| Dong Shuncheng,Sun Yanze,Yang Yue,Du Yonghuan,Zhang Peiyi,Ang Wensheng,Wen Wanxin.Convolutional neural network-based three-dimensional dose reconstruction using volumetric scintillation light[J].Chinese Journal of Radiological Medicine and Protection,2023,43(12):1034-1040 |
| Convolutional neural network-based three-dimensional dose reconstruction using volumetric scintillation light |
| Received:April 10, 2023 |
| DOI：10.3760/cma.j.cn112271-20230410-00113 |
| KeyWords:Convolutional neural networks 3D dosimetry Radioluminescence |
| FundProject: |
| Author Name | Affiliation | E-mail | | Dong Shuncheng | School of Radiation Medicine and Protection (SRMP) of Soochow University, Suzhou 215031, China | | | Sun Yanze | Department of Radiation Oncology, Second Affiliated Hospital of Soochow University, Suzhou 215004, China | | | Yang Yue | Department of Radiation Oncology, Zhongshan Hospital, Fudan University, Shanghai 200032, China | | | Du Yonghuan | School of Radiation Medicine and Protection (SRMP) of Soochow University, Suzhou 215031, China | | | Zhang Peiyi | School of Radiation Medicine and Protection (SRMP) of Soochow University, Suzhou 215031, China | | | Ang Wensheng | School of Radiation Medicine and Protection (SRMP) of Soochow University, Suzhou 215031, China | | | Wen Wanxin | School of Radiation Medicine and Protection (SRMP) of Soochow University, Suzhou 215031, China | wxwen@suda.edu.cn |
|
| Hits: 645 |
| Download times: 240 |
| Abstract:: |
| Objective To reconstruct the three-dimensional (3D) dose distribution in radiotherapy based on the convolutional neural networks (CNN) through multi-perspective scintillation light processing.Methods First, fluorescence images were captured from three orthogonal perspectives using a complementary metal-oxide-semiconductor (CMOS) imaging sensor. Then, the images were converted into 3D images, which were input to the trained CNN for dose reconstruction. Finally, the reconstructed doses in different fields were evaluated in terms of gamma pass rate, mean-square error (MSE), percentage depth dose (PDD), and cross beam profile (CBP). Additionally, as the CNN model, 3D-Unet was pre-trained on a virtual dataset.Results With the 50% maximum dose of as the threshold and 3%/3mm as the standard, the central-plane and stereo-mean gamma pass rates of all field reconstruction distributions were over 90%, with MSEs remained below 1%. Besides, the PDD and CBP curves showed MSEs below 1‰ and below 1%, respectively.Conclusions The deep learning-based method for 3D dose reconstruction using scintillation light contributes to enhanced verification of instantaneous 3D relative dose based on plastic scintillation detectors. |
| HTML View Full Text View/Add Comment Download reader |
| Close |
|
|
|
