A5051084728- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Advanced Radiotherapy Techniques
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Advanced MRI Techniques and Applications
- Machine Fault Diagnosis Techniques
- Image and Signal Denoising Methods
- Blind Source Separation Techniques
- Retinal Imaging and Analysis
- Radiation Dose and Imaging
- AI in cancer detection
- Prostate Cancer Diagnosis and Treatment
- Cerebrovascular and Carotid Artery Diseases
- Spectroscopy and Chemometric Analyses
- Advanced Image Processing Techniques
- Medical Imaging and Analysis
- Analog and Mixed-Signal Circuit Design
- Fault Detection and Control Systems
- Graph Theory and Algorithms
- ECG Monitoring and Analysis
- Radiation Therapy and Dosimetry
- Sparse and Compressive Sensing Techniques
- Image Retrieval and Classification Techniques
- Generative Adversarial Networks and Image Synthesis
Laboratoire Traitement du Signal et de l'Image
2016-2025
Centre Eugène Marquis
2019-2024
Inserm
2014-2024
Université de Rennes
2014-2024
Centre Hospitalier Universitaire de Rennes
2023
Université Rennes 2
2018
National Institutes of Health
2010-2012
Université Paris-Est Créteil
2002-2006
Laboratoire Images, signaux et systèmes intelligents
2006
Université Paris Cité
2002-2006
Purpose Anatomical variations occur during head and neck (H&N) radiotherapy treatment. kV cone‐beam computed tomography (CBCT) images can be used for daily dose monitoring to assess owing anatomic changes. Deep learning methods (DLMs) have recently been proposed generate pseudo‐CT (pCT) from CBCT perform calculation. This study aims evaluate the accuracy of a DLM compare this method with three existing calculation in H&N cancer radiotherapy. Methods Forty‐four patients received VMAT...
In this paper, we propose some recent works on data analysis and synthesis based Empirical Mode Decomposition (EMD). Firstly, a direct 2D extension of original Huang EMD algorithm with application to texture analysis, fractional Brownian motion synthesis. Secondly, an analytical version PDE in 1D-space is presented. We proposed 2D-case the so-called "sifting process" used Huang's EMD. The 2D-sifting process performed two steps: extrema detection (by neighboring window or morphological...
A novel Empirical Mode Decomposition (EMD) algorithm, called 2T-EMD, for both mono- and multivariate signals is proposed in this paper. It differs from the other approaches by its computational lightness algorithmic simplicity. The method essentially based on a redefinition of signal mean envelope, computed thanks to new characteristic points, which offers possibility decompose without any projection. scope application algorithm specified, comparison 2T-EMD technique with classical methods...
Background and Purpose: Addressing the need for accurate dose calculation in MRI-only radiotherapy, generation of synthetic Computed Tomography (sCT) from MRI has emerged. Deep learning (DL) techniques, have shown promising results achieving high sCT accuracies. However, existing synthesis methods are often center-specific, posing a challenge to their generalizability. To overcome this limitation, recent studies proposed approaches, such as multicenter training . Material methods: The...
ou non, émanant des établissements d'enseignement et de recherche français étrangers, laboratoires publics privés.
Image registration is fundamental in medical imaging, enabling precise alignment of anatomical structures for diagnosis, treatment planning, image-guided interventions, and longitudinal monitoring. This work introduces IMPACT (Image Metric with Pretrained model-Agnostic Comparison Transmodality registration), a novel similarity metric designed robust multimodal image registration. Rather than relying on raw intensities, handcrafted descriptors, or task-specific training, defines semantic...
We present a texture analysis algorithm based on gray-level cooccurrence (GLC) model and bidimensional empirical mode decomposition (BEMD) of field. The EMD, which has been recently introduced in signal processing by Huang 1998, is adaptive for nonlinear nonstationary data analysis. main contribution our approach to apply the extraction image denoising. This decomposition, obtained sifting process, plays an important role characterization regions textured images. process realized using...
The quality assurance of synthetic CT (sCT) is crucial for safe clinical transfer to an MRI-only radiotherapy planning workflow. aim this work propose a population-based process assessing local errors in the generation sCTs and their impact on dose distribution. For analysis be anatomically meaningful, customized interpatient registration method brought population data same coordinate system. Then, voxel-based was applied two sCT methods: bulk-density generative adversarial network. MRI...
Introduction For radiotherapy based solely on magnetic resonance imaging (MRI), generating synthetic computed tomography scans (sCT) from MRI is essential for dose calculation. The use of deep learning (DL) methods to generate sCT has shown encouraging results if the images used training network and generation come same device. objective this study was create evaluate a generic DL model capable sCTs various devices prostate Materials In total, 90 patients three centers (30 CT-MR...
In this paper, we present a Bayesian maximum posteriori method for multi-slice helical CT reconstruction based on an L0-norm prior. It makes use of very low number projections. A set surrogate potential functions is used to successively approximate the function while generating prior and accelerate convergence speed. Simulation results show that proposed provides high quality reconstructions with highly sparse sampled noise-free presence noise, still significantly better than obtained...