• Corpus ID: 204743742

Deep learning for accelerating Monte Carlo radiation transport simulation in intensity-modulated radiation therapy

  title={Deep learning for accelerating Monte Carlo radiation transport simulation in intensity-modulated radiation therapy},
  author={Zhao Peng and Hongming Shan and Tianyu Liu and Xi Pei and Jieping Zhou and Ge Wang and X. George Xu},
  journal={arXiv: Medical Physics},
Cancer is a primary cause of morbidity and mortality worldwide. The radiotherapy plays a more and more important role in cancer treatment. In the radiotherapy, the dose distribution maps in patient need to be calculated and evaluated for the purpose of killing tumor and protecting healthy tissue. Monte Carlo (MC) radiation transport calculation is able to account for all aspects of radiological physics within 3D heterogeneous media such as the human body and generate the dose distribution maps… 

Figures and Tables from this paper

Fast Monte Carlo dose calculation based on deep learning

  • Jiaqi FuJ. BaiYanfang LiuCheng Ni
  • Physics, Medicine
    2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
  • 2020
The 3D CT-MCDL proposed by this study can fast and accurately calculate dose distribution at different cancer sites and plan types (IMRT and VMAT), it can be applied clinically to dose correction in plan optimization as well as in the final dose calculation.

Millisecond speed deep learning based proton dose calculation with Monte Carlo accuracy

A deep learning based millisecond speed dose calculation algorithm (DoTA) accurately predicting the dose deposited by mono-energetic proton pencil beams for arbitrary energies and patient geometries and significantly improves upon analytical pencil beam algorithms both in precision and speed.

Boosting radiotherapy dose calculation accuracy with deep learning

It is hypothesized that a conversion scheme can be established to boost low‐accuracy doses to high-accuracy, using intensity information obtained from computed tomography (CT) images, by converting between two commercially available dose calculation methods: Anisotropic analytic algorithm and Acuros XB (AXB).

Learning the Physics of Particle Transport via Transformers

This study presents a data-driven dose calculation algorithm predicting the dose deposited by monoenergetic proton beams for arbitrary energies and patient geometries, and trains the network and evaluates prediction accuracy using computationally expensive but accurate Monte Carlo simulations, considered the gold standard in particle physics.

Fast and accurate dose predictions for novel radiotherapy treatments in heterogeneous phantoms using conditional 3D-UNet generative adversarial networks.

A generative adversarial network (GAN) model is developed, which is able to emulate the equivalent Geant4 Monte Carlo simulation with adequate accuracy and use it to predict the radiation dose delivered by a broad synchrotron beam to various phantoms.

Artificial Intelligence for Monte Carlo Simulation in Medical Physics

Monte Carlo simulation of particle tracking in matter is the reference simulation method in the field of medical physics. It is heavily used in various applications such as 1) patient dose

Advanced Monte Carlo simulations of emission tomography imaging systems with GATE

Some methodological developments that are not specific for imaging but that can improve detector modeling and provide computation time gains, such as Variance Reduction Techniques and Artificial Intelligence integration, are described and discussed.



MCDNet – A Denoising Convolutional Neural Network to Accelerate Monte Carlo Radiation Transport Simulations: A Proof of Principle With Patient Dose From X-Ray CT Imaging

This paper proposes and demonstrates the Monte Carlo Denoising Net (MCDNet), a convolutional encoder-decoder neural network, for the purpose of accelerating the MC radiation transport simulations for patient CT dosimetry, and is the first CNN-based method to speed-up MC radiation Transport simulations involving 3D and heterogeneous patient anatomies for x-ray CT.

ARCHERRT - a GPU-based and photon-electron coupled Monte Carlo dose computing engine for radiation therapy: software development and application to helical tomotherapy.

ARCHERRT was developed successfully to perform fast and accurate MC dose calculation for radiotherapy using PSFs and patient CT phantoms and achieves a fast speed for PSF-based dose calculations.

3-D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning From a 2-D Trained Network

A conveying path-based convolutional encoder-decoder (CPCE) network in 2-D and 3-D configurations within the GAN framework for LDCT denoising, which has a better performance in that it suppresses image noise and preserves subtle structures.

Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction

It is shown that the deep learning approach, combined with the feedback from radiologists, produces higher quality reconstructions than or similar to that using the current commercial methods.

Report of the AAPM Task Group No. 105: Issues associated with clinical implementation of Monte Carlo-based photon and electron external beam treatment planning.

The purpose of this report is to set out the salient issues associated with clinical implementation and experimental verification of MC dose algorithms, and to provide the framework upon which to build a comprehensive program for commissioning and routine quality assurance of MC-based treatment planning systems.

Quadratic Autoencoder for Low-Dose CT Denoising

  • Fenglei FanHongming ShanGe Wang
  • Computer Science
    15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine
  • 2019
This paper uses Quadratic neurons to construct an encoder-decoder structure, referred to as the quadratic autoencoder, and applies it for low-dose CT denoising, and performs experiments on the Mayo low- dose CT dataset to demonstrate that the quadRatic aut Koencoder yields a betterDenoising performance.

Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising

The experimental results on the Mayo low-dose CT dataset demonstrate the utility and robustness of quadratic autoencoder in terms of image denoising and model efficiency.

Accelerated Correction of Reflection Artifacts by Deep Neural Networks in Photo-Acoustic Tomography

Based on the simulated PAT dataset from computed tomography (CT) scans, this network-accelerated reconstruction approach is shown to outperform two state-of-the-art iterative algorithms in terms of the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) in the presence of noise.

A technique for the quantitative evaluation of dose distributions.

A composite distribution has recently been developed that presents the dose difference in regions that fail both dose-difference and DTA comparison criteria, and a technique is developed to unify dose distribution comparisons using the acceptance criteria.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.