A knowledge-guided tri-branch network with dynamic lesion localization reaches 98.5% AUC and 94.6% accuracy on large fundus datasets for glaucoma screening and generalizes across benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fundus Image-based Glaucoma Screening via Retinal Knowledge-Oriented Dynamic Multi-Level Feature Integration
A knowledge-guided tri-branch network with dynamic lesion localization reaches 98.5% AUC and 94.6% accuracy on large fundus datasets for glaucoma screening and generalizes across benchmarks.