Gwenolé Quellec

Performance of AI-based diabetic retinopathy screening is highly dependent on evaluation setting: a five-year, multi-framework study

Gwenolé Quellec, Mathieu Lamard, Sarah Matta, Laurent Borderie et autres

Abstract Despite near-perfect performance reported on benchmark datasets, the real-world behavior of artificial intelligence (AI) systems for diabetic retinopathy (DR) screening remains insufficiently characterized. Here, we report a multi-framework evaluation of OphtAI, a CE-marked AI system for automated detection of referable DR …

fr, fi (code pays fourni par la source)

Turning Distillation against Obfuscation: A Recovery Framework for DNN White-Box Watermarks

Mahdieh Pouresmaeil, Reda Bellafqira, Kassem Kallas, Gwenolé Quellec et autres

White-box watermarking embeds ownership signatures directly into DNN parameters, yet it faces a critical blind spot: topology-altering obfuscation. By modifying a model’s internal structure while preserving its input-output behavior, an attacker can misalign the watermark from its expected parameter locations, causing standard …

fr (code pays fourni par la source)

Constrained latent state modeling: A unifying perspective on representation learning under competing constraints

Gwenolé Quellec

Learning latent representations from complex data is central to modern machine learning, spanning temporal, multimodal, and partially observed systems. In such settings, representations are more naturally understood as latent states capturing underlying system dynamics rather than compressed summaries of observations. Yet current …

Constrained latent state modeling: A unifying perspective on representation learning under competing constraints

Gwenolé Quellec

Learning latent representations from complex data is central to modern machine learning, spanning temporal, multimodal, and partially observed systems. In such settings, representations are more naturally understood as latent states capturing underlying system dynamics rather than compressed summaries of observations. Yet current …

Performance of AI-based diabetic retinopathy screening is highly dependent on evaluation setting: A five-year, multi-framework study

Gwenolé Quellec, Mathieu Lamard, Sarah Matta, Laurent Borderie et autres

fr, fi, gb, us (code pays fourni par la source)

When ten cases are not enough: Uncertainty and power in AI screening evaluations

Gwenolé Quellec

fr (code pays fourni par la source)

Acoustic and machine learning methods for speech-based suicide risk assessment: A systematic review

A. Mariè, Marion Garnier, Thomas Bertin, Laura Machart et autres

Suicide remains a public health challenge, necessitating improved detection methods to facilitate timely intervention and treatment. This systematic review evaluates the role of Artificial Intelligence (AI) and Machine Learning (ML) in assessing suicide risk through acoustic analysis of speech. Following PRISMA guidelines, …

fr (code pays fourni par la source)

A robust deep learning classifier for screening multiple retinal diseases on optical coherence tomography

Philippe Zhang, Gwenolé Quellec, Sarah Christina Matta, Laurent Borderie et autres

Retinal diseases are among the leading causes of visual impairment worldwide, where timely diagnosis and management are critical to prevent irreversible vision loss and blindness, especially in regions with limited access to ophthalmologists. While artificial intelligence (AI) has shown remarkable potential for …

fr (code pays fourni par la source)

Automated multimodal severity assessment of diabetic retinopathy using ultra-widefield color fundus photography and clinical tabular data

Alireza Rezaei, Sarah Christina Matta, Rachid Zeghlache, Pierre-Henri Conze et autres

This study introduces an automatic deep-learning-based approach to diabetic retinopathy (DR) severity assessment by integrating two modalities: Ultra-Widefield Color Fundus Photography (UWF-CFP) from the CLARUS 500 device (Carl Zeiss Meditec Inc., Dublin, CA, USA) and a comprehensive set of clinical data from …

fr, us (code pays fourni par la source)

Deep learning for retinal non-perfusion and foveal avascular zone analysis in wide-field OCTA in diabetic retinopathy

Hugo Le Boité, Sophie Bonnin, Mathias Gallardo, Mathieu Lamard et autres

We developed an automated framework for segmenting low-quality and non-perfusion areas in widefield OCTA images to obtain two key metrics useful for diabetic retinopathy (DR) monitoring: the retinal non-perfusion index (NPI) and foveal avascular zone (FAZ) area. Using 170 images from 88 …

fr (code pays fourni par la source)

JustRAIGS: Justified Referral in AI Glaucoma Screening Challenge

Yeganeh Madadi, Hina Raja, Koenraad Arndt Vermeer, Hans G. Lemij et autres

A major contributor to permanent vision loss is glaucoma. Early diagnosis is crucial for preventing vision loss due to glaucoma, making glaucoma screening essential. A more affordable method of glaucoma screening can be achieved by applying artificial intelligence to evaluate color fundus …

us, nl, kr, es, il, br, de, cn, fr, in (code pays fourni par la source)

SarAdapter: Prioritizing Attention on Semantic-Aware Representative Tokens for Enhanced Medical Image Segmentation

Weili Jiang, Yihao Li, Lin An, Gwenolé Quellec et autres

Transformer-based segmentation methods exhibit considerable potential in medical image analysis. However, their improved performance often comes with increased computational complexity, limiting their application in resource-constrained medical settings. Prior methods follow two independent tracks: (i) accelerating existing networks via semantic-aware routing, and (ii) …

cn, am (code pays fourni par la source)