Photonics Research · 2020 · 13 citations · 30 references
MedicineBiomedical EngineeringRadiologyBiomedical ImagingDiagnostic ImagingDiagnostic RadiologyMonte Carlo DosimetryMonte Carlo MethodsMonte Carlo SimulationPhoton DosimetryRadiobiological ModelingDeep Reinforcement LearningMonte Carlo EstimationMonte Carlo Scatter SimulationParticle Density EstimationPhoton ScatterPhoton ScatteringScatter ModelingScattering
Particle distribution estimation is an important issue in medical diagnosis. In particular, photon scattering in some medical devices extremely degrades image quality and causes measurement inaccuracy. The Monte Carlo (MC) algorithm is regarded as the most accurate particle estimation approach but is still time-consuming, even with graphic processing unit (GPU) acceleration. The goal of this work is to develop an automatic scatter estimation framework for high-efficiency photon distribution estimation. Specifically, a GPU-based MC simulation initially yields a raw scatter signal with a low photon number to hasten scatter generation. In the proposed method, assume that the scatter signal follows Poisson distribution, where an optimization objective function fused with sparse feature penalty is modeled. Then, an over-relaxation algorithm is deduced mathematically to solve this objective function. For optimizing the parameters in the over-relaxation algorithm, the deep <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="m1"> <mml:mrow> <mml:mi>Q</mml:mi> </mml:mrow> </mml:math> -network in the deep reinforcement learning scheme is built to intelligently interact with the over-relaxation algorithm to accurately and rapidly estimate a scatter signal with the large range of photon numbers. Experimental results demonstrated that our proposed framework can achieve superior performance with structural similarity <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="m2"> <mml:mrow> <mml:mo form="prefix">></mml:mo> <mml:mn>0.94</mml:mn> </mml:mrow> </mml:math> , peak signal-to-noise ratio <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="m3"> <mml:mrow> <mml:mo form="prefix">></mml:mo> <mml:mn>26.55</mml:mn> <mml:mtext> </mml:mtext> <mml:mi>dB</mml:mi> </mml:mrow> </mml:math> , and relative absolute error <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="m4"> <mml:mrow> <mml:mo form="prefix"><</mml:mo> <mml:mn>5.62</mml:mn> <mml:mi>%</mml:mi> </mml:mrow> </mml:math> , and the lowest computation time for one scatter image generation can be within 2 s.
30
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan C. Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing · 2004 · 56K citations
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Mastering the game of Go with deep neural networks and tree search
David Silver, Aja Huang, Chris J. Maddison et al. · Nature · 2016 · 15.8K citations