activity
20242026
collaborators

6 papers

cs.CV2026

Fully Automated High-Precision Segmentation of Retinal Atrophy and Ellipsoid Zone Thickness in OCT: A Reliable Tool for Real-World GA Monitoring

Wolf-Dieter Vogl, Hlynur Skulason, Oliver Leingang +3

Geographic atrophy (GA) secondary to age-related macular degeneration (AMD) requires precise monitoring of relevant structural biomarkers to assess disease stage, progression, and…

cs.CV2025

MIRAGE: Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis

José Morano, Botond Fazekas, Emese Sükei +7

Artificial intelligence (AI) has become a fundamental tool for assisting clinicians in analyzing ophthalmic images, such as optical coherence tomography (OCT). However, developing…

cs.CV2025

SD-RetinaNet: Topologically Constrained Semi-Supervised Retinal Lesion and Layer Segmentation in OCT

Botond Fazekas, Guilherme Aresta, Philipp Seeböck +3

Optical coherence tomography (OCT) is widely used for diagnosing and monitoring retinal diseases, such as age-related macular degeneration (AMD). The segmentation of biomarkers suc…

cs.CV2025

RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models

Ronald Fecso, José Morano, Ursula Schmidt-Erfurth +1

The rise of imaging techniques such as optical coherence tomography (OCT) and advances in deep learning (DL) have enabled clinicians and researchers to streamline retinal disease s…

cs.AI2025

Specialized curricula for training vision-language models in retinal image analysis

Robbie Holland, Thomas R. P. Taylor, Christopher Holmes +13

Clinicians spend a significant amount of time reviewing medical images and transcribing their findings regarding patient diagnosis, referral and treatment in text form. Vision-lang…

cs.CV2024

Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations

Taha Emre, Arunava Chakravarty, Dmitrii Lachinov +3

Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse. E…