F. Sureau
YOU?
Author Swipe
View article: Bimodal PET/MRI generative reconstruction based on VAE architectures
Bimodal PET/MRI generative reconstruction based on VAE architectures Open
Objective. In this study, we explore positron emission tomography (PET)/magnetic resonance imaging (MRI) joint reconstruction within a deep learning framework, introducing a novel synergistic method. Approach. We propose a new approach bas…
View article: Synergistic PET/CT Reconstruction Using a Joint Generative Model
Synergistic PET/CT Reconstruction Using a Joint Generative Model Open
We propose in this work a framework for synergistic positron emission tomography (PET)/computed tomography (CT) reconstruction using a joint generative model as a penalty. We use a synergistic penalty function that promotes PET/CT pairs th…
View article: A Bregman Majorization-Minimization Framework For Pet Image Reconstruction
A Bregman Majorization-Minimization Framework For Pet Image Reconstruction Open
International audience
View article: Deep Equilibrium for Hyperparameter Estimation in Dynamic PET Reconstruction
Deep Equilibrium for Hyperparameter Estimation in Dynamic PET Reconstruction Open
International audience
View article: Synergistic PET/MR Reconstruction with VAE Constraint
Synergistic PET/MR Reconstruction with VAE Constraint Open
International audience
View article: Convergent ADMM Plug and Play PET Image Reconstruction
Convergent ADMM Plug and Play PET Image Reconstruction Open
In this work, we investigate hybrid PET reconstruction algorithms based on coupling a model-based variational reconstruction and the application of a separately learnt Deep Neural Network operator (DNN) in an ADMM Plug and Play framework. …
View article: VAE constrained MR guided PET reconstruction
VAE constrained MR guided PET reconstruction Open
International audience
View article: Use of dynamic reconstruction for parametric Patlak imaging in dynamic whole body PET
Use of dynamic reconstruction for parametric Patlak imaging in dynamic whole body PET Open
Dynamic whole body (DWB) PET acquisition protocols enable the use of whole body parametric imaging for clinical applications. In FDG imaging, accurate parametric images of Patlak K i can be complementary to regular standardised uptake valu…
View article: Euclid: Forecasts for k-cut 3×2 Point Statistics
Euclid: Forecasts for k-cut 3×2 Point Statistics Open
Modelling uncertainties at small scales, i.e. high k in the power spectrum P(k), due to baryonic feedback, nonlinear structure growth and the fact that galaxies are biased tracers poses a significant obstacle to fully leverage the constrai…
View article: Euclid: Forecasts for $k$-cut $3 \times 2$ Point Statistics
Euclid: Forecasts for $k$-cut $3 \times 2$ Point Statistics Open
Modelling uncertainties at small scales, i.e. high $k$ in the power spectrum $P(k)$, due to baryonic feedback, nonlinear structure growth and the fact that galaxies are biased tracers poses a significant obstacle to fully leverage the cons…
View article: Dynamic 4D PET Reconstruction Using the Spectral Model and Adaptive Residual Modelling
Dynamic 4D PET Reconstruction Using the Spectral Model and Adaptive Residual Modelling Open
International audience
View article: <i>Euclid</i>: Forecast constraints on the cosmic distance duality relation with complementary external probes
<i>Euclid</i>: Forecast constraints on the cosmic distance duality relation with complementary external probes Open
Context. In metric theories of gravity with photon number conservation, the luminosity and angular diameter distances are related via the Etherington relation, also known as the distance duality relation (DDR). A violation of this relation…
View article: Shear measurement bias
Shear measurement bias Open
We present a new shear calibration method based on machine learning. The method estimates the individual shear responses of the objects from the combination of several measured properties on the images using supervised learning. The superv…
View article: Shear measurement bias
Shear measurement bias Open
We present a study of the dependencies of shear bias on simulation (input) and measured (output) parameters, noise, point-spread function anisotropy, pixel size, and the model bias coming from two different and independent galaxy shape est…
View article: Deep learning for a space-variant deconvolution in galaxy surveys
Deep learning for a space-variant deconvolution in galaxy surveys Open
The deconvolution of large survey images with millions of galaxies requires developing a new generation of methods that can take a space-variant point spread function into account. These methods have also to be accurate and fast. We invest…
View article: Shear measurement bias II: a fast machine learning calibration method
Shear measurement bias II: a fast machine learning calibration method Open
We present a new shear calibration method based on machine learning. The\nmethod estimates the individual shear responses of the objects from the\ncombination of several measured properties on the images using supervised\nlearning. The sup…
View article: Shear measurement bias II: a fast machine learning calibration method
Shear measurement bias II: a fast machine learning calibration method Open
We present a new shear calibration method based on machine learning. The method estimates the individual shear responses of the objects from the combination of several measured properties on the images using supervised learning. The superv…
View article: <i>Euclid</i>: the selection of quiescent and star-forming galaxies using observed colours
<i>Euclid</i>: the selection of quiescent and star-forming galaxies using observed colours Open
The Euclid mission will observe well over a billion galaxies out to z ∼ 6 and beyond. This will offer an unrivalled opportunity to investigate several key questions for understanding galaxy formation and evolution. The first step for many …
View article: <i>Euclid</i>: The reduced shear approximation and magnification bias for Stage IV cosmic shear experiments
<i>Euclid</i>: The reduced shear approximation and magnification bias for Stage IV cosmic shear experiments Open
Context. Stage IV weak lensing experiments will offer more than an order of magnitude leap in precision. We must therefore ensure that our analyses remain accurate in this new era. Accordingly, previously ignored systematic effects must be…
View article: Learning sparse representations on the sphere
Learning sparse representations on the sphere Open
Many representation systems on the sphere have been proposed in the past, such as spherical harmonics, wavelets, or curvelets. Each of these data representations is designed to extract a specific set of features, and choosing the best fixe…
View article: Unsupervised feature-learning for galaxy SEDs with denoising autoencoders
Unsupervised feature-learning for galaxy SEDs with denoising autoencoders Open
With the increasing number of deep multi-wavelength galaxy surveys, the spectral energy distribution (SED) of galaxies has become an invaluable tool for studying the formation of their structures and their evolution. In this context, stand…
View article: Shear measurement bias I: dependencies on methods, simulation parameters and measured parameters
Shear measurement bias I: dependencies on methods, simulation parameters and measured parameters Open
We present a study of the dependencies of shear bias on simulation (input) and measured (output) parameters, noise, point-spread function anisotropy, pixel size, and the model bias coming from two different and independent galaxy shape est…