Synthetic CT generation from CBCT and MRI using StarGAN in the Pelvic Region
Abstract Rationale and objectives This study evaluated StarGAN, a deep learning model designed to generate synthetic computed tomography (sCT) images from magnetic resonance imaging (MRI) and cone-beam computed tomography (CBCT) data using a single model. The goal was to provide accurate Hounsfield...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | Radiation Oncology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13014-025-02590-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861749653176320 |
|---|---|
| author | Paritt Wongtrakool Chanon Puttanawarut Pimolpun Changkaew Supakiet Piasanthia Pareena Earwong Nauljun Stansook Suphalak Khachonkham |
| author_facet | Paritt Wongtrakool Chanon Puttanawarut Pimolpun Changkaew Supakiet Piasanthia Pareena Earwong Nauljun Stansook Suphalak Khachonkham |
| author_sort | Paritt Wongtrakool |
| collection | DOAJ |
| description | Abstract Rationale and objectives This study evaluated StarGAN, a deep learning model designed to generate synthetic computed tomography (sCT) images from magnetic resonance imaging (MRI) and cone-beam computed tomography (CBCT) data using a single model. The goal was to provide accurate Hounsfield unit (HU) data for dose calculation to enable MRI simulation and adaptive radiation therapy (ART) using CBCT or MRI. We also compared the performance and benefits of StarGAN to the commonly used CycleGAN. Materials and methods StarGAN and CycleGAN were employed in this study. The dataset comprised 53 cases of pelvic cancer. Evaluation involved qualitative and quantitative analyses, focusing on synthetic image quality and dose distribution calculation. Results For sCT generated from CBCT, StarGAN demonstrated superior anatomical preservation based on qualitative evaluation. Quantitatively, CycleGAN exhibited a lower mean absolute error (MAE) for the body (42.8 ± 4.3 HU) and bone (138.2 ± 20.3), whereas StarGAN produced a higher MAE for the body (50.8 ± 5.2 HU) and bone (153.4 ± 27.7 HU). Dosimetric evaluation showed a mean dose difference (DD) within 2% for the planning target volume (PTV) and body, with a gamma passing rate (GPR) > 90% under the 2%/2 mm criteria. For sCT generated from MRI, qualitative evaluation also favored the anatomical preservation provided by StarGAN. CycleGAN recorded a lower MAE (79.8 ± 14 HU for the body and 253.6 ± 30.9 HU for bone) compared with StarGAN (94.7 ± 7.4 HU for the body and 353.6 ± 34.9 HU for bone). Both models achieved a mean DD within 2% in the PTV and body, and GPR > 90%. Conclusion While CycleGAN exhibited superior quantitative metrics, StarGAN was better in anatomical preservation, highlighting its potential for sCT generation in radiotherapy. |
| format | Article |
| id | doaj-art-ac113fb421e349bdb471fa4fa48a9edf |
| institution | Kabale University |
| issn | 1748-717X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Radiation Oncology |
| spelling | doaj-art-ac113fb421e349bdb471fa4fa48a9edf2025-02-09T12:48:39ZengBMCRadiation Oncology1748-717X2025-02-0120111410.1186/s13014-025-02590-2Synthetic CT generation from CBCT and MRI using StarGAN in the Pelvic RegionParitt Wongtrakool0Chanon Puttanawarut1Pimolpun Changkaew2Supakiet Piasanthia3Pareena Earwong4Nauljun Stansook5Suphalak Khachonkham6Master of Science Program in Medical Physics, Department of Diagnostic and Therapeutic Radiology, Faculty of Medicine, Ramathibodi Hospital, Mahidol UniversityDepartment of Clinical Epidemiology and Biostatistics, Faculty of Medicine, Ramathibodi Hospital, Mahidol UniversityDivision of Radiation and Oncology, Department of Diagnostic and Therapeutic Radiology, Faculty of Medicine, Ramathibodi Hospital, Mahidol UniversityDivision of Radiation and Oncology, Department of Diagnostic and Therapeutic Radiology, Faculty of Medicine, Ramathibodi Hospital, Mahidol UniversityMaster of Science Program in Medical