Making every microaneurysm count: A hybrid approach to monitor progression of diabetic retinopathy

Previous studies have shown that the progression of diabetic retinopathy (DR) can be monitored by counting the number of microaneurysms (MAs). In this work, we propose an approach to maximize the sensitivity of MA detection by using a combination of two different techniques, namely local thresholdin...

Full description

Main Authors: Ali, S.S.A., Tang, T.B., Laude, A., Faye, I.
Format: Conference or Workshop Item
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.32130 /
Published: IEEE Computer Society 2014
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84906342273&doi=10.1109%2fICIAS.2014.6869472&partnerID=40&md5=a910f7a6732c6c9df0544cab4ac5a100
http://eprints.utp.edu.my/32130/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.32130
recordtype eprints
spelling utp-eprints.321302022-03-29T04:59:34Z Making every microaneurysm count: A hybrid approach to monitor progression of diabetic retinopathy Ali, S.S.A. Tang, T.B. Laude, A. Faye, I. Previous studies have shown that the progression of diabetic retinopathy (DR) can be monitored by counting the number of microaneurysms (MAs). In this work, we propose an approach to maximize the sensitivity of MA detection by using a combination of two different techniques, namely local thresholding and Canny edge detection. The proposed approach was evaluated with publically available dataset DIARETDB1 where ten fundus images containing a total of 315 MAs were randomly selected. Out of these, the proposed approach was able to detect 295 MAs, achieving a sensitivity of 93.65. Limiting factors were identified to be noise filtering, presence of artifacts and dark-shaded retinal vessels. © 2014 IEEE. IEEE Computer Society 2014 Conference or Workshop Item NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-84906342273&doi=10.1109%2fICIAS.2014.6869472&partnerID=40&md5=a910f7a6732c6c9df0544cab4ac5a100 Ali, S.S.A. and Tang, T.B. and Laude, A. and Faye, I. (2014) Making every microaneurysm count: A hybrid approach to monitor progression of diabetic retinopathy. In: UNSPECIFIED. http://eprints.utp.edu.my/32130/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description Previous studies have shown that the progression of diabetic retinopathy (DR) can be monitored by counting the number of microaneurysms (MAs). In this work, we propose an approach to maximize the sensitivity of MA detection by using a combination of two different techniques, namely local thresholding and Canny edge detection. The proposed approach was evaluated with publically available dataset DIARETDB1 where ten fundus images containing a total of 315 MAs were randomly selected. Out of these, the proposed approach was able to detect 295 MAs, achieving a sensitivity of 93.65. Limiting factors were identified to be noise filtering, presence of artifacts and dark-shaded retinal vessels. © 2014 IEEE.
format Conference or Workshop Item
author Ali, S.S.A.
Tang, T.B.
Laude, A.
Faye, I.
spellingShingle Ali, S.S.A.
Tang, T.B.
Laude, A.
Faye, I.
Making every microaneurysm count: A hybrid approach to monitor progression of diabetic retinopathy
author_sort Ali, S.S.A.
title Making every microaneurysm count: A hybrid approach to monitor progression of diabetic retinopathy
title_short Making every microaneurysm count: A hybrid approach to monitor progression of diabetic retinopathy
title_full Making every microaneurysm count: A hybrid approach to monitor progression of diabetic retinopathy
title_fullStr Making every microaneurysm count: A hybrid approach to monitor progression of diabetic retinopathy
title_full_unstemmed Making every microaneurysm count: A hybrid approach to monitor progression of diabetic retinopathy
title_sort making every microaneurysm count: a hybrid approach to monitor progression of diabetic retinopathy
publisher IEEE Computer Society
publishDate 2014
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-84906342273&doi=10.1109%2fICIAS.2014.6869472&partnerID=40&md5=a910f7a6732c6c9df0544cab4ac5a100
http://eprints.utp.edu.my/32130/
_version_ 1741197690673299456
score 11.62408

Similar Items