format | Electronic-eCollection | |
dc.format.extent | 665807 - ? | |
dc.language | eng | |
dc.language.iso | eng | |
dc.publisher | FRONTIERS MEDIA SA | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0 | |
dc.title | CT-Based Pelvic T1-Weighted MR Image Synthesis Using UNet, UNet++ and Cycle-Consistent Generative Adversarial Network (Cycle-GAN). | |
dc.type | Journal Article | |
dcterms.dateAccepted | 2021-07-15 | |
rioxxterms.version | VoR | |
rioxxterms.versionofrecord | 10.3389/fonc.2021.665807 | |
rioxxterms.licenseref.uri | https://creativecommons.org/licenses/by/4.0 | |
rioxxterms.type | Journal Article/Review | |
dc.relation.isPartOf | Frontiers in oncology | |
pubs.notes | Not known | |
pubs.organisational-group | /ICR | |
pubs.organisational-group | /ICR/Primary Group | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Computational Imaging | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Gynaecological Cancer | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Gynaecological Cancer/Gynaecological Cancer (hon.) | |
pubs.organisational-group | /ICR/Primary Group/Royal Marsden Clinical Units | |
pubs.organisational-group | /ICR/Students | |
pubs.organisational-group | /ICR/Students/PhD and MPhil | |
pubs.organisational-group | /ICR/Students/PhD and MPhil/19/20 Starting Cohort | |
pubs.organisational-group | /ICR | |
pubs.organisational-group | /ICR/Primary Group | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Computational Imaging | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Gynaecological Cancer | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Radiotherapy and Imaging/Gynaecological Cancer/Gynaecological Cancer (hon.) | |
pubs.organisational-group | /ICR/Primary Group/Royal Marsden Clinical Units | |
pubs.organisational-group | /ICR/Students | |
pubs.organisational-group | /ICR/Students/PhD and MPhil | |
pubs.organisational-group | /ICR/Students/PhD and MPhil/19/20 Starting Cohort | |
pubs.publication-status | Published | |
pubs.volume | 11 | |
pubs.embargo.terms | Not known | |
icr.researchteam | Computational Imaging | |
icr.researchteam | Gynaecological Cancer | |
icr.researchteam | Computational Imaging | |
icr.researchteam | Gynaecological Cancer | |
dc.contributor.icrauthor | Kalantar, Reza | |
dc.contributor.icrauthor | Blackledge, Matthew | |