Lotfi CHAARI

Full Professor with Toulouse INP

Menu:

• Home
• Research
• Publications
• Teaching
• Activities
• Softwares

Research

My main interest is focused on developing methods and applications for biomedical signal and image processing/analysis and remote sensing. Developments involve machine/deep learning techniques, as well as  Bayesian, variational and hybrid methods.

    Methods

• Deep and sparse neural networks
• Machine learning
• Bayesian inference
• Variational methods
• MCMC
• Efficient hybrid sampling
• Optimization
  

    Applications

• Biomedical signal and image processing/analysis

1. Image reconstruction and restoration (MRI, pMRI, MRSI)
2. Tumor relapse prediction (MRSI, MRI, PET)
   
3. Brain activity analysis (fMRI, detection-estimation)
4. EEG source localization
   
5. Drowsiness detection (EEG, ECG)
6. Anomaly detection (EEG, ECG, MRSI, PET)
   

• Remote sensing
  

1. Change detection (multi-temporal and hyperspectral data)
   
2. Hyperspectral unmixing
3. Anomaly detection
   

• AGRI2IA: Agriculture and AI
      Funding: CNRS
  
• La TEP-TDM au ⁶⁸Ga-DOTATOC, un potentiel biomarqueur prédictif de toxicité post-thérapeutique au ¹⁷⁷Lu-DOTATATE dans les TNE digestives métastatiques

        Funding : Ligue Nationale Contre le Cancer

Olga Golubnitschaja Ammar Achraf Jean-Christophe Pesquet Philippe Ciuciu  Amel Benazza-Benyahia Caroline Chaux Nelly Pustelnik Jean-Yves Tourneret Hadj Batatia Sébastien Mériaux Florence Forbes Thomas Vincent Michel Dojat Bassem Bouaziz Abdelaziz Kallel Anita Hökelmann Antonio Quintero-Rincon Alain Giros Sylvain Fuertes Gilles Picart

Topic: Parallel Magnetic Resonance Imaging reconstruction problems using wavelet representations
Supervisors: Jean-Christophe PESQUET and Philippe CIUCIU
Team: Signal and Communications, IGM LabInfo, UMR8049, University of Marne la Vallee.
Research context:
To reduce scanning time or improve spatio-temporal resolution in some MRI applications, parallel MRI acquisition techniques with multiple coils have emerged since the early 90's as powerful methods. In these techniques, MRI images have to be reconstructed from acquired undersampled "k-space" data. To this end, several reconstruction techniques have been proposed such as the widely-used SENSitivity Encoding (SENSE) method. However, the reconstructed images generally present artifacts due to the noise corrupting the observed data and coil sensitivity profile estimation errors. In this work, we present novel SENSE-based reconstruction methods which proceed with regularization in the complex wavelet domain so as to promote the sparsity of the solution. These methods achieve accurate image reconstruction under degraded experimental conditions, in which neither the SENSE method nor standard regularized methods (e.g. Tikhonov) give convincing results. The proposed approaches relies on fast parallel optimization algorithms dealing with convex but non-differentiable criteria involving suitable sparsity promoting priors. Moreover, in contrast with most of the available reconstruction methods which proceed by a slice by slice reconstruction, one of the proposed methods allows 4D (3D + time) reconstruction exploiting spatial and temporal correlations. The hyperparameter estimation problem inherent to the regularization process has also been addressed from a Bayesian viewpoint by using MCMC techniques. Experiments on real anatomical and functional data show that the proposed methods allow us to reduce reconstruction artifacts and improve the statistical sensitivity/specificity in functional MRI.

© 2020 Lotfi CHAARI
Original design by Andreas Viklund