A5066059428- Advanced MRI Techniques and Applications
- Medical Image Segmentation Techniques
- Advanced Neuroimaging Techniques and Applications
- Functional Brain Connectivity Studies
- EEG and Brain-Computer Interfaces
- Multiple Sclerosis Research Studies
- Image Retrieval and Classification Techniques
- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Brain Tumor Detection and Classification
- Medical Imaging Techniques and Applications
- Morphological variations and asymmetry
- Cardiac Imaging and Diagnostics
- Medical Imaging and Analysis
- Robotics and Sensor-Based Localization
- Anatomy and Medical Technology
- 3D Shape Modeling and Analysis
- Image Processing Techniques and Applications
- Neural dynamics and brain function
- Image and Signal Denoising Methods
- AI in cancer detection
- Bone and Joint Diseases
- Computer Graphics and Visualization Techniques
- Gene expression and cancer classification
- Advanced Vision and Imaging
Université de Rennes
2014-2023
Institut de Recherche en Informatique et Systèmes Aléatoires
2014-2023
Centre National de la Recherche Scientifique
2014-2023
Inserm
2014-2023
Empenn
2023
Institut national de recherche en informatique et en automatique
2013-2022
Centre Hospitalier Universitaire de Rennes
2011-2019
Université Rennes 2
2019
Département de la Santé et de l'Action Sociale
2009-2018
Institut de Recherche en Santé, Environnement et Travail
2017
A critical issue in image restoration is the problem of noise removal while keeping integrity relevant information. Denoising a crucial step to increase quality and improve performance all tasks needed for quantitative imaging analysis. The method proposed this paper based on 3-D optimized blockwise version nonlocal (NL)-means filter (Buades, , 2005). NL-means uses redundancy information under study remove noise. has been already demonstrated 2-D images, but reducing computational burden...
The primary objective of this study is to perform a blinded evaluation group retrospective image registration techniques using as gold standard prospective, marker-based method. To ensure blindedness, all registrations were performed by participants who had no knowledge the results until after their been submitted. A secondary goal project evaluate importance correcting geometrical distortion in MR images comparing error rectified images, i.e., those that have correction applied, with same...
In image processing, restoration is expected to improve the qualitative inspection of and performance quantitative analysis techniques. this paper, an adaptation nonlocal (NL)-means filter proposed for speckle reduction in ultrasound (US) images. Originally developed additive white Gaussian noise, we propose use a Bayesian framework derive NL-means adapted relevant noise model. Quantitative results on synthetic data show performances method compared well-established state-of-the-art methods....
We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using new open-science computing infrastructure. allowed for automatic and independent evaluation large range in fair completely manner. infrastructure used to evaluate thirteen methods MS lesions segmentation, exploring broad state-of-theart algorithms, against high-quality database 53 cases coming from four centers following common definition...
The ANALYZE software system, which permits detailed investigation and evaluation of 3-D biomedical images, is discussed. can be used with imaging modalities based on X-ray computed tomography, radionuclide emission ultrasound magnetic resonance imaging. package unique in its synergistic integration fully interactive modules for direct display, manipulation, measurement multidimensional image data. One the most versatile powerful capabilities volume rendering display. An important advantage...
All retrospective image registration methods have attached to them some intrinsic estimate of error. However, this accuracy may not always be a good indicator the distance between actual and estimated positions targets within cranial cavity. This paper describes project whose principal goal is use prospective method based on fiducial markers as 'gold standard' perform an objective, blinded evaluation several image-to-image techniques. Image volumes three modalities -- CT, MR, PET were taken...
Although numerous methods to register brains of different individuals have been proposed, no work has done, as far we know, evaluate and objectively compare the performances nonrigid (or elastic) registration on same database subjects. In this paper, propose an evaluation framework, based global local measures relevance registration. We chosen focus more particularly matching cortical areas, since intersubject are dedicated anatomical functional normalization, also because other groups shown...
Atypical functional lateralization and specialization for language have been proposed to account developmental disorders, yet results from neuroimaging studies are sparse inconsistent. This magnetic resonance imaging study compared children with a specific subtype of impairment affecting structural (n = 21), matched group typically developing using panel four tasks neither requiring reading nor metalinguistic skills, including two auditory lexico-semantic (category fluency responsive naming)...
Mood depressive disorder is one of the most disabling chronic diseases with a high rate everyday life disability that affects 350 million people around world. Recent advances in neuroimaging have reported widespread structural abnormalities, suggesting dysfunctional frontal-limbic circuit involved pathophysiological mechanisms depression. However, variety different white matter regions has been implicated and sought to suffer from lack reproducibility such categorical-based biomarkers. These...
MRI plays a crucial role in multiple sclerosis diagnostic and patient follow-up. In particular, the delineation of T2-FLAIR hyperintense lesions is although mostly performed manually - tedious task. Many methods have thus been proposed to automate this However, sufficiently large datasets with thorough expert manual segmentation are still lacking evaluate these methods. We present unique dataset for MS evaluation. It consists 53 patients acquired on 4 different scanners harmonized protocol....
A critical issue in image restoration is the problem of noise removal while keeping integrity relevant information. The method proposed this paper a fully automatic 3D blockwise version nonlocal (NL) means filter with wavelet subbands mixing. mixing based on multiresolution approach for improving quality denoising filter. Quantitative validation was carried out synthetic datasets generated BrainWeb simulator. results show that our NL-means outperforms classical implementation terms and...
Automatic segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) images is essential for clinical assessment and treatment planning MS. Recent years have seen an increasing use Convolutional Neural Networks (CNNs) this task. Although these methods provide accurate segmentation, their applicability in settings remains limited due to a reproducibility issue across different image domains. MS can highly variable characteristics patients, MRI scanners imaging...
Traditional rehabilitation techniques present limitations and the majority of patients show poor 1-year post-stroke recovery. Thus, Neurofeedback (NF) or Brain-Computer-Interface applications for stroke purposes are gaining increased attention. Indeed, NF has potential to enhance volitional control targeted cortical areas thus impact on motor function However, current implementations limited by temporal, spatial practical constraints specific imaging modality used. In this pilot work first...
In this paper, we investigate the introduction of cortical constraints for non rigid intersubject brain registration. We extract sulcal patterns with active ribbon method, presented by Le Goualher et al. (1997). An energy based registration method (Hellier al., 2001), which will be called photometric in makes it possible to incorporate matching sulci. The local sparse similarity and are, thus, expressed a unified framework. show benefits on database 18 subjects, global assessment This new...