Search Results for author:
Found 5 papers, 3 papers with code
Uncertainty-aware retinal layer segmentation in OCT through probabilistic signed distance functions
To address these shortcomings, our methodology refines the segmentation by predicting a signed distance function (SDF) that effectively parameterizes the retinal layer shape via level set.
VascX Models: Model Ensembles for Retinal Vascular Analysis from Color Fundus Images
Additional CFIs, mainly from the population-based Rotterdam Study were annotated by graders for arteries and veins at pixel level, resulting in a dataset diverse in patient demographics and imaging conditions.
Ranked #3 on
Retinal Vessel Segmentation
on UZLF
Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors
Firstly, we study the effect of weight initialization (ImageNet vs. random) on the transferability of adversarial attacks from the surrogate model to the target model.
Iterative Augmentation of Visual Evidence for Weakly-Supervised Lesion Localization in Deep Interpretability Frameworks: Application to Color Fundus Images
We show that the augmented visual evidence of the predictions highlights the biomarkers considered by experts for diagnosis and improves the final localization performance.
A deep learning model for segmentation of geographic atrophy to study its long-term natural history
Participants: 409 CFIs of 238 eyes with GA from the Rotterdam Study (RS) and the Blue Mountain Eye Study (BMES) for model development, and 5, 379 CFIs of 625 eyes from the Age-Related Eye Disease Study (AREDS) for analysis of GA growth rate.
