A5105874207- Medical Image Segmentation Techniques
- Advanced MRI Techniques and Applications
- Aortic Disease and Treatment Approaches
- Aortic aneurysm repair treatments
- Cerebrovascular and Carotid Artery Diseases
- Cardiac Valve Diseases and Treatments
- Cardiac Imaging and Diagnostics
- Vascular Malformations Diagnosis and Treatment
- Retinal Imaging and Analysis
- Intracranial Aneurysms: Treatment and Complications
- Medical Imaging Techniques and Applications
- Cardiovascular Function and Risk Factors
- Cardiovascular Health and Disease Prevention
- Industrial Vision Systems and Defect Detection
- Retinal Diseases and Treatments
- Retinal and Optic Conditions
- Renal and Vascular Pathologies
- Acute Ischemic Stroke Management
- Image and Object Detection Techniques
- Digital Image Processing Techniques
- Image Retrieval and Classification Techniques
- Advanced X-ray and CT Imaging
- Cerebrospinal fluid and hydrocephalus
- Optical Coherence Tomography Applications
- Remote-Sensing Image Classification
Paris-Est Sup
2005-2023
ESME - École d’ingénieurs pluridisciplinaires
2009-2023
Laboratoire des signaux et systèmes
2020-2023
Laboratoire Images, signaux et systèmes intelligents
2005-2023
Université Paris-Est Créteil
2005-2023
Infection et inflammation
2015
Sorbonne Université
2009-2012
Inserm
2009-2012
Background. In recent years, deep learning has been increasingly applied to a vast array of ophthalmological diseases. Inherited retinal diseases (IRD) are rare genetic conditions with distinctive phenotype on fundus autofluorescence imaging (FAF). Our purpose was automatically classify different IRDs by means FAF images using algorithm. Methods. this study, patients retinitis pigmentosa (RP), Best disease (BD), Stargardt (STGD), as well healthy comparable group were used train multilayer...
Arterial pulse wave velocity (PWV) is associated with increased mortality in aging and disease. Several studies have shown the accuracy of applanation tonometry carotid-femoral PWV (Cf-PWV) relevance evaluating central aorta stiffness using 2D cardiovascular magnetic resonance (CMR) to estimate PWV, aortic distensibility-derived through theoretical Bramwell-Hill model (BH-PWV). Our aim was compare various methods (aoPWV) estimation from 4D flow CMR, terms associations age, Cf-PWV, BH-PWV...
The segmentation of left ventricular structures is necessary for the evaluation ejection fraction (EF) and myocardial mass (LVM). A semi-automated 2D algorithm using connected filters a deformable model allowing an accurate endocardial detection was proposed. epicardial border deduced restricted inside region interest defined from border. Papillary muscles were detected fuzzy k-means algorithm. method applied to challenge training validation databases, consisting 15 subjects each. performed...
This study deals with information fusion for image segmentation. The evidence theory (or the Dempster–Shafer theory) allows modellisation of uncertainty and imprecision in as well combination different sources. Here, this approach is used an unsupervised framework to combine stochastic watershed segmentation which provides several results, a Hessian operator order obtain unique efficient method tested on natural images from Berkeley dataset evaluated using evaluation metrics. results surpass...
Diagnosis and computer-guided therapy of cerebral Arterio-Venous Malformations (AVM) require an accurate understanding the vascular network both from structural biomechanical point view. We propose to obtain such information by analyzing three Dimensional Rotational Angiography (3DRA) images. In this paper, we describe a two-step process allowing 1) 3D automatic segmentation vessels 3DRA images using region-growing based algorithm 2) reconstruction segmented constrained Delaunay...
Choroidal Neovascularization (CNV) is the advanced stage of Age-related Macular Degeneration (AMD), which leading cause irreversible visual loss for elder people in developed countries. Optical Coherence Tomography Angiography (OCTA) a recent non-invasive imaging technique widely used nowadays diagnosis and follow-up CNV. In this study, an automatic screening CNV based on deep learning performed using OCTA choriocapillaris images. eyes (advanced wet AMD) are diagnosed among healthy (no with...
3D rotational angiography (3DRA) provides high quality images of the cerebral arteriovenous malformation (AVM) nidus that can be reconstructed in 3D. However, these reconstructions are limited to only visualization without possible interactive exploration geometric characteristics structures. Refined understanding AVM angioarchitecture prior treatment is mandatory and vascular segmentation an important preliminary step allow physicians analyze complex networks help guide microcatheters...
Automated extraction of quantitative parameters from Cardiac Magnetic Resonance Images (CMRI) is crucial for the management patients with myocardial infarct. This work proposes a post-processing procedure to jointly analyze Cine and Delayed-Enhanced (DE) acquisitions in order provide an automatic quantification contraction enhancement study their relationship. For that purpose, following processes are performed: 1) DE/Cine temporal synchronization 3D scan alignment, 2) rigid registration...
Vascular imaging is crucial in the treatment of many diseases. In case cerebral ArterioVenous Malformation (AVM), where vascular network can be deeply altered, an accurate knowledge its topology required. For this purpose, after a vessels segmentation and skeletization applied on 3D rotational angiographic images (3DRA), we build symbolic tree representation thanks to topological descriptors, such as end points, junctions branches. This leads efficient tool assist neuroradiologist understand...
Neurovascular pathologies are often treated with the help of imaging to guide catheters inside arteries. However, positioning a microcatheter into aortic arch and threading it through blood vessels for embolization, mechanical thrombectomy or stenting is challenging task. Indeed, adverse anatomies frequently encountered, especially when dilated, supra-aortic branches elongated tortuous. In this article, we propose pipeline using convolutional neural networks segmentation from magnetic...
This paper deals with the registration of Magnetic Resonance (MR) and Computerized Tomography (CT) cardiac images. We use a multimodal iconic algorithm based on maximisation mutual information joint histogram two apply it to MR CT The purpose is determine in (3D+t) data volume, short-axis slices that correspond (2D+t) slices, acquired same patient. couples images should be similar according their spatial position, orientation cycle phase. used Powell's direction set optimization method for...
Most cerebrovascular diseases (including strokes and aneurysms) are treated endovascularly with catheters that navigated from the groin through vessels to brain. Many patients have complex anatomy of aortic arch supra-aortic vessels, which can make it difficult select best for navigation, resulting in longer procedures more complications or failures. To this end, we propose a framework dedicated analysis trunks. This automatically compute anatomical geometrical features meshes segmented...
We present an original algorithm to assess the deformations of left ventricle on standard cardiac cine-MRI rather than tagged-MRI. Our results are validated by comparison with derived from tagged image sequences that analysed harmonic phase MRI (HARP MRI) method. First, a segmentation process, based level set method is applied 2D+t dataset MR images detect endocardial contours. Second, successive segmented contours matched using rigid registration. then apply morphing process implemented...
Purpose: Compare various methods of transit time (TT) and consequently aortic Pulse Wave Velocity (aoPWV) estimation from 4D MRI (aoPWV=aortic length/TT), in terms associations with age Bramwell-Hill (BH aoPWV).Method: We studied 43 healthy subjects (48±17yrs.)who had 4DFlow MRI.Three strategies were used to estimate aoPWV: (S1) using flow curves two locations calculate TT (ascending (AA) distal descending aorta (dDA)) as a 2D-like strategy, (S2 S3) the entire path-line between dDA AA...