arXiv subjects

Julien Bert

Publications and source records attributed to Julien Bert.

11 recordsLinked to original sources

arXiv2026

A Fast and Generic Energy-Shifting Transformer for Hybrid Monte Carlo Radiotherapy Calculation

We introduce a novel learning framework for accelerated Monte Carlo (MC) dose calculation termed Energy-Shifting. This approach leverages deep learning to synthesize highly complex polyenergetic dose distributions directly from simple monoenergetic inputs under identical beam configurations. Unlike conventional denoising techniques, which rely on noisy low-count dose maps that compromise beam profile integrity, our method achieves superior cross-domain generalization on unseen datasets by integrating high-fidelity anatomical textures and source-specific beam similarity into the model's input space. Furthermore, we propose a novel 3D architecture termed TransUNetSE3D, featuring Transformer blocks for global context and Residual Squeeze-and-Excitation (SE) modules for adaptive channel-wise feature recalibration. Hierarchical representations of these blocks are fused into the network's latent space alongside the primary dose-map parameters, allowing physics-aware reconstruction. This hybrid design outperforms existing UNet and Transformer-based benchmarks in both spatial precision and structural preservation, while maintaining the execution speed necessary for real-time use. Our proposed pipeline achieves a Gamma Passing Rate exceeding 98% (3%/3mm) compared to the MC reference, evaluated within the framework of a treatment planning system (TPS) using 6MV TrueBeam Lineac Accelerator (LINAC) for prostate radiotherapy. These results offer a robust solution for fast volumetric dosimetry in adaptive radiotherapy.

physics.med-ph↗

arXiv2025

GATE 10 Monte Carlo particle transport simulation -- Part II: architecture and innovations

Over the past years, we have developed GATE version 10, a major re-implementation of the long-standing Geant4-based Monte Carlo application for particle and radiation transport simulation in medical physics. This release introduces many new features and significant improvements, most notably a Python-based user interface replacing the legacy static input files. The new functionality of GATE version 10 is described in the part 1 companion paper. The development brought significant challenges. In this paper, we present the solutions that we have developed to overcome these challenges. In particular, we present a modular design that robustly manages the core components of a simulation: particle sources, geometry, physics processes, and data acquisition. The architecture consists of parts written in C++ and Python, which needed to be coupled. We explain how this framework allows for the precise, time-aware generation of primary particles, a critical requirement for accurately modeling positron emission tomography (PET), radionuclide therapies, and prompt-gamma timing systems. We present how GATE 10 handles complex Geant4 physics settings while exposing a simple interface to the user. Furthermore, we describe the technical solutions that facilitate the seamless integration of advanced physics models and variance reduction techniques. The architecture supports sophisticated scoring of physical quantities (such as Linear Energy Transfer and Relative Biological Effectiveness) and is designed for multithreaded execution. The new user interface allows researchers to script complex simulation workflows and directly couple external tools, such as artificial intelligence models for source generation or detector response. By detailing these architectural innovations, we demonstrate how GATE 10 provides a more powerful and flexible tool for research and innovation in medical physics.

physics.med-ph↗

arXiv2025

GATE 10 Monte Carlo particle transport simulation -- Part I: development and new features

We present GATE version 10, a major evolution of the open-source Monte Carlo simulation application for medical physics, built on Geant4. This release marks a transformative evolution, featuring a modern Python-based user interface, enhanced multithreading and multiprocessing capabilities, the ability to be embedded as a library within other software, and a streamlined framework for collaborative development. In this Part 1 paper, we outline GATE's position among other Monte Carlo codes, the core principles driving this evolution, and the robust development cycle employed. We also detail the new features and improvements. Part 2 will detail the architectural innovations and technical challenges. By combining an open, collaborative framework with cutting-edge features, such a Monte Carlo platform supports a wide range of academic and industrial research, solidifying its role as a critical tool for innovation in medical physics.

physics.med-ph↗

arXiv2025

Machine Learning-Based Modeling of the Anode Heel Effect in X-ray Beam Monte Carlo Simulations

To develop a machine learning-based framework for accurately modeling the anode heel effect in Monte Carlo simulations of X-ray imaging systems, enabling realistic beam intensity profiles with minimal experimental calibration. Multiple regression models were trained to predict spatial intensity variations along the anode-cathode axis using experimentally acquired weights derived from beam measurements across different tube potentials. These weights captured the asymmetry introduced by the anode heel effect. A systematic fine-tuning protocol was established to minimize the number of required measurements while preserving model accuracy. The models were implemented in the OpenGATE 10 and GGEMS Monte Carlo toolkits to evaluate their integration feasibility and predictive performance. Among the tested models, gradient boosting regression (GBR) delivered the highest accuracy, with prediction errors remaining below 5% across all energy levels. The optimized fine-tuning strategy required only six detector positions per energy level, reducing measurement effort by 65%. The maximum error introduced through this fine-tuning process remained below 2%. Dose actor comparisons within Monte Carlo simulations demonstrated that the GBR-based model closely replicated clinical beam profiles and significantly outperformed conventional symmetric beam models. This study presents a robust and generalizable method for incorporating the anode heel effect into Monte Carlo simulations using machine learning. By enabling accurate, energy-dependent beam modeling with limited calibration data, the approach enhances simulation realism for applications in clinical dosimetry, image quality assessment, and radiation protection.

