Deep learning-based spot weight generation for online adaptive IMPT: implementation and technical feasibility on a clinical delivery system.
Authors
Affiliations (12)
Affiliations (12)
- Cancer Center, Hubei Key Laboratory of Precision Radiation Oncology, Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430022, China; Key Laboratory of Biological Targeted Therapy (Huazhong University of Science and Technology), Ministry of Education, Wuhan, Hubei 430022, China.
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan 430072, China.
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong.
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD, USA.
- Department of Human Oncology, University of Wisconsin-Madison, Madison, WI 53792, USA.
- Medical Artificial Intelligence Lab, The First Hospital of Hebei Medical University, Hebei Medical University, Shijiazhuang 050000, China; Hebei Provincial Engineering Research Center for AI-Based Cancer Treatment Decision-Making, The First Hospital of Hebei Medical University, Hebei Medical University, Shijiazhuang 050000, China; Department of Oncology, The First Hospital of Hebei Medical University, Hebei Medical University, Shijiazhuang 050000, China.
- Department of Radiation Oncology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450000, China.
- Cancer Center, Hubei Key Laboratory of Precision Radiation Oncology, Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430022, China.
- Huazhong University of Science and Technology, School of Electrical and Electronic Engineering, Wuhan 430074, China.
- Cancer Center, Hubei Key Laboratory of Precision Radiation Oncology, Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430022, China; Key Laboratory of Biological Targeted Therapy (Huazhong University of Science and Technology), Ministry of Education, Wuhan, Hubei 430022, China. Electronic address: [email protected].
- Cancer Center, Hubei Key Laboratory of Precision Radiation Oncology, Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430022, China; Key Laboratory of Biological Targeted Therapy (Huazhong University of Science and Technology), Ministry of Education, Wuhan, Hubei 430022, China. Electronic address: [email protected].
- Cancer Center, Hubei Key Laboratory of Precision Radiation Oncology, Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430022, China; Key Laboratory of Biological Targeted Therapy (Huazhong University of Science and Technology), Ministry of Education, Wuhan, Hubei 430022, China. Electronic address: [email protected].
Abstract
To investigate the feasibility of a deep learning-based method for generating intensity-modulated proton therapy (IMPT) spot weights to enable a faster, more automated workflow. A 3D Attention U-Net with a masked mean absolute error loss generated spot weights from four input channels (optimized plan dose, reference dose, CT image, spot mask), using planned spot weights as labels, and trained and tested on prostate, brain, and lung cases. Robustness was evaluated on target dose metrics only. The workflow was validated in the Eclipse® treatment planning system and delivered on a ProBeam 360° system. For weights in the range 0-5, mean absolute errors were below 0.8 for the prostate and brain models (15.9% and 48.1% of all weights, respectively) and below 1.7 for the lung model (31.2%). Mean relative errors were below 10% for the prostate model (5-65, 83.7%), 20% for the brain model (5-65, 51.7%), and 40% for the lung model (5-110, 68.6%); the remaining weights lay above these ranges and accounted for <0.5% of all weights. Gamma passing rates within the body contours (2%, 2 mm, 10% dose threshold) were 99.73 ± 0.32%, 98.95 ± 0.86%, and 92.75 ± 3.52% for the prostate, brain, and lung models, respectively. All delivered plans met the clinical QA acceptance criteria. The proposed framework demonstrates the technical feasibility of generating IMPT spot weights with deep learning and implementing them on a clinical delivery system. Further improvement is needed for heterogeneous sites such as the lung.