Cargando…

MV CBCT-Based Synthetic CT Generation Using a Deep Learning Method for Rectal Cancer Adaptive Radiotherapy

Due to image quality limitations, online Megavoltage cone beam CT (MV CBCT), which represents real online patient anatomy, cannot be used to perform adaptive radiotherapy (ART). In this study, we used a deep learning method, the cycle-consistent adversarial network (CycleGAN), to improve the MV CBCT...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhao, Jun, Chen, Zhi, Wang, Jiazhou, Xia, Fan, Peng, Jiayuan, Hu, Yiwen, Hu, Weigang, Zhang, Zhen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8201514/
https://www.ncbi.nlm.nih.gov/pubmed/34136391
http://dx.doi.org/10.3389/fonc.2021.655325
_version_ 1783707827793035264
author Zhao, Jun
Chen, Zhi
Wang, Jiazhou
Xia, Fan
Peng, Jiayuan
Hu, Yiwen
Hu, Weigang
Zhang, Zhen
author_facet Zhao, Jun
Chen, Zhi
Wang, Jiazhou
Xia, Fan
Peng, Jiayuan
Hu, Yiwen
Hu, Weigang
Zhang, Zhen
author_sort Zhao, Jun
collection PubMed
description Due to image quality limitations, online Megavoltage cone beam CT (MV CBCT), which represents real online patient anatomy, cannot be used to perform adaptive radiotherapy (ART). In this study, we used a deep learning method, the cycle-consistent adversarial network (CycleGAN), to improve the MV CBCT image quality and Hounsfield-unit (HU) accuracy for rectal cancer patients to make the generated synthetic CT (sCT) eligible for ART. Forty rectal cancer patients treated with the intensity modulated radiotherapy (IMRT) were involved in this study. The CT and MV CBCT images of 30 patients were used for model training, and the images of the remaining 10 patients were used for evaluation. Image quality, autosegmentation capability and dose calculation capability using the autoplanning technique of the generated sCT were evaluated. The mean absolute error (MAE) was reduced from 135.84 ± 41.59 HU for the CT and CBCT comparison to 52.99 ± 12.09 HU for the CT and sCT comparison. The structural similarity (SSIM) index for the CT and sCT comparison was 0.81 ± 0.03, which is a great improvement over the 0.44 ± 0.07 for the CT and CBCT comparison. The autosegmentation model performance on sCT for femoral heads was accurate and required almost no manual modification. For the CTV and bladder, although modification was needed for autocontouring, the Dice similarity coefficient (DSC) indices were high, at 0.93 and 0.94 for the CTV and bladder, respectively. For dose evaluation, the sCT-based plan has a much smaller dose deviation from the CT-based plan than that of the CBCT-based plan. The proposed method solved a key problem for rectal cancer ART realization based on MV CBCT. The generated sCT enables ART based on the actual patient anatomy at the treatment position.
format Online
Article
Text
id pubmed-8201514
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-82015142021-06-15 MV CBCT-Based Synthetic CT Generation Using a Deep Learning Method for Rectal Cancer Adaptive Radiotherapy Zhao, Jun Chen, Zhi Wang, Jiazhou Xia, Fan Peng, Jiayuan Hu, Yiwen Hu, Weigang Zhang, Zhen Front Oncol Oncology Due to image quality limitations, online Megavoltage cone beam CT (MV CBCT), which represents real online patient anatomy, cannot be used to perform adaptive radiotherapy (ART). In this study, we used a deep learning method, the cycle-consistent adversarial network (CycleGAN), to improve the MV CBCT image quality and Hounsfield-unit (HU) accuracy for rectal cancer patients to make the generated synthetic CT (sCT) eligible for ART. Forty rectal cancer patients treated with the intensity modulated radiotherapy (IMRT) were involved in this study. The CT and MV CBCT images of 30 patients were used for model training, and the images of the remaining 10 patients were used for evaluation. Image quality, autosegmentation capability and dose calculation capability using the autoplanning technique of the generated sCT were evaluated. The mean absolute error (MAE) was reduced from 135.84 ± 41.59 HU for the CT and CBCT comparison to 52.99 ± 12.09 HU for the CT and sCT comparison. The structural similarity (SSIM) index for the CT and sCT comparison was 0.81 ± 0.03, which is a great improvement over the 0.44 ± 0.07 for the CT and CBCT comparison. The autosegmentation model performance on sCT for femoral heads was accurate and required almost no manual modification. For the CTV and bladder, although modification was needed for autocontouring, the Dice similarity coefficient (DSC) indices were high, at 0.93 and 0.94 for the CTV and bladder, respectively. For dose evaluation, the sCT-based plan has a much smaller dose deviation from the CT-based plan than that of the CBCT-based plan. The proposed method solved a key problem for rectal cancer ART realization based on MV CBCT. The generated sCT enables ART based on the actual patient anatomy at the treatment position. Frontiers Media S.A. 2021-05-31 /pmc/articles/PMC8201514/ /pubmed/34136391 http://dx.doi.org/10.3389/fonc.2021.655325 Text en Copyright © 2021 Zhao, Chen, Wang, Xia, Peng, Hu, Hu and Zhang https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Zhao, Jun
Chen, Zhi
Wang, Jiazhou
Xia, Fan
Peng, Jiayuan
Hu, Yiwen
Hu, Weigang
Zhang, Zhen
MV CBCT-Based Synthetic CT Generation Using a Deep Learning Method for Rectal Cancer Adaptive Radiotherapy
title MV CBCT-Based Synthetic CT Generation Using a Deep Learning Method for Rectal Cancer Adaptive Radiotherapy
title_full MV CBCT-Based Synthetic CT Generation Using a Deep Learning Method for Rectal Cancer Adaptive Radiotherapy
title_fullStr MV CBCT-Based Synthetic CT Generation Using a Deep Learning Method for Rectal Cancer Adaptive Radiotherapy
title_full_unstemmed MV CBCT-Based Synthetic CT Generation Using a Deep Learning Method for Rectal Cancer Adaptive Radiotherapy
title_short MV CBCT-Based Synthetic CT Generation Using a Deep Learning Method for Rectal Cancer Adaptive Radiotherapy
title_sort mv cbct-based synthetic ct generation using a deep learning method for rectal cancer adaptive radiotherapy
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8201514/
https://www.ncbi.nlm.nih.gov/pubmed/34136391
http://dx.doi.org/10.3389/fonc.2021.655325
work_keys_str_mv AT zhaojun mvcbctbasedsyntheticctgenerationusingadeeplearningmethodforrectalcanceradaptiveradiotherapy
AT chenzhi mvcbctbasedsyntheticctgenerationusingadeeplearningmethodforrectalcanceradaptiveradiotherapy
AT wangjiazhou mvcbctbasedsyntheticctgenerationusingadeeplearningmethodforrectalcanceradaptiveradiotherapy
AT xiafan mvcbctbasedsyntheticctgenerationusingadeeplearningmethodforrectalcanceradaptiveradiotherapy
AT pengjiayuan mvcbctbasedsyntheticctgenerationusingadeeplearningmethodforrectalcanceradaptiveradiotherapy
AT huyiwen mvcbctbasedsyntheticctgenerationusingadeeplearningmethodforrectalcanceradaptiveradiotherapy
AT huweigang mvcbctbasedsyntheticctgenerationusingadeeplearningmethodforrectalcanceradaptiveradiotherapy
AT zhangzhen mvcbctbasedsyntheticctgenerationusingadeeplearningmethodforrectalcanceradaptiveradiotherapy