Physics, Department of Diagnostic and Therapeutic Radiology, Faculty of Medicine, Ramathibodi Hospital, Mahidol UniversityDivision of Radiation and Oncology, Department of Diagnostic and Therapeutic Radiology, Faculty of Medicine, Ramathibodi Hospital, Mahidol UniversityDivision of Radiation and Oncology, Department of Diagnostic and Therapeutic Radiology, Faculty of Medicine, Ramathibodi Hospital, Mahidol UniversityAbstract Rationale and objectives This study evaluated StarGAN, a deep learning model designed to generate synthetic computed tomography (sCT) images from magnetic resonance imaging (MRI) and cone-beam computed tomography (CBCT) data using a single model. The goal was to provide accurate Hounsfield unit (HU) data for dose calculation to enable MRI simulation and adaptive radiation therapy (ART) using CBCT or MRI. We also compared the performance and benefits of StarGAN to the commonly used CycleGAN. Materials and methods StarGAN and CycleGAN were employed in this study. The dataset comprised 53 cases of pelvic cancer. Evaluation involved qualitative and quantitative analyses, focusing on synthetic image quality and dose distribution calculation. Results For sCT generated from CBCT, StarGAN demonstrated superior anatomical preservation based on qualitative evaluation. Quantitatively, CycleGAN exhibited a lower mean absolute error (MAE) for the body (42.8 ± 4.3 HU) and bone (138.2 ± 20.3), whereas StarGAN produced a higher MAE for the body (50.8 ± 5.2 HU) and bone (153.4 ± 27.7 HU). Dosimetric evaluation showed a mean dose difference (DD) within 2% for the planning target volume (PTV) and body, with a gamma passing rate (GPR) > 90% under the 2%/2 mm criteria. For sCT generated from MRI, qualitative evaluation also favored the anatomical preservation provided by StarGAN. CycleGAN recorded a lower MAE (79.8 ± 14 HU for the body and 253.6 ± 30.9 HU for bone) compared with StarGAN (94.7 ± 7.4 HU for the body and 353.6 ± 34.9 HU for bone). Both models achieved a mean DD within 2% in the PTV and body, and GPR > 90%. Conclusion While CycleGAN exhibited superior quantitative metrics, StarGAN was better in anatomical preservation, highlighting its potential for sCT generation in radiotherapy.https://doi.org/10.1186/s13014-025-02590-2RadiotherapySynthetic CTDeep learningStarGANCycleGANCBCT |
| spellingShingle | Paritt Wongtrakool Chanon Puttanawarut Pimolpun Changkaew Supakiet Piasanthia Pareena Earwong Nauljun Stansook Suphalak Khachonkham Synthetic CT generation from CBCT and MRI using StarGAN in the Pelvic Region Radiation Oncology Radiotherapy Synthetic CT Deep learning StarGAN CycleGAN CBCT |
| title | Synthetic CT generation from CBCT and MRI using StarGAN in the Pelvic Region |
| title_full | Synthetic CT generation from CBCT and MRI using StarGAN in the Pelvic Region |
| title_fullStr | Synthetic CT generation from CBCT and MRI using StarGAN in the Pelvic Region |
| title_full_unstemmed | Synthetic CT generation from CBCT and MRI using StarGAN in the Pelvic Region |
| title_short | Synthetic CT generation from CBCT and MRI using StarGAN in the Pelvic Region |
| title_sort | synthetic ct generation from cbct and mri using stargan in the pelvic region |
| topic | Radiotherapy Synthetic CT Deep learning StarGAN CycleGAN CBCT |
| url | https://doi.org/10.1186/s13014-025-02590-2 |
| work_keys_str_mv | AT parittwongtrakool syntheticctgenerationfromcbctandmriusingstarganinthepelvicregion AT chanonputtanawarut syntheticctgenerationfromcbctandmriusingstarganinthepelvicregion AT pimolpunchangkaew syntheticctgenerationfromcbctandmriusingstarganinthepelvicregion AT supakietpiasanthia syntheticctgenerationfromcbctandmriusingstarganinthepelvicregion AT pareenaearwong syntheticctgenerationfromcbctandmriusingstarganinthepelvicregion AT nauljunstansook syntheticctgenerationfromcbctandmriusingstarganinthepelvicregion AT suphalakkhachonkham syntheticctgenerationfromcbctandmriusingstarganinthepelvicregion |