PROTOTWIN-PET: A deep learning and GPU-based workflow for dose verification in proton therapy with PET

Cabrales, PabloOnecha, Víctor V.Izquierdo-García, DavidFraile Prieto, Luis MarioUdías Moinelo, José ManuelLópez Herraiz, Joaquín2025-07-112025-07-112025-01-20P. Cabrales, V. V. Onecha, D. Izquierdo-García, L. M. Fraile, J. M. Udías, y J. L. Herraiz, «PROTOTWIN-PET: A Deep Learning and GPU-Based Workflow for Dose Verification in Proton Therapy With PET», IEEE Trans. Radiat. Plasma Med. Sci., vol. 9, n.o 6, pp. 821-831, jul. 2025, doi: 10.1109/TRPMS.2025.3531536.10.1109/TRPMS.2025.3531536https://hdl.handle.net/20.500.14352/122436In proton therapy (PT), accurate dose delivery verification is critical for detecting treatment plan deviations. This can be achieved by imaging activated positron emitters with a positron emission tomography (PET) acquisition and converting the data into a delivered dose image. This work presents PROTOTWIN-PET (PROTOn therapy digital TWIN models for dose verification with PET), a patient-specific, deep learning (DL) and GPU-based workflow for 3-D dose verification. The proposed workflow generates a dataset of simulated, realistic 3-D PET and dose pairs that reflect possible clinical deviations in patient positioning and physical parameters. Using this dataset, a DL model is trained to estimate the delivered dose from the PET image, incorporating a deviation-predicting branch (DPB) to estimate patient positioning deviations. PROTOTWIN-PET is demonstrated on a two-field oropharyngeal cancer treatment plan, estimating the delivered dose in milliseconds with an average mean relative error of 0.6% and near-perfect gamma passing rates (3 mm, 3%). Positioning deviations are estimated on average within a tenth of a millimeter and degree. PROTOTWIN-PET can be implemented within the one-day interval between the plan CT acquisition and the first treatment session, potentially enabling timely treatment plan adjustments and maximizing the precision of PT. PROTOTWIN-PET is available at github.com/pcabrales/prototwin-pet.git.engPROTOTWIN-PET: A deep learning and GPU-based workflow for dose verification in proton therapy with PETjournal article2469-7303https://www.doi.org/10.1109/TRPMS.2025.3531536https://ieeexplore.ieee.org/document/10847605open access539.1615.849.6Deep learning (DL)Digital twinsDose verificationGPUPositron emission tomography (PET)Proton therapy (PT)Física nuclearDiagnóstico por imagen y medicina nuclear2207 Física Atómica y Nuclear3201.12 Radioterapia