CENTRE DE RECHERCHE EN ACQUISITION ET TRAITEMENT D'IMAGES POUR LA SANTE

Domaines scientifiques déclarés au RNSR

Mots-clés des publications HAL repérées

Projets ANR

• Reconstruction par tomographie électronique de projections à faible DOSE d'électrons · 2026
• Reconstruction de l'anisotropie du collagene par imagerie ultrasonore · 2026
• Fusion de données d'imagerie et de texte pour la prédiction longitudinale et l'intervention dans l'AVC · 2025

Publications HAL récentes repérées

• A convergent Plug-and-Play Majorization-Minimization algorithm for Poisson inverse problems · 2026

  Résumé de la publication : In this paper, we present a novel variational plug-and-play algorithm for Poisson inverse problems. Our approach minimizes an explicit functional which is the sum of a Kullback-Leibler data fidelity term and a regularization term based on a pre-trained neural network. By combining…

• Partial Volume Correction of SPECT Images With Deep Learning Trained on Synthetic Data · 2026

  Résumé de la publication : Partial Volume Effects (PVEs) cause blurring and inaccuracies in activity measurements in SPECT imaging. They are a major challenge, especially for SPECT-based dosimetry in radionuclide therapies using 177 Lu. This study aims to develop and evaluate new deep learning methods to correct…

• Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans · 2026

  Résumé de la publication : With the growing volume of CT examinations, there is an increasing demand for automated tools such as organ segmentation, abnormality detection, and report generation to support radiologists in managing their clinical workload. Multi-label classification of 3D Chest CT scans remains a critical…

• Icecream: High-Fidelity Equivariant Cryo-Electron Tomography · 2026

  Résumé de la publication : Cryo-electron tomography (cryo-ET) visualizes 3D cellular architecture in near-native states. Recent deep-learning methods (CryoCARE, IsoNet, DeepDeWedge, CryoLithe) improve denoising and artifact correction, but performance remains limited by very low signal-to-noise ratio, a restricted angular range (‘missing wedge’), and the lack of ground…

• A causal adversarial graph neural network for multi-center autism spectrum disorder identification · 2026

  Résumé de la publication : Autism spectrum disorder (ASD) diagnosis from resting-state fMRI (rs-fMRI) remains challenging due to spurious feature correlations, site-related distribution shifts, and limited interpretability of existing models. To overcome these issues, we propose a causal adversarial graph neural network (CAG) that integrates causal inference…