Cone Beam CT (CBCT) Based Synthetic CT Generation Using Deep Learning Methods for Dose Calculation of Nasopharyngeal Carcinoma Radiotherapy

Objective: To generate synthetic CT (sCT) images with high quality from CBCT and planning CT (pCT) for dose calculation by using deep learning methods. Methods: 169 NPC patients with a total of 20926 slices of CBCT and pCT images were included. In this study the CycleGAN, Pix2pix and U-Net models we...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Xudong Xue PhD, Yi Ding PhD, Jun Shi MS, Xiaoyu Hao MS, Xiangbin Li PhD, Dan Li MS, Yuan Wu PhD, Hong An PhD, Man Jiang PhD, Wei Wei PhD, Xiao Wang PhD
Formato: article
Lenguaje:EN
Publicado: SAGE Publishing 2021
Materias:
Acceso en línea:https://doaj.org/article/7da452e2c3014ae69531093403bf9961
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7da452e2c3014ae69531093403bf9961
record_format dspace
spelling oai:doaj.org-article:7da452e2c3014ae69531093403bf99612021-12-02T08:03:20ZCone Beam CT (CBCT) Based Synthetic CT Generation Using Deep Learning Methods for Dose Calculation of Nasopharyngeal Carcinoma Radiotherapy1533-033810.1177/15330338211062415https://doaj.org/article/7da452e2c3014ae69531093403bf99612021-12-01T00:00:00Zhttps://doi.org/10.1177/15330338211062415https://doaj.org/toc/1533-0338Objective: To generate synthetic CT (sCT) images with high quality from CBCT and planning CT (pCT) for dose calculation by using deep learning methods. Methods: 169 NPC patients with a total of 20926 slices of CBCT and pCT images were included. In this study the CycleGAN, Pix2pix and U-Net models were used to generate the sCT images. The Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Peak Signal to Noise Ratio (PSNR), and Structural Similarity Index (SSIM) were used to quantify the accuracy of the proposed models in a testing cohort of 34 patients. Radiation dose were calculated on pCT and sCT following the same protocol. Dose distributions were evaluated for 4 patients by comparing the dose-volume-histogram (DVH) and 2D gamma index analysis. Results: The average MAE and RMSE values between sCT by three models and pCT reduced by 15.4 HU and 26.8 HU at least, while the mean PSNR and SSIM metrics between sCT by different models and pCT added by 10.6 and 0.05 at most, respectively. There were only slight differences for DVH of selected contours between different plans. The passing rates of 2D gamma index analysis under 3 mm/3% 3 mm/2%, 2 mm/3%and 2 mm/2% criteria were all higher than 95%. Conclusions: All the sCT had achieved better evaluation metrics than those of original CBCT, while the performance of CycleGAN model was proved to be best among three methods. The dosimetric agreement confirmed the HU accuracy and consistent anatomical structures of sCT by deep learning methods.Xudong Xue PhDYi Ding PhDJun Shi MSXiaoyu Hao MSXiangbin Li PhDDan Li MSYuan Wu PhDHong An PhDMan Jiang PhDWei Wei PhDXiao Wang PhDSAGE PublishingarticleNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENTechnology in Cancer Research & Treatment, Vol 20 (2021)
institution DOAJ
collection DOAJ
language EN
topic Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
spellingShingle Neoplasms. Tumors. Oncology. Including cancer and carcinogens
RC254-282
Xudong Xue PhD
Yi Ding PhD
Jun Shi MS
Xiaoyu Hao MS
Xiangbin Li PhD
Dan Li MS
Yuan Wu PhD
Hong An PhD
Man Jiang PhD
Wei Wei PhD
Xiao Wang PhD
Cone Beam CT (CBCT) Based Synthetic CT Generation Using Deep Learning Methods for Dose Calculation of Nasopharyngeal Carcinoma Radiotherapy
description Objective: To generate synthetic CT (sCT) images with high quality from CBCT and planning CT (pCT) for dose calculation by using deep learning methods. Methods: 169 NPC patients with a total of 20926 slices of CBCT and pCT images were included. In this study the CycleGAN, Pix2pix and U-Net models were used to generate the sCT images. The Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Peak Signal to Noise Ratio (PSNR), and Structural Similarity Index (SSIM) were used to quantify the accuracy of the proposed models in a testing cohort of 34 patients. Radiation dose were calculated on pCT and sCT following the same protocol. Dose distributions were evaluated for 4 patients by comparing the dose-volume-histogram (DVH) and 2D gamma index analysis. Results: The average MAE and RMSE values between sCT by three models and pCT reduced by 15.4 HU and 26.8 HU at least, while the mean PSNR and SSIM metrics between sCT by different models and pCT added by 10.6 and 0.05 at most, respectively. There were only slight differences for DVH of selected contours between different plans. The passing rates of 2D gamma index analysis under 3 mm/3% 3 mm/2%, 2 mm/3%and 2 mm/2% criteria were all higher than 95%. Conclusions: All the sCT had achieved better evaluation metrics than those of original CBCT, while the performance of CycleGAN model was proved to be best among three methods. The dosimetric agreement confirmed the HU accuracy and consistent anatomical structures of sCT by deep learning methods.
format article
author Xudong Xue PhD
Yi Ding PhD
Jun Shi MS
Xiaoyu Hao MS
Xiangbin Li PhD
Dan Li MS
Yuan Wu PhD
Hong An PhD
Man Jiang PhD
Wei Wei PhD
Xiao Wang PhD
author_facet Xudong Xue PhD
Yi Ding PhD
Jun Shi MS
Xiaoyu Hao MS
Xiangbin Li PhD
Dan Li MS
Yuan Wu PhD
Hong An PhD
Man Jiang PhD
Wei Wei PhD
Xiao Wang PhD
author_sort Xudong Xue PhD
title Cone Beam CT (CBCT) Based Synthetic CT Generation Using Deep Learning Methods for Dose Calculation of Nasopharyngeal Carcinoma Radiotherapy
title_short Cone Beam CT (CBCT) Based Synthetic CT Generation Using Deep Learning Methods for Dose Calculation of Nasopharyngeal Carcinoma Radiotherapy
title_full Cone Beam CT (CBCT) Based Synthetic CT Generation Using Deep Learning Methods for Dose Calculation of Nasopharyngeal Carcinoma Radiotherapy
title_fullStr Cone Beam CT (CBCT) Based Synthetic CT Generation Using Deep Learning Methods for Dose Calculation of Nasopharyngeal Carcinoma Radiotherapy
title_full_unstemmed Cone Beam CT (CBCT) Based Synthetic CT Generation Using Deep Learning Methods for Dose Calculation of Nasopharyngeal Carcinoma Radiotherapy
title_sort cone beam ct (cbct) based synthetic ct generation using deep learning methods for dose calculation of nasopharyngeal carcinoma radiotherapy
publisher SAGE Publishing
publishDate 2021
url https://doaj.org/article/7da452e2c3014ae69531093403bf9961
work_keys_str_mv AT xudongxuephd conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT yidingphd conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT junshims conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT xiaoyuhaoms conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT xiangbinliphd conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT danlims conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT yuanwuphd conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT honganphd conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT manjiangphd conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT weiweiphd conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
AT xiaowangphd conebeamctcbctbasedsyntheticctgenerationusingdeeplearningmethodsfordosecalculationofnasopharyngealcarcinomaradiotherapy
_version_ 1718398669416300544