Enhancing image quality in fast neutron-based range verification of proton therapy using a deep learning-based prior in LM-MAP-EM reconstruction.
Authors
Affiliations (7)
Affiliations (7)
- Department of Computer science, Electrical engineering and Mathematical sciences, Western Norway University of Applied Sciences, Inndalsveien 28, Bergen, Hordaland, 5063, NORWAY.
- Department of Physics and Technology, University of Bergen, Allégaten 55, Bergen, Hordaland, 5007, NORWAY.
- Department of Mathematics, The University of Manchester, Alan Turing Building, Upper Brook St, Manchester, England, M13 9SR, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND.
- Department of Oncology and Medical Physics, Haukeland Universitetssjukehus, Jonas Lies veg 65, Postboks 1400, Bergen, Hordaland, 5021, NORWAY.
- Technology Methods and Systems Data Based Methods, Fraunhofer Institute for Electronic Nano Systems ENAS, Technologie-Campus 3, Chemnitz, SN, 09126, GERMANY.
- Department of Radiation Science and Technology, Delft University of Technology, Mekelweg 15, Delft, 2629 JD, NETHERLANDS.
- Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, Inndalsveien 28, Bergen, Hordaland, 5063, NORWAY.
Abstract
This study investigates the use of list-mode (LM) maximum a posteriori (MAP) expectation maximization (EM) incorporating prior information predicted by a convolutional neural network for image reconstruction in fast neutron (FN)-based proton therapy range verification.
Approach. A conditional generative adversarial network (pix2pix) was trained on progressively noisier data, where detector resolution effects were introduced gradually to simulate realistic conditions. FN data were generated using Monte Carlo simulations of an 85 MeV proton pencil beam in a computed tomography (CT)-based lung cancer patient model, with range shifts emulating weight gain and loss. The network was trained to estimate the expected two-dimensional (2D) ground truth FN production distribution from simple back-projection images. Performance was evaluated using mean squared error (MSE), structural similarity index (SSIM), and the correlation between shifts in predicted distributions and true range shifts. 
Main results. Our results show that pix2pix performs well on noise-free data but suffers from significant degradation when detector resolution effects are introduced. Among the LM-MAP-EM approaches tested, incorporating a mean prior estimate into the reconstruction process improved performance, with LM-MAP-EM using a mean prior estimate outperforming naïve LM maximum likelihood EM (LM-MLEM) and conventional LM-MAP-EM with a smoothing quadratic energy function in terms of SSIM. 
Significance. Findings suggest that deep learning techniques can enhance iterative reconstruction for range verification in proton therapy. However, the effectiveness of the model is highly dependent on data quality, limiting its robustness in high-noise scenarios.
.