Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data

Thomas P. Karnowski, V. Priya Govindasamy, Kenneth W. Tobin, Edward Chaum, M. D. Abramoff

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

In this work we report on a method for lesion segmentation based on the morphological reconstruction methods of Sbeh et. al. We adapt the method to include segmentation of dark lesions with a given vasculature segmentation. The segmentation is performed at a variety of scales determined using ground-truth data. Since the method tends to over-segment imagery, ground-truth data was used to create post-processing filters to separate nuisance blobs from true lesions. A sensitivity and specificity of 90% of classification of blobs into nuisance and actual lesion was achieved on two data sets of 86 images and 1296 images.

Original languageEnglish (US)
Title of host publicationProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
Pages5433-5436
Number of pages4
StatePublished - Dec 1 2008
Event30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - Vancouver, BC, Canada
Duration: Aug 20 2008Aug 25 2008

Other

Other30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
CountryCanada
CityVancouver, BC
Period8/20/088/25/08

Fingerprint

Retina
Processing
Imagery (Psychotherapy)
Sensitivity and Specificity
Microaneurysm

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Karnowski, T. P., Govindasamy, V. P., Tobin, K. W., Chaum, E., & Abramoff, M. D. (2008). Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 (pp. 5433-5436). [4650443]

Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data. / Karnowski, Thomas P.; Govindasamy, V. Priya; Tobin, Kenneth W.; Chaum, Edward; Abramoff, M. D.

Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. p. 5433-5436 4650443.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Karnowski, TP, Govindasamy, VP, Tobin, KW, Chaum, E & Abramoff, MD 2008, Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data. in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08., 4650443, pp. 5433-5436, 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08, Vancouver, BC, Canada, 8/20/08.
Karnowski TP, Govindasamy VP, Tobin KW, Chaum E, Abramoff MD. Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. p. 5433-5436. 4650443
Karnowski, Thomas P. ; Govindasamy, V. Priya ; Tobin, Kenneth W. ; Chaum, Edward ; Abramoff, M. D. / Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. pp. 5433-5436
@inproceedings{7f77138ec0b04996a80c578500b988ff,
title = "Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data",
abstract = "In this work we report on a method for lesion segmentation based on the morphological reconstruction methods of Sbeh et. al. We adapt the method to include segmentation of dark lesions with a given vasculature segmentation. The segmentation is performed at a variety of scales determined using ground-truth data. Since the method tends to over-segment imagery, ground-truth data was used to create post-processing filters to separate nuisance blobs from true lesions. A sensitivity and specificity of 90{\%} of classification of blobs into nuisance and actual lesion was achieved on two data sets of 86 images and 1296 images.",
author = "Karnowski, {Thomas P.} and Govindasamy, {V. Priya} and Tobin, {Kenneth W.} and Edward Chaum and Abramoff, {M. D.}",
year = "2008",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781424418152",
pages = "5433--5436",
booktitle = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08",

}

TY - GEN

T1 - Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data

AU - Karnowski, Thomas P.

AU - Govindasamy, V. Priya

AU - Tobin, Kenneth W.

AU - Chaum, Edward

AU - Abramoff, M. D.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - In this work we report on a method for lesion segmentation based on the morphological reconstruction methods of Sbeh et. al. We adapt the method to include segmentation of dark lesions with a given vasculature segmentation. The segmentation is performed at a variety of scales determined using ground-truth data. Since the method tends to over-segment imagery, ground-truth data was used to create post-processing filters to separate nuisance blobs from true lesions. A sensitivity and specificity of 90% of classification of blobs into nuisance and actual lesion was achieved on two data sets of 86 images and 1296 images.

AB - In this work we report on a method for lesion segmentation based on the morphological reconstruction methods of Sbeh et. al. We adapt the method to include segmentation of dark lesions with a given vasculature segmentation. The segmentation is performed at a variety of scales determined using ground-truth data. Since the method tends to over-segment imagery, ground-truth data was used to create post-processing filters to separate nuisance blobs from true lesions. A sensitivity and specificity of 90% of classification of blobs into nuisance and actual lesion was achieved on two data sets of 86 images and 1296 images.

UR - http://www.scopus.com/inward/record.url?scp=61849119022&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61849119022&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781424418152

SP - 5433

EP - 5436

BT - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08

ER -