Title | ||
---|---|---|
Detection of hypertensive retinopathy using vessel measurements and textural features. |
Abstract | ||
---|---|---|
Features that indicate hypertensive retinopathy have been well described in the medical literature. This paper presents a new system to automatically classify subjects with hypertensive retinopathy (HR) using digital color fundus images. Our method consists of the following steps: 1) normalization and enhancement of the image; 2) determination of regions of interest based on automatic location of the optic disc; 3) segmentation of the retinal vasculature and measurement of vessel width and tortuosity; 4) extraction of color features; 5) classification of vessel segments as arteries or veins; 6) calculation of artery-vein ratios using the six widest (major) vessels for each category; 7) calculation of mean red intensity and saturation values for all arteries; 8) calculation of amplitude-modulation frequency-modulation (AM-FM) features for entire image; and 9) classification of features into HR and non-HR using linear regression. This approach was tested on 74 digital color fundus photographs taken with TOPCON and CANON retinal cameras using leave-one out cross validation. An area under the ROC curve (AUC) of 0.84 was achieved with sensitivity and specificity of 90% and 67%, respectively. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/EMBC.2014.6944848 | EMBC |
Keywords | Field | DocType |
eye,linear regression,topcon retinal cameras,diseases,leave-one out cross-validation,image normalization,textural features,biomedical optical imaging,tortuosity,frequency modulation,mean red intensity,digital color fundus photographs,roc curve,regression analysis,regions-of-interest,automatic location,blood vessels,image segmentation,optic disc,retinal vasculature segmentation,vessel segment classification,vessel width,vessel measurement,image sensors,artery-vein ratios,feature extraction,image classification,color feature extraction,amplitude modulation,canon retinal cameras,medical literature,digital color fundus images,vessel measurements,automatically classify subjects,image texture,image enhancement,amplitude-modulation frequency-modulation features,medical image processing,sensitivity analysis,image colour analysis,hypertensive retinopathy detection | Computer vision,Retina,Tortuosity,Computer science,Hypertensive retinopathy,Fundus (eye),Stroke,Optic disc,Artificial intelligence,Blood pressure,Retinal | Conference |
Volume | ISSN | Citations |
2014 | 1557-170X | 0 |
PageRank | References | Authors |
0.34 | 6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Carla Agurto | 1 | 0 | 2.70 |
Vinayak Joshi | 2 | 0 | 0.34 |
Sheila Nemeth | 3 | 0 | 0.34 |
Peter Soliz | 4 | 0 | 0.34 |
Simon Barriga | 5 | 0 | 0.34 |