TY  - JOUR
AU  - Simard, Mikaël
AU  - Fullarton, Ryan
AU  - Volz, Lennart
AU  - Schuy, Christoph
AU  - Chung, Savanna
AU  - Baker, Colin
AU  - Graeff, Christian
AU  - Fekete, Charles-Antoine Collins
TI  - A generative adversarial network to improve integrated mode proton imaging resolution using paired proton–carbon data
JO  - Medical physics
VL  - 52
IS  - 9
SN  - 0094-2405
CY  - Hoboken, NJ
PB  - Wiley
M1  - GSI-2025-01088
SP  - e18081
PY  - 2025
N1  - Beamtime funding of Philipps University Marburg (MIT-2022-12). This is an open access article under the terms of the Creative Commons Attribution License 4.
AB  - Integrated mode proton imaging is a clinically accessible method for proton radiographs (pRads), but its spatial resolution is limited by multiple Coulomb scattering (MCS). As the amplitude of MCS decreases with increasing particle charge, heavier ions such as carbon ions produce radiographs with better resolution (cRads). Improving image resolution of pRads may thus be achieved by transferring individual proton pencil beam images to the equivalent carbon ion data using a trained image translation network. The approach can be interpreted as applying a data-driven deconvolution operation with a spatially variant point spread function.Propose a deep learning framework based on paired proton-carbon data to increase the resolution of integrated mode pRads.A conditional generative adversarial network, Proton2Carbon, was developed to translate proton pencil beam images into synthetic carbon ion beam images. The model was trained on 547 224 paired proton-carbon images acquired with a scintillation detector at the Marburg Ion Therapy Centre. Image reconstruction was performed using a 2D lateral method, and the model was evaluated on internal and external datasets for spatial resolution, using custom 3D-printed line pair modules.The Proton2Carbon model improved the spatial resolution of pRads from 1.7 to 2.7 lp/cm on internal data and to 2.3 lp/cm on external data, demonstrating generalizability. Water equivalent thickness accuracy remained consistent with pRads and cRads. Evaluation on an anthropomorphic head phantom showed enhanced structural clarity, though some increased noise was observed.This study demonstrates that deep learning can enhance pRad image quality by leveraging paired proton-carbon data. Proton2Carbon can be integrated into existing imaging workflows to improve clinical and research applications of proton radiography. To facilitate further research, the full dataset used to train Proton2Carbon is publicly released and available at https://zenodo.org/records/14945165.
KW  - Protons
KW  - Carbon
KW  - Image Processing, Computer-Assisted: methods
KW  - Deep Learning
KW  - Humans
KW  - Phantoms, Imaging
KW  - Generative Adversarial Networks
KW  - generative adversarial network (Other)
KW  - image‐to‐image translation (Other)
KW  - ion beam therapy (Other)
KW  - ion imaging (Other)
KW  - ion radiography (Other)
KW  - super‐resolution imaging (Other)
KW  - Protons (NLM Chemicals)
KW  - Carbon (NLM Chemicals)
LB  - PUB:(DE-HGF)16
C6  - pmid:40926569
UR  - <Go to ISI:>//WOS:001570644000001
DO  - DOI:10.1002/mp.18081
UR  - https://repository.gsi.de/record/362215
ER  -