A new deep learning model for predicting IMRT dose distributions for lung cancer with dose masks
Purpose3D U-Net deep neural networks are widely used for predicting radiotherapy dose distributions. However, dose prediction for lung cancer IMRT is limited to conventional radiotherapy, with significant errors in predicting the intermediate and low-dose regions.MethodsWe included a mixed dataset o...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1587788/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849339000659116032 |
|---|---|
| author | Xuezhen Feng Xuezhen Feng Mingqing Wang Xinyan Lin Xinyan Lin Can Li Can Li Yuxi Pan Guoping Zuo Ruijie Yang |
| author_facet | Xuezhen Feng Xuezhen Feng Mingqing Wang Xinyan Lin Xinyan Lin Can Li Can Li Yuxi Pan Guoping Zuo Ruijie Yang |
| author_sort | Xuezhen Feng |
| collection | DOAJ |
| description | Purpose3D U-Net deep neural networks are widely used for predicting radiotherapy dose distributions. However, dose prediction for lung cancer IMRT is limited to conventional radiotherapy, with significant errors in predicting the intermediate and low-dose regions.MethodsWe included a mixed dataset of conventional radiotherapy and simultaneous integrated boost (SIB) radiotherapy with various prescription schemes. In addition to inputting CT images and anatomical structures, we incorporated dose mask information to provide richer local low-dose details. We trained five models with varying numbers of dose masks to investigate their impact on dose prediction models.ResultsThe inclusion of dose masks led to significant improvements in prediction accuracy for both the PTV and OARs. In particular, the mean absolute error (MAE) of dosimetric metrics for most OARs fell below 2%, and voxel-wise MAE within each structure steadily decreased as more dose masks were supplied—most notably in low-dose regions. These results demonstrate that incorporating dose masks effectively enhances training efficiency and prediction stability. Among models receiving varying numbers of dose masks, the configuration with ten masks achieved the highest predictive accuracy.ConclusionThis study proposes a dose mask-assisted method for lung cancer IMRT dose prediction. It demonstrates high accuracy and robustness in clinical radiotherapy scenarios with various prescription schemes, including conventional radiotherapy and SIB. The inclusion of additional dose masks significantly improved model performance, with prediction accuracy increasing as the number of masks increased. |
| format | Article |
| id | doaj-art-8bea6ce9de5a4e7f8edb3c0e91a33ff6 |
| institution | Kabale University |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-8bea6ce9de5a4e7f8edb3c0e91a33ff62025-08-20T03:44:14ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-08-011510.3389/fonc.2025.15877881587788A new deep learning model for predicting IMRT dose distributions for lung cancer with dose masksXuezhen Feng0Xuezhen Feng1Mingqing Wang2Xinyan Lin3Xinyan Lin4Can Li5Can Li6Yuxi Pan7Guoping Zuo8Ruijie Yang9School of Nuclear Science and Technology, University of South China, Hengyang, ChinaDepartment of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, ChinaDepartment of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, ChinaSchool of Physics, Beihang University, Beijing, ChinaDepartment of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, ChinaInstitute of Operations Research and Information Engineering, Beijing University of Technology, Beijing, ChinaDepartment of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, ChinaDepartment of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, ChinaSchool of Nuclear Science and Technology, University of South China, Hengyang, ChinaDepartment of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, ChinaPurpose3D U-Net deep neural networks are widely used for predicting radiotherapy dose distributions. However, dose prediction for lung cancer IMRT is limited to conventional radiotherapy, with significant errors in predicting the intermediate and low-dose regions.MethodsWe included a mixed dataset of conventional radiotherapy and simultaneous integrated boost (SIB) radiotherapy with various prescription schemes. In addition to inputting CT images and anatomical structures, we incorporated dose mask information to provide richer local low-dose details. We trained five models with varying numbers of dose masks to investigate their impact on dose prediction models.ResultsThe inclusion of dose masks led to significant improvements in prediction accuracy for both the PTV and OARs. In particular, the mean absolute error (MAE) of dosimetric metrics for most OARs fell below 2%, and voxel-wise MAE within each structure steadily decreased as more dose masks were supplied—most notably in low-dose regions. These results demonstrate that incorporating dose masks effectively enhances training efficiency and prediction stability. Among models receiving varying numbers of dose masks, the configuration with ten masks achieved the highest predictive accuracy.ConclusionThis study proposes a dose mask-assisted method for lung cancer IMRT dose prediction. It demonstrates high accuracy and robustness in clinical radiotherapy scenarios with various prescription schemes, including conventional radiotherapy and SIB. The inclusion of additional dose masks significantly improved model performance, with prediction accuracy increasing as the number of masks increased.https://www.frontiersin.org/articles/10.3389/fonc.2025.1587788/fulldeep learningIMRTdose predictionradiotherapy treatment planninglung cancer |
| spellingShingle | Xuezhen Feng Xuezhen Feng Mingqing Wang Xinyan Lin Xinyan Lin Can Li Can Li Yuxi Pan Guoping Zuo Ruijie Yang A new deep learning model for predicting IMRT dose distributions for lung cancer with dose masks Frontiers in Oncology deep learning IMRT dose prediction radiotherapy treatment planning lung cancer |
| title | A new deep learning model for predicting IMRT dose distributions for lung cancer with dose masks |
| title_full | A new deep learning model for predicting IMRT dose distributions for lung cancer with dose masks |
| title_fullStr | A new deep learning model for predicting IMRT dose distributions for lung cancer with dose masks |
| title_full_unstemmed | A new deep learning model for predicting IMRT dose distributions for lung cancer with dose masks |
| title_short | A new deep learning model for predicting IMRT dose distributions for lung cancer with dose masks |
| title_sort | new deep learning model for predicting imrt dose distributions for lung cancer with dose masks |
| topic | deep learning IMRT dose prediction radiotherapy treatment planning lung cancer |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1587788/full |
| work_keys_str_mv | AT xuezhenfeng anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT xuezhenfeng anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT mingqingwang anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT xinyanlin anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT xinyanlin anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT canli anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT canli anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT yuxipan anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT guopingzuo anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT ruijieyang anewdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT xuezhenfeng newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT xuezhenfeng newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT mingqingwang newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT xinyanlin newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT xinyanlin newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT canli newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT canli newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT yuxipan newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT guopingzuo newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks AT ruijieyang newdeeplearningmodelforpredictingimrtdosedistributionsforlungcancerwithdosemasks |