Model-based method for improving the accuracy and repeatability of estimating vascular bifurcations and crossovers from retinal fundus images.

A model-based algorithm, termed exclusion region and position refinement (ERPR), is presented for improving the accuracy and repeatability of estimating the locations where vascular structures branch and cross over, in the context of human retinal images. The goal is two fold. First, accurate morpho...

Volledige beschrijving

Bibliografische gegevens
Gepubliceerd in:	IEEE Transactions on information technology in biomedicine 8, 2 (2004).
Hoofdauteur:	Chia-Ling Tsai
Formaat:	Artikel
Taal:	English
Onderwerpen:	Accurate morphometry. Biomedical image analysis. Crossovers. Exclusion region and position refinement algorithm. Feature extraction. Feature refinement. Feature stability. Human retinal images. Image registration. Landmarks. Location repeatability. Median location error. Model-based algorithm. Mosaic synthesis. Neuronal structure. Vascular bifurcation. Vessel orientation.