A convolutional neural network model for EPID-based non-transit dosimetry.

PURPOSE: To develop an alternative computational approach for EPID-based non-transit dosimetry using a convolutional neural network model. METHOD: A U-net followed by a non-trainable layer named True Dose Modulation recovering the spatialized information was developed. The model was trained on 186 Intensity-Modulated Radiation Therapy Step & Shot beams from 36 treatment plans of different tumor locations to convert grayscale portal images into planar absolute dose distributions. Input data were acquired from an amorphous-Silicon Electronic Portal Image Device and a 6 MV X-ray beam. Ground truths were computed from a conventional kernel-based dose algorithm. The model was trained by a two-step learning process and validated through a five-fold cross-validation procedure with sets of training and validation of 80% and 20%, respectively. A study regarding the dependance of the amount of training data was conducted. The performance of the model was evaluated from a quantitative analysis based the ϒ-index, absolute and relative errors computed between the inferred dose distributions and ground truths for six square and 29 clinical beams from seven treatment plans. These results were also compared to those of an existing portal image-to-dose conversion algorithm. RESULTS: For the clinical beams, averages of ϒ-index and ϒ-passing rate (2%-2mm > 10% Dmax ) of 0.24 (±0.04) and 99.29 (±0.70)% were obtained. For the same metrics and criteria, averages of 0.31 (±0.16) and 98.83 (±2.40)% were obtained with the six square beams. Overall, the developed model performed better than the existing analytical method. The study also showed that sufficient model accuracy can be achieved with the amount of training samples used. CONCLUSION: A deep learning-based model was developed to convert portal images into absolute dose distributions. The accuracy obtained shows that this method has great potential for EPID-based non-transit dosimetry.

An efficient numerical tool for dose deposition prediction applied to synchrotron medical imaging and radiation therapy.

Medical imaging and radiation therapy are widely used synchrotron-based techniques which have one thing in common: a significant dose delivery to typically biological samples. Among the ways to provide the experimenters with image guidance techniques indicating optimization strategies, Monte Carlo simulation has become the gold standard for accurately predicting radiation dose levels under specific irradiation conditions. A highly important hampering factor of this method is, however, its slow statistical convergence. A track length estimator (TLE) module has been coded and implemented for the first time in the open-source Monte Carlo code GATE/Geant4. Results obtained with the module and the procedures used to validate them are presented. A database of energy-absorption coefficients was also generated, which is used by the TLE calculations and is now also included in GATE/Geant4. The validation was carried out by comparing the TLE-simulated doses with experimental data in a synchrotron radiation computed tomography experiment. The TLE technique shows good agreement versus both experimental measurements and the results of a classical Monte Carlo simulation. Compared with the latter, it is possible to reach a pre-defined statistical uncertainty in about two to three orders of magnitude less time for complex geometries without loss of accuracy.

First theoretical determination of relative biological effectiveness of very high energy electrons.

Very high energy electrons (VHEEs, E > 70 MeV) present promising clinical advantages over conventional beams due to their increased range, improved penumbra and relative insensitivity to tissue heterogeneities. They have recently garnered additional interest in their application to spatially fractionated radiotherapy or ultra-high dose rate (FLASH) therapy. However, the lack of radiobiological data limits their rapid development. This study aims to provide numerical biologically-relevant information by characterizing VHEE beams (100 and 300 MeV) against better-known beams (clinical energy electrons, photons, protons, carbon and neon ions). Their macro- and microdosimetric properties were compared, using the dose-averaged linear energy transfer ([Formula: see text]) as the macroscopic metric, and the dose-mean lineal energy [Formula: see text] and the dose-weighted lineal energy distribution, yd(y), as microscopic metrics. Finally, the modified microdosimetric kinetic model was used to calculate the respective cell survival curves and the theoretical RBE. From the macrodosimetric point of view, VHEEs presented a potential improved biological efficacy over clinical photon/electron beams due to their increased [Formula: see text]. The microdosimetric data, however, suggests no increased biological efficacy of VHEEs over clinical electron beams, resulting in RBE values of approximately 1, giving confidence to their clinical implementation. This study represents a first step to complement further radiobiological experiments.

Multiple speckle exposure imaging for the study of blood flow changes induced by functional activation of barrel cortex and olfactory bulb in mice.

Speckle contrast imaging allows in vivo imaging of relative blood flow changes. Multiple exposure speckle imaging (MESI) is more accurate than the standard single-exposure method since it allows separating the contribution of the static and moving scatters of the recorded speckle patterns. MESI requires experimental validation on phantoms prior to in vivo experiments to ensure the proper calibration of the system and the robustness of the model. The data analysis relies on the calculation of the speckle contrast for each exposure and a subsequent nonlinear fit to the MESI model to extract the scatterers correlation time and the relative contribution of moving scatters. We have designed two multichannel polydimethylsiloxane chips to study the influence of multiple and static scattering on the accuracy of MESI quantitation. We also propose a method based on standard C++ libraries to implement a computationally efficient analysis of the MESI data. Finally, the system was used to obtain in vivo hemodynamic data on two distinct sensory areas of the mice brain: the barrel cortex and the olfactory bulb.