A5079375904- Retinal Imaging and Analysis
- Retinal Diseases and Treatments
- Industrial Vision Systems and Defect Detection
- Medical Image Segmentation Techniques
- Optical measurement and interference techniques
- Advanced Neural Network Applications
- Digital Imaging for Blood Diseases
- AI in cancer detection
- Image Processing Techniques and Applications
- Glaucoma and retinal disorders
- 3D Surveying and Cultural Heritage
- Optical Polarization and Ellipsometry
- Retinal and Optic Conditions
- Medical Imaging and Analysis
- Remote Sensing and LiDAR Applications
- Robotics and Sensor-Based Localization
- Cardiac Imaging and Diagnostics
- Prostate Cancer Diagnosis and Treatment
- Optical Coherence Tomography Applications
- Surface Roughness and Optical Measurements
- Advanced MRI Techniques and Applications
- Advanced Image Fusion Techniques
- Radiomics and Machine Learning in Medical Imaging
- Additive Manufacturing Materials and Processes
- Infrared Target Detection Methodologies
Université de Bourgogne
2016-2025
Centre National de la Recherche Scientifique
2012-2024
Université Bourgogne Franche-Comté
2015-2024
Institut de Chimie
2023-2024
ImViA - Imagerie et Vision Artificielle
2019-2024
Institut de Chimie Moléculaire de l'Université de Bourgogne
2023-2024
Laboratoire Interdisciplinaire Carnot de Bourgogne
2023
Vision pour la Robotique
2020-2021
Universiti Teknologi Petronas
2014-2020
ORCID
2020
Diabetic Retinopathy is the most prevalent cause of avoidable vision impairment, mainly affecting working-age population in world. Recent research has given a better understanding requirement clinical eye care practice to identify and cheaper ways identification, management, diagnosis treatment retinal disease. The importance diabetic retinopathy screening programs difficulty achieving reliable early at reasonable cost needs attention develop computer-aided tool. Computer-aided disease image...
The world faces difficulties in terms of eye care, including treatment, quality prevention, vision rehabilitation services, and scarcity trained care experts. Early detection diagnosis ocular pathologies would enable forestall visual impairment. One challenge that limits the adoption computer-aided tool by ophthalmologists is number sight-threatening rare pathologies, such as central retinal artery occlusion or anterior ischemic optic neuropathy, others are usually ignored. In past two...
RGB-D saliency detection aims to fuse multi-modal cues accurately localize salient regions. Existing works often adopt attention modules for feature modeling, with few methods explicitly leveraging fine-grained details merge semantic cues. Thus, despite the auxiliary depth information, it is still challenging existing models distinguish objects similar appearances but at distinct camera distances. In this paper, from a new perspective, we propose novel Hierarchical Depth Awareness network...
This paper concerns the validation of automatic retinal image analysis (ARIA) algorithms. For reasons space and consistency, we concentrate on algorithms processing color fundus camera images, currently largest section ARIA literature. We sketch context (imaging instruments target tasks) validation, summarizing main techniques. then present a list recommendations focusing creation large repositories test data created by international consortia, easily accessible via moderated Web sites,...
This paper addresses the problem of automatic classification Spectral Domain OCT (SD-OCT) data for identification patients with DME versus normal subjects. Optical Coherence Tomography (OCT) has been a valuable diagnostic tool DME, which is among most common causes irreversible vision loss in individuals diabetes. Here, framework five distinctive steps proposed and we present an extensive study each step. Our method considers combination various preprocessing conjunction Local Binary...
Spectral domain optical coherence tomography (OCT) (SD-OCT) is most widely imaging equipment used in ophthalmology to detect diabetic macular edema (DME). Indeed, it offers an accurate visualization of the morphology retina as well layers. The dataset this study has been acquired by Singapore Eye Research Institute (SERI), using CIRRUS TM (Carl Zeiss Meditec, Inc., Dublin, CA, USA) SD-OCT device. consists 32 OCT volumes (16 DME and 16 normal cases). Each volume contains 128 B-scans with...
Tuberculosis (TB) is a major health threat in the developing countries. Many patients die every year due to lack of treatment and error diagnosis. Developing computer-aided diagnosis (CAD) system for TB detection can help early containing disease. Most current CAD systems use handcrafted features, however, lately there shift towards deep-learning-based automatic feature extractors. In this paper, we present potential method tuberculosis using deep-learning which classifies CXR images into...
Liver cancer is the sixth most common in world and fourth leading cause of mortality. In unresectable liver cancers, especially hepatocellular carcinoma (HCC), transarterial radioembolisation (TARE) can be considered for treatment. TARE treatment involves a contrast-enhanced magnetic resonance imaging (CE-MRI) exam performed beforehand to delineate tumour(s) order perform dosimetry calculation. Due significant amount time expertise required delineation process, there strong need automation....
Diabetic Macular Edema (DME) is one of the many eye diseases that commonly found in diabetic patients. If it left untreated may cause vision loss. This paper focuses on classification abnormal and normal OCT (Optical Coherence Tomography) image volumes using a pre-trained CNN (Convolutional Neural Network). Using VGG16 (Visual Geometry Group), features are extracted at different layers network, e.g. before fully connected layer after each layer. On basis these was performed classifiers...
The creation of an automatic diabetic retinopathy screening system using retina cameras is currently receiving considerable interest in the medical imaging community. detection microaneurysms a key element this effort. In work, we propose new segmentation technique based on novel application radon transform, which able to identify these lesions without any previous knowledge morphological features and with minimal image preprocessing. algorithm has been evaluated Retinopathy Online Challenge...
A ternary composite comprising of p-toluene sulfonic acid doped polyaniline (PANI), chitosan and reduced graphene oxide (RGO) with stable aqueous dispersibility has been synthesised via oxidative polymerisation aniline in chitosan/RGO dispersion. For comparison; PANI, PANI/chitosan PANI/RGO composites were also using the same procedure. FTIR, Raman, XPS, XRD UV-VIS confirmed successful synthesis PANI composites. The dispersions found to be even after more than four months. stability...
Diabetic macular edema (DME) is one of the most common eye complication caused by diabetes mellitus, resulting in partial or total loss vision. Optical Coherence Tomography (OCT) volumes have been widely used to diagnose different diseases, thanks their sensitivity represent small amounts fluid, thickness between layers and swelling. However, lack tools for automatic image analysis supporting disease diagnosis still a problem. Convolutional neural networks (CNNs) shown outstanding...
One crucial parameter to evaluate the state of heart after myocardial infarction (MI) is viability segment, i.e., if segment recovers its functionality upon revascularization. MRI performed several minutes injection a contrast agent (delayed enhancement-MRI or DE-MRI) method choice extent MI, and by extension, assess viable tissues an injury. The Emidec dataset composed series exams with DE-MR images in short axis orientation covering left ventricle from normal cases patients infarction,...
In this paper, we present an evaluation of four encoder–decoder CNNs in the segmentation prostate gland T2W magnetic resonance imaging (MRI) image. The selected are FCN, SegNet, U-Net, and DeepLabV3+, which was originally proposed for road scene, biomedical, natural images. Segmentation MRI images is important step automatic diagnosis cancer to enable better lesion detection staging cancer. Therefore, many research efforts have been conducted improve main challenges blurry boundary...