Blood vessel segmentation in color fundus images based on regional and Hessian features

Purpose: To propose a new algorithm of blood vessel segmentation based on regional and Hessian features for image analysis in retinal abnormality diagnosis. Methods: Firstly, color fundus images from the publicly available database DRIVE were converted from RGB to grayscale. To enhance the contrast...

Full description

Main Authors: Shah, S.A.A., Tang, T.B., Faye, I., Laude, A.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.19419 /
Published: Springer Verlag 2017
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85018747145&doi=10.1007%2fs00417-017-3677-y&partnerID=40&md5=3eb38d771822d5839d43f81c42897735
http://eprints.utp.edu.my/19419/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.19419
recordtype eprints
spelling utp-eprints.194192018-04-20T00:45:36Z Blood vessel segmentation in color fundus images based on regional and Hessian features Shah, S.A.A. Tang, T.B. Faye, I. Laude, A. Purpose: To propose a new algorithm of blood vessel segmentation based on regional and Hessian features for image analysis in retinal abnormality diagnosis. Methods: Firstly, color fundus images from the publicly available database DRIVE were converted from RGB to grayscale. To enhance the contrast of the dark objects (blood vessels) against the background, the dot product of the grayscale image with itself was generated. To rectify the variation in contrast, we used a 5 × 5 window filter on each pixel. Based on 5 regional features, 1 intensity feature and 2 Hessian features per scale using 9 scales, we extracted a total of 24 features. A linear minimum squared error (LMSE) classifier was trained to classify each pixel into a vessel or non-vessel pixel. Results: The DRIVE dataset provided 20 training and 20 test color fundus images. The proposed algorithm achieves a sensitivity of 72.05 with 94.79 accuracy. Conclusions: Our proposed algorithm achieved higher accuracy (0.9206) at the peripapillary region, where the ocular manifestations in the microvasculature due to glaucoma, central retinal vein occlusion, etc. are most obvious. This supports the proposed algorithm as a strong candidate for automated vessel segmentation. © 2017, Springer-Verlag Berlin Heidelberg. Springer Verlag 2017 Article PeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85018747145&doi=10.1007%2fs00417-017-3677-y&partnerID=40&md5=3eb38d771822d5839d43f81c42897735 Shah, S.A.A. and Tang, T.B. and Faye, I. and Laude, A. (2017) Blood vessel segmentation in color fundus images based on regional and Hessian features. Graefe's Archive for Clinical and Experimental Ophthalmology, 255 (8). pp. 1525-1533. http://eprints.utp.edu.my/19419/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description Purpose: To propose a new algorithm of blood vessel segmentation based on regional and Hessian features for image analysis in retinal abnormality diagnosis. Methods: Firstly, color fundus images from the publicly available database DRIVE were converted from RGB to grayscale. To enhance the contrast of the dark objects (blood vessels) against the background, the dot product of the grayscale image with itself was generated. To rectify the variation in contrast, we used a 5 × 5 window filter on each pixel. Based on 5 regional features, 1 intensity feature and 2 Hessian features per scale using 9 scales, we extracted a total of 24 features. A linear minimum squared error (LMSE) classifier was trained to classify each pixel into a vessel or non-vessel pixel. Results: The DRIVE dataset provided 20 training and 20 test color fundus images. The proposed algorithm achieves a sensitivity of 72.05 with 94.79 accuracy. Conclusions: Our proposed algorithm achieved higher accuracy (0.9206) at the peripapillary region, where the ocular manifestations in the microvasculature due to glaucoma, central retinal vein occlusion, etc. are most obvious. This supports the proposed algorithm as a strong candidate for automated vessel segmentation. © 2017, Springer-Verlag Berlin Heidelberg.
format Article
author Shah, S.A.A.
Tang, T.B.
Faye, I.
Laude, A.
spellingShingle Shah, S.A.A.
Tang, T.B.
Faye, I.
Laude, A.
Blood vessel segmentation in color fundus images based on regional and Hessian features
author_sort Shah, S.A.A.
title Blood vessel segmentation in color fundus images based on regional and Hessian features
title_short Blood vessel segmentation in color fundus images based on regional and Hessian features
title_full Blood vessel segmentation in color fundus images based on regional and Hessian features
title_fullStr Blood vessel segmentation in color fundus images based on regional and Hessian features
title_full_unstemmed Blood vessel segmentation in color fundus images based on regional and Hessian features
title_sort blood vessel segmentation in color fundus images based on regional and hessian features
publisher Springer Verlag
publishDate 2017
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85018747145&doi=10.1007%2fs00417-017-3677-y&partnerID=40&md5=3eb38d771822d5839d43f81c42897735
http://eprints.utp.edu.my/19419/
_version_ 1741196203762122752
score 11.62408

Similar Items