Paper Info
Title
A Probabilistic Model for the Optimal Configuration of Retinal Junctions Using Theoretically Proven Features
Abstract
This paper aims to reconstruct retinal vessel trees from the broken vessel segments in fund us images for clinical studies and early diagnosis of systemic diseases including diabetic retinopathy, atherosclerosis, and hypertension. A Naive Bayes model is proposed for correct configurations of segments at retinal junctions including bifurcations, crossovers, overlaps, and mixture of these. The Maximum A Posteriori (MAP) is established to select the most likely configuration. In addition, the feature set consists of proportional associations of vessels width, angle and orientation. These theoretically proven associations are based on the optimality principles of minimum work in the vasculature for blood flow efficiency. We modelled the system using the training set of DRIVE database, tested on the testing set of same database, and produced 93.3% overall accuracy.
Year
DOI
Venue
2014
10.1109/ICPR.2014.569
Pattern Recognition
Keywords
Field
DocType
Bayes methods,blood vessels,diseases,eye,maximum likelihood estimation,medical image processing,DRIVE database,MAP,atherosclerosis,bifurcation,blood flow efficiency,broken vessel segment,crossover,diabetic retinopathy,hypertension,maximum a posteriori,naive Bayes model,optimal configuration,probabilistic model,retinal junction,retinal vessel trees,systemic diseases,theoretically proven feature,vasculature,vessel angle,vessel orientation,vessels width
Training set,Computer vision,Naive Bayes classifier,Pattern recognition,Computer science,Feature extraction,Image segmentation,Statistical model,Artificial intelligence,Maximum a posteriori estimation,Retinal,Bifurcation
Conference
ISSN
Citations 
PageRank 
1051-4651
0
0.34
References 
Authors
8
3
Name
Order
Citations
PageRank
Touseef Ahmad Qureshi1101.60
Andrew Hunter2254.40
Bashir Al-diri3417.50