A probabilistic model for the optimal configuration of retinal junctions using theoretically proven features

Qureshi, Touseef Ahmad and Hunter, Andrew and Al-Diri, Bashir (2014) A probabilistic model for the optimal configuration of retinal junctions using theoretically proven features. Proceedings - International Conference on Pattern Recognition (ICPR) . pp. 3304-3309. ISSN 1051-4651

Documents
A probabilistic model for the optimal configuration of retinal junctions using theoretically proven features

Request a copy
[img] PDF
__ddat02_staffhome_jpartridge_06977281.pdf - Whole Document
Restricted to Repository staff only

402kB
Item Type:Article
Item Status:Live Archive

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.

Additional Information:22nd International Conference on Pattern Recognition, ICPR 2014 ; Conference Date: 24 - 28 August 2014, Stockholm, Sweden Conference Code:109641
Keywords:Bayesian networks, Blood vessels, Diagnosis, Eye protection, Pattern recognition, Diabetic retinopathy, Maximum a posteriori, Naive Bayes models, Optimality principle, Overall accuracies, Probabilistic modeling, Systemic disease, Vessel segments, Ophthalmology, NotOAChecked
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
C Biological Sciences > C190 Biology not elsewhere classified
Divisions:College of Science > School of Computer Science
Related URLs:
Relationships:
Relation typeTarget identifier
http://purl.org/dc/terms/Referenceshttp://eprints.lincoln.ac.uk/23687/
ID Code:16529
Deposited On:23 Jan 2015 12:13

Repository Staff Only: item control page