Retinal microaneurysms detection using local convergence index features

Research output: Contribution to journalArticleAcademicpeer-review

9 Citations (Scopus)

Abstract

Retinal microaneurysms (MAs) are the earliest clinical sign of diabetic retinopathy disease. Detection of microaneurysms is crucial for the early diagnosis of diabetic retinopathy and prevention of blindness. In this paper, a novel and reliable method for automatic detection of microaneurysms in retinal images is proposed. In the first stage of the proposed method, several preliminary microaneurysm candidates are extracted using a gradient weighting technique and an iterative thresholding approach. In the next stage, in addition to intensity and shape descriptors, a new set of features based on local convergence index filters is extracted for each candidate. Finally, the collective set of features is fed to a hybrid sampling/boosting classifier to discriminate the MAs from non-MAs candidates. The method is evaluated on images with different resolutions and modalities (RGB and SLO) using six publicly available datasets including the Retinopathy Online Challenges dataset (ROC). The proposed method achieves an average sensitivity score of 0.471 on the ROC dataset outperforming state-of-the-art approaches in an extensive comparison. The experimental results on the other five datasets demonstrate the effectiveness and robustness of the proposed microaneurysms detection method regardless of different image resolutions and modalities.

Original languageEnglish
Pages (from-to)3300-3315
Number of pages16
JournalIEEE Transactions on Image Processing
Volume27
Issue number7
DOIs
Publication statusPublished - 12 Mar 2018

Fingerprint

Image resolution
Classifiers
Sampling

Keywords

  • Computer-aided diagnosis
  • diabetic retinopathy
  • local convergence filter
  • microaneurysm detection
  • retina

Cite this

@article{c1db5a480d2743b9b41109e1c46afe8d,
title = "Retinal microaneurysms detection using local convergence index features",
abstract = "Retinal microaneurysms (MAs) are the earliest clinical sign of diabetic retinopathy disease. Detection of microaneurysms is crucial for the early diagnosis of diabetic retinopathy and prevention of blindness. In this paper, a novel and reliable method for automatic detection of microaneurysms in retinal images is proposed. In the first stage of the proposed method, several preliminary microaneurysm candidates are extracted using a gradient weighting technique and an iterative thresholding approach. In the next stage, in addition to intensity and shape descriptors, a new set of features based on local convergence index filters is extracted for each candidate. Finally, the collective set of features is fed to a hybrid sampling/boosting classifier to discriminate the MAs from non-MAs candidates. The method is evaluated on images with different resolutions and modalities (RGB and SLO) using six publicly available datasets including the Retinopathy Online Challenges dataset (ROC). The proposed method achieves an average sensitivity score of 0.471 on the ROC dataset outperforming state-of-the-art approaches in an extensive comparison. The experimental results on the other five datasets demonstrate the effectiveness and robustness of the proposed microaneurysms detection method regardless of different image resolutions and modalities.",
keywords = "Computer-aided diagnosis, diabetic retinopathy, local convergence filter, microaneurysm detection, retina",
author = "B. Dashtbozorg and J. Zhang and F. Huang and {ter Haar Romeny}, B.M.",
year = "2018",
month = "3",
day = "12",
doi = "10.1109/TIP.2018.2815345",
language = "English",
volume = "27",
pages = "3300--3315",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers",
number = "7",

}

Retinal microaneurysms detection using local convergence index features. / Dashtbozorg, B.; Zhang, J.; Huang, F.; ter Haar Romeny, B.M.

In: IEEE Transactions on Image Processing, Vol. 27, No. 7, 12.03.2018, p. 3300-3315.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Retinal microaneurysms detection using local convergence index features

AU - Dashtbozorg, B.

AU - Zhang, J.

AU - Huang, F.

AU - ter Haar Romeny, B.M.

PY - 2018/3/12

Y1 - 2018/3/12

N2 - Retinal microaneurysms (MAs) are the earliest clinical sign of diabetic retinopathy disease. Detection of microaneurysms is crucial for the early diagnosis of diabetic retinopathy and prevention of blindness. In this paper, a novel and reliable method for automatic detection of microaneurysms in retinal images is proposed. In the first stage of the proposed method, several preliminary microaneurysm candidates are extracted using a gradient weighting technique and an iterative thresholding approach. In the next stage, in addition to intensity and shape descriptors, a new set of features based on local convergence index filters is extracted for each candidate. Finally, the collective set of features is fed to a hybrid sampling/boosting classifier to discriminate the MAs from non-MAs candidates. The method is evaluated on images with different resolutions and modalities (RGB and SLO) using six publicly available datasets including the Retinopathy Online Challenges dataset (ROC). The proposed method achieves an average sensitivity score of 0.471 on the ROC dataset outperforming state-of-the-art approaches in an extensive comparison. The experimental results on the other five datasets demonstrate the effectiveness and robustness of the proposed microaneurysms detection method regardless of different image resolutions and modalities.

AB - Retinal microaneurysms (MAs) are the earliest clinical sign of diabetic retinopathy disease. Detection of microaneurysms is crucial for the early diagnosis of diabetic retinopathy and prevention of blindness. In this paper, a novel and reliable method for automatic detection of microaneurysms in retinal images is proposed. In the first stage of the proposed method, several preliminary microaneurysm candidates are extracted using a gradient weighting technique and an iterative thresholding approach. In the next stage, in addition to intensity and shape descriptors, a new set of features based on local convergence index filters is extracted for each candidate. Finally, the collective set of features is fed to a hybrid sampling/boosting classifier to discriminate the MAs from non-MAs candidates. The method is evaluated on images with different resolutions and modalities (RGB and SLO) using six publicly available datasets including the Retinopathy Online Challenges dataset (ROC). The proposed method achieves an average sensitivity score of 0.471 on the ROC dataset outperforming state-of-the-art approaches in an extensive comparison. The experimental results on the other five datasets demonstrate the effectiveness and robustness of the proposed microaneurysms detection method regardless of different image resolutions and modalities.

KW - Computer-aided diagnosis

KW - diabetic retinopathy

KW - local convergence filter

KW - microaneurysm detection

KW - retina

UR - http://www.scopus.com/inward/record.url?scp=85043455296&partnerID=8YFLogxK

U2 - 10.1109/TIP.2018.2815345

DO - 10.1109/TIP.2018.2815345

M3 - Article

C2 - 29641408

AN - SCOPUS:85043455296

VL - 27

SP - 3300

EP - 3315

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 7

ER -