physics.med-ph↗

arXiv2025

Semi-Supervised Learning for Dose Prediction in Targeted Radionuclide: A Synthetic Data Study

Targeted Radionuclide Therapy (TRT) is a modern strategy in radiation oncology that aims to administer a potent radiation dose specifically to cancer cells using cancer-targeting radiopharmaceuticals. Accurate radiation dose estimation tailored to individual patients is crucial. Deep learning, particularly with pre-therapy imaging, holds promise for personalizing TRT doses. However, current methods require large time series of SPECT imaging, which is hardly achievable in routine clinical practice, and thus raises issues of data availability. Our objective is to develop a semi-supervised learning (SSL) solution to personalize dosimetry using pre-therapy images. The aim is to develop an approach that achieves accurate results when PET/CT images are available, but are associated with only a few post-therapy dosimetry data provided by SPECT images. In this work, we introduce an SSL method using a pseudo-label generation approach for regression tasks inspired by the FixMatch framework. The feasibility of the proposed solution was preliminarily evaluated through an in-silico study using synthetic data and Monte Carlo simulation. Experimental results for organ dose prediction yielded promising outcomes, showing that the use of pseudo-labeled data provides better accuracy compared to using only labeled data.

physics.med-ph↗

arXiv2024

Deep Learning-Based Beamlet Model for Generic X-Ray Beam Dose Calculation

Modeling the absorbed dose during X-ray imaging is essential for optimizing radiation exposure. Monte Carlo simulations (MCS) are the gold standard for precise 3D dose estimation but require significant computation time. Deep learning offers faster dose prediction but often lacks generality, as models are typically trained for specific anatomical sites and beam geometries. The aim in this work was proposing a generic deep-learning approach for dose calculation that can be used for multiple X-ray imaging systems. This article proposes a versatile approach combining beamlet decomposition with deep learning, where the X-ray beam is broken down into beamlets. By using a sampling approach, various beam shapes can be generated, reducing learning complexity. The model learns the dose response of a beamlet for different energies and patient properties, making it adaptable to new system geometries without altering the learning model. In this work, we propose combining two U-Net networks (1D+3D) trained on different body parts to predict the dose of a beamlet regardless of its orientation and energy. Results have shown that the deep learning-based dose engine achieved a relative dose error of approximately 1.2+/-3.87% compared to the reference dose. For a more realistic simulation in cone-beam CT, dose results exhibited a relative error within the beam of 5% compared to a full MCS. The convergence of the proposed method was faster compared to MCS, with a speedup of 130 times for equivalent dose results. The versatility of the proposed solution allows for the simulation of multiple X-ray systems without the need to retrain the deep learning model with new beam specificities. The same trained model is capable of calculating the 3D dose within the patient for helical CT, cone-beam CT, fan-beam CT, or any collimated beam shape.

physics.med-ph↗

arXiv2024

CT respiratory motion synthesis using joint supervised and adversarial learning

Objective: Four-dimensional computed tomography (4DCT) imaging consists in reconstructing a CT acquisition into multiple phases to track internal organ and tumor motion. It is commonly used in radiotherapy treatment planning to establish planning target volumes. However, 4DCT increases protocol complexity, may not align with patient breathing during treatment, and lead to higher radiation delivery. Approach: In this study, we propose a deep synthesis method to generate pseudo respiratory CT phases from static images for motion-aware treatment planning. The model produces patient-specific deformation vector fields (DVFs) by conditioning synthesis on external patient surface-based estimation, mimicking respiratory monitoring devices. A key methodological contribution is to encourage DVF realism through supervised DVF training while using an adversarial term jointly not only on the warped image but also on the magnitude of the DVF itself. This way, we avoid excessive smoothness typically obtained through deep unsupervised learning, and encourage correlations with the respiratory amplitude. Main results: Performance is evaluated using real 4DCT acquisitions with smaller tumor volumes than previously reported. Results demonstrate for the first time that the generated pseudo-respiratory CT phases can capture organ and tumor motion with similar accuracy to repeated 4DCT scans of the same patient. Mean inter-scans tumor center-of-mass distances and Dice similarity coefficients were $1.97$mm and $0.63$, respectively, for real 4DCT phases and $2.35$mm and $0.71$ for synthetic phases, and compares favorably to a state-of-the-art technique (RMSim).

cs.CV↗

arXiv2024

Fast-Track of F-18 Positron paths simulations using GANs

In recent years, the use of Monte Carlo (MC) simulations in the domain of Medical Physics has become a state-of-the-art technology that consumes lots of computational resources for the accurate prediction of particle interactions. The use of generative adversarial network (GAN) has been recently proposed as an alternative to improve the efficiency and extending the applications of computational tools in both medical imaging and therapeutic applications. This study introduces a new approach to simulate positron paths originating from Fluorine 18 (18 F) isotopes through the utilization of GANs. The proposed methodology developed a pure conditional transformer least squares (LS)-GAN model, designed to generate positron paths, and to track their interaction within the surrounding material. Conditioning factors include the pre-determined number of interactions, and the initial momentum of the emitted positrons, as derived from the emission spectrum of 18 F. By leveraging these conditions, the model aims to quickly and accurately simulate electromagnetic interactions of positron paths. Results were compared to the outcome produced with Geant4 Application for Tomography Emission (GATE) MC simulations toolkit. Less than 10 % of difference was observed in the calculation of the mean and maximum length of the path and the 1-D point spread function (PSF) for three different materials (Water, Bone, Lung).

physics.med-ph↗

arXiv2023

On-line Dose Calculation Using Deep Learning for Beams Selection in Non-Coplanar Radiotherapy

Non-coplanar Intensity-Modulated Radiation Therapy (IMRT) goes a step further by orienting the gantry carrying the radiation beam and the patient couch in a non-coplanar manner to accurately target the cancer region and better avoid organs-at-risk. The use of a non-coplanar treatment trajectory significantly enhances the degree of freedom and flexibility but increases drastically the complexity of the optimization. In inverse planning optimization the dose contribution for all potential beam directions is usually pre-calculates and pre-loads into the Treatment Planning System (TPS). The size the dose matrix becomes more critical when moving from coplanar IMRT to non-coplanar IMRT since the number of beams increases drastically. A solution would be to calculate "on-the-fly" the dose contribution to each new candidate beam during optimization. This is only possible if a dose calculation engine is fast enough to be used online during optimization iterations, which is not the case in standard method. Therefore, in this work we propose an IMRT optimization scheme using deep learning based dose engine to compute the dose matrix on-line. The proposed deep learning approach will be combined into a simulated-annealing-based optimization method for non-coplanar IMRT. Since the dose engine will compute the dose contribution on-line during the optimization, the final main optimization method requires to keep in memory a very lightweight dose matrix. The proposed method was compared with clinical data showing a good agreement considering dosimetry of the treatment plans. The main advantage of the proposed method was the reduction of the memory storage from 9GB to 10MB during the optimization process.

physics.med-ph↗

arXiv2023

Cross-modal tumor segmentation using generative blending augmentation and self training

\textit{Objectives}: Data scarcity and domain shifts lead to biased training sets that do not accurately represent deployment conditions. A related practical problem is cross-modal image segmentation, where the objective is to segment unlabelled images using previously labelled datasets from other imaging modalities. \textit{Methods}: We propose a cross-modal segmentation method based on conventional image synthesis boosted by a new data augmentation technique called Generative Blending Augmentation (GBA). GBA leverages a SinGAN model to learn representative generative features from a single training image to diversify realistically tumor appearances. This way, we compensate for image synthesis errors, subsequently improving the generalization power of a downstream segmentation model. The proposed augmentation is further combined to an iterative self-training procedure leveraging pseudo labels at each pass. \textit{Results}: The proposed solution ranked first for vestibular schwannoma (VS) segmentation during the validation and test phases of the MICCAI CrossMoDA 2022 challenge, with best mean Dice similarity and average symmetric surface distance measures. \textit{Conclusion and significance}: Local contrast alteration of tumor appearances and iterative self-training with pseudo labels are likely to lead to performance improvements in a variety of segmentation contexts.

eess.IV↗

arXiv2021

Regularized directional representations for medical image registration

In image registration, many efforts have been devoted to the development of alternatives to the popular normalized mutual information criterion. Concurrently to these efforts, an increasing number of works have demonstrated that substantial gains in registration accuracy can also be achieved by aligning structural representations of images rather than images themselves. Following this research path, we propose a new method for mono- and multimodal image registration based on the alignment of regularized vector fields derived from structural information such as gradient vector flow fields, a technique we call \textit{vector field similarity}. Our approach can be combined in a straightforward fashion with any existing registration framework by substituting vector field similarity to intensity-based registration. In our experiments, we show that the proposed approach compares favourably with conventional image alignment on several public image datasets using a diversity of imaging modalities and anatomical locations.

cs.CV↗