HRF Dataset
A commonly used public dataset in the retinal vessel segmentation field, containing high-resolution fundus images and expert-annotated vessel masks across categories including healthy, diabetic retinopathy, and glaucoma cases; it typically comprises several tens of images and is suited to methodological validation.
Timeline (last 90 days)
On an exploratory cohort of 30 HRF images, the pipeline reported 96.7% accuracy, an F1 score of 0.968, and a ROC-AUC of 0.978.
The HRF dataset is a commonly used public dataset in the retinal vessel segmentation field, containing high-resolution fundus images and expert-annotated vessel masks, with images covering categories such as healthy, diabetic retinopathy, and glaucoma, typically numbering in the tens of images.
The disease labels used in the study are proxy labels, not clinical gold-standard grading, and independent reference caliber measurements are lacking, so the 96.7% accuracy only demonstrates that the pipeline is feasible in exploratory settings, not clinically usable screening performance.
All Facts (3)
On an exploratory cohort of 30 HRF images, the pipeline reported 96.7% accuracy, an F1 score of 0.968, and a ROC-AUC of 0.978.
50%UnverifiedThe HRF dataset is a commonly used public dataset in the retinal vessel segmentation field, containing high-resolution fundus images and expert-annotated vessel masks, with images covering categories such as healthy, diabetic retinopathy, and glaucoma, typically numbering in the tens of images.
50%UnverifiedThe disease labels used in the study are proxy labels, not clinical gold-standard grading, and independent reference caliber measurements are lacking, so the 96.7% accuracy only demonstrates that the pipeline is feasible in exploratory settings, not clinically usable screening performance.
50%