Automated segmentation of retinal blood vessels and identification of proliferative diabetic retinopathy
- 11 April 2007
- journal article
- research article
- Published by Optica Publishing Group in Journal of the Optical Society of America A
- Vol. 24 (5) , 1448-1456
Abstract
Proliferative diabetic retinopathy can lead to blindness. However, early recognition allows appropriate, timely intervention. Fluorescein-labeled retinal blood vessels of 27 digital images were automatically segmented using the Gabor wavelet transform and classified using traditional features such as area, perimeter, and an additional five morphological features based on the derivatives-of-Gaussian wavelet-derived data. Discriminant analysis indicated that traditional features do not detect early proliferative retinopathy. The best single feature for discrimination was the wavelet curvature with an area under the curve (AUC) of 0.76. Linear discriminant analysis with a selection of six features achieved an AUC of 0.90 (0.73–0.97, 95% confidence interval). The wavelet method was able to segment retinal blood vessels and classify the images according to the presence or absence of proliferative retinopathy.Keywords
This publication has 24 references indexed in Scilit:
- Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classificationIEEE Transactions on Medical Imaging, 2006
- The impact of diabetic retinopathy: perspectives from patient focus groupsFamily Practice, 2004
- A review of vessel extraction techniques and algorithmsACM Computing Surveys, 2004
- Ridge-Based Vessel Segmentation in Color Images of the RetinaIEEE Transactions on Medical Imaging, 2004
- Adaptive local thresholding by verification-based multithreshold probing with application to vessel detection in retinal imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- A national screening programme for diabetic retinopathyBMJ, 2001
- Segmentation of vessel-like patterns using mathematical morphology and curvature evaluationIEEE Transactions on Image Processing, 2001
- World blindness: a 21st century perspectiveBritish Journal of Ophthalmology, 2001
- Quantification and characterisation of arteries in retinal imagesComputer Methods and Programs in Biomedicine, 2000
- Locating blood vessels in retinal images by piecewise threshold probing of a matched filter responseIEEE Transactions on Medical Imaging, 2000