Automated detection of neovascularization for proliferative diabetic retinopathy screening

Sohini Roychowdhury, Dara Koozekanani, Keshab K Parhi

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

6 Citations (Scopus)

Abstract

Neovascularization is the primary manifestation of proliferative diabetic retinopathy (PDR) that can lead to acquired blindness. This paper presents a novel method that classifies neovascularizations in the 1-optic disc (OD) diameter region (NVD) and elsewhere (NVE) separately to achieve low false positive rates of neovascularization classification. First, the OD region and blood vessels are extracted. Next, the major blood vessel segments in the 1-OD diameter region are classified for NVD, and minor blood vessel segments elsewhere are classified for NVE. For NVD and NVE classifications, optimal region-based feature sets of 10 and 6 features, respectively, are used. The proposed method achieves classification sensitivity, specificity and accuracy for NVD and NVE of 74%, 98.2%, 87.6%, and 61%, 97.5%, 92.1%, respectively. Also, the proposed method achieves 86.4% sensitivity and 76% specificity for screening images with PDR from public and local data sets. Thus, the proposed NVD and NVE detection methods can play a key role in automated screening and prioritization of patients with diabetic retinopathy.

Original languageEnglish (US)
Title of host publication2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1300-1303
Number of pages4
Volume2016-October
ISBN (Electronic)9781457702204
DOIs
StatePublished - Oct 13 2016
Event38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 - Orlando, United States
Duration: Aug 16 2016Aug 20 2016

Other

Other38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
CountryUnited States
CityOrlando
Period8/16/168/20/16

Fingerprint

Blood vessels
Diabetic Retinopathy
Optics
Optic Disk
Screening
Blood Vessels
Sensitivity and Specificity
Blindness

Keywords

  • Diabetic retinopathy
  • Frangi-filter
  • Neovascularization
  • Watershed transform

Cite this

Roychowdhury, S., Koozekanani, D., & Parhi, K. K. (2016). Automated detection of neovascularization for proliferative diabetic retinopathy screening. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 (Vol. 2016-October, pp. 1300-1303). [7590945] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2016.7590945

Automated detection of neovascularization for proliferative diabetic retinopathy screening. / Roychowdhury, Sohini; Koozekanani, Dara; Parhi, Keshab K.

2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. p. 1300-1303 7590945.

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

Roychowdhury, S, Koozekanani, D & Parhi, KK 2016, Automated detection of neovascularization for proliferative diabetic retinopathy screening. in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. vol. 2016-October, 7590945, Institute of Electrical and Electronics Engineers Inc., pp. 1300-1303, 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016, Orlando, United States, 8/16/16. https://doi.org/10.1109/EMBC.2016.7590945
Roychowdhury S, Koozekanani D, Parhi KK. Automated detection of neovascularization for proliferative diabetic retinopathy screening. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1300-1303. 7590945 https://doi.org/10.1109/EMBC.2016.7590945
Roychowdhury, Sohini ; Koozekanani, Dara ; Parhi, Keshab K. / Automated detection of neovascularization for proliferative diabetic retinopathy screening. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1300-1303
@inproceedings{f97a3710eac1469a84c60d06db9eebfb,
title = "Automated detection of neovascularization for proliferative diabetic retinopathy screening",
abstract = "Neovascularization is the primary manifestation of proliferative diabetic retinopathy (PDR) that can lead to acquired blindness. This paper presents a novel method that classifies neovascularizations in the 1-optic disc (OD) diameter region (NVD) and elsewhere (NVE) separately to achieve low false positive rates of neovascularization classification. First, the OD region and blood vessels are extracted. Next, the major blood vessel segments in the 1-OD diameter region are classified for NVD, and minor blood vessel segments elsewhere are classified for NVE. For NVD and NVE classifications, optimal region-based feature sets of 10 and 6 features, respectively, are used. The proposed method achieves classification sensitivity, specificity and accuracy for NVD and NVE of 74{\%}, 98.2{\%}, 87.6{\%}, and 61{\%}, 97.5{\%}, 92.1{\%}, respectively. Also, the proposed method achieves 86.4{\%} sensitivity and 76{\%} specificity for screening images with PDR from public and local data sets. Thus, the proposed NVD and NVE detection methods can play a key role in automated screening and prioritization of patients with diabetic retinopathy.",
keywords = "Diabetic retinopathy, Frangi-filter, Neovascularization, Watershed transform",
author = "Sohini Roychowdhury and Dara Koozekanani and Parhi, {Keshab K}",
year = "2016",
month = "10",
day = "13",
doi = "10.1109/EMBC.2016.7590945",
language = "English (US)",
volume = "2016-October",
pages = "1300--1303",
booktitle = "2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Automated detection of neovascularization for proliferative diabetic retinopathy screening

AU - Roychowdhury, Sohini

AU - Koozekanani, Dara

AU - Parhi, Keshab K

PY - 2016/10/13

Y1 - 2016/10/13

N2 - Neovascularization is the primary manifestation of proliferative diabetic retinopathy (PDR) that can lead to acquired blindness. This paper presents a novel method that classifies neovascularizations in the 1-optic disc (OD) diameter region (NVD) and elsewhere (NVE) separately to achieve low false positive rates of neovascularization classification. First, the OD region and blood vessels are extracted. Next, the major blood vessel segments in the 1-OD diameter region are classified for NVD, and minor blood vessel segments elsewhere are classified for NVE. For NVD and NVE classifications, optimal region-based feature sets of 10 and 6 features, respectively, are used. The proposed method achieves classification sensitivity, specificity and accuracy for NVD and NVE of 74%, 98.2%, 87.6%, and 61%, 97.5%, 92.1%, respectively. Also, the proposed method achieves 86.4% sensitivity and 76% specificity for screening images with PDR from public and local data sets. Thus, the proposed NVD and NVE detection methods can play a key role in automated screening and prioritization of patients with diabetic retinopathy.

AB - Neovascularization is the primary manifestation of proliferative diabetic retinopathy (PDR) that can lead to acquired blindness. This paper presents a novel method that classifies neovascularizations in the 1-optic disc (OD) diameter region (NVD) and elsewhere (NVE) separately to achieve low false positive rates of neovascularization classification. First, the OD region and blood vessels are extracted. Next, the major blood vessel segments in the 1-OD diameter region are classified for NVD, and minor blood vessel segments elsewhere are classified for NVE. For NVD and NVE classifications, optimal region-based feature sets of 10 and 6 features, respectively, are used. The proposed method achieves classification sensitivity, specificity and accuracy for NVD and NVE of 74%, 98.2%, 87.6%, and 61%, 97.5%, 92.1%, respectively. Also, the proposed method achieves 86.4% sensitivity and 76% specificity for screening images with PDR from public and local data sets. Thus, the proposed NVD and NVE detection methods can play a key role in automated screening and prioritization of patients with diabetic retinopathy.

KW - Diabetic retinopathy

KW - Frangi-filter

KW - Neovascularization

KW - Watershed transform

UR - http://www.scopus.com/inward/record.url?scp=85009136676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009136676&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2016.7590945

DO - 10.1109/EMBC.2016.7590945

M3 - Conference contribution

VL - 2016-October

SP - 1300

EP - 1303

BT - 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -