Home > Research > Publications & Outputs > GGM classifier with multi-scale line detectors ...

Electronic data

  • template_updatedV1

    Rights statement: The final publication is available at Springer via http://dx.doi.org/10.1007/s11760-019-01515-3

    Accepted author manuscript, 1.14 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

GGM classifier with multi-scale line detectors for retinal vessel segmentation

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

GGM classifier with multi-scale line detectors for retinal vessel segmentation. / Khan, M.A.U.; Khan, T.M.; Naqvi, S.S. et al.
In: Signal, Image and Video Processing, Vol. 13, No. 8, 01.11.2019, p. 1667–1675.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Khan, MAU, Khan, TM, Naqvi, SS & Aurangzeb Khan, M 2019, 'GGM classifier with multi-scale line detectors for retinal vessel segmentation', Signal, Image and Video Processing, vol. 13, no. 8, pp. 1667–1675. https://doi.org/10.1007/s11760-019-01515-3

APA

Khan, M. A. U., Khan, T. M., Naqvi, S. S., & Aurangzeb Khan, M. (2019). GGM classifier with multi-scale line detectors for retinal vessel segmentation. Signal, Image and Video Processing, 13(8), 1667–1675. https://doi.org/10.1007/s11760-019-01515-3

Vancouver

Khan MAU, Khan TM, Naqvi SS, Aurangzeb Khan M. GGM classifier with multi-scale line detectors for retinal vessel segmentation. Signal, Image and Video Processing. 2019 Nov 1;13(8):1667–1675. Epub 2019 Jun 10. doi: 10.1007/s11760-019-01515-3

Author

Khan, M.A.U. ; Khan, T.M. ; Naqvi, S.S. et al. / GGM classifier with multi-scale line detectors for retinal vessel segmentation. In: Signal, Image and Video Processing. 2019 ; Vol. 13, No. 8. pp. 1667–1675.

Bibtex

@article{f58f02f60ebe4b8198955b1f571c6cd6,
title = "GGM classifier with multi-scale line detectors for retinal vessel segmentation",
abstract = "Persistent changes in the diameter of retinal blood vessels may indicate some chronic eye diseases. Computer-assisted change observation attempts may become challenging due to the emergence of interfering pathologies around blood vessels in retinal fundus images. The end result is lower sensitivity to thin vessels for certain computerized detection methods. Quite recently, multi-scale line detection method proved to be worthy for improved sensitivity toward lower-caliber vessels detection. This happens largely due to its adaptive property that responds more to the longevity patterns than width of a given vessel. However, the method suffers from the lack of a better aggregation process for individual line detectors. This paper investigates a scenario that introduces a supervised generalized Gaussian mixture classifier as a robust solution for the aggregate process. The classifier is built with class-conditional probability density functions as a logistic function of linear mixtures. To boost the classifier{\textquoteright}s performance, the weighted scale images are modeled as Gaussian mixtures. The classifier is trained with weighted images modeled on a Gaussian mixture. The net effect is increased sensitivity for small vessels. The classifier{\textquoteright}s performance has been tested with three commonly available data sets: DRIVE, SATRE, and CHASE_DB1. The results of the proposed method (with an accuracy of 96%, 96.1% and 95% on DRIVE, STARE, and CHASE_DB1, respectively) demonstrate its competitiveness against the state-of-the-art methods and its reliability for vessel segmentation.",
keywords = "Diabetic retinopathy, Image segmentation, Retinal images, Vessel segmentation, Classification (of information), Digital storage, Eye protection, Gaussian distribution, Large scale systems, Ophthalmology, Probability density function, Scales (weighing instruments), Conditional probability density, Retinal blood vessels, Retinal fundus images, Retinal image, Retinal vessel segmentations, State-of-the-art methods, Blood vessels",
author = "M.A.U. Khan and T.M. Khan and S.S. Naqvi and {Aurangzeb Khan}, M.",
note = "The final publication is available at Springer via http://dx.doi.org/10.1007/s11760-019-01515-3",
year = "2019",
month = nov,
day = "1",
doi = "10.1007/s11760-019-01515-3",
language = "English",
volume = "13",
pages = "1667–1675",
journal = "Signal, Image and Video Processing",
issn = "1863-1703",
publisher = "Springer London",
number = "8",

}

RIS

TY - JOUR

T1 - GGM classifier with multi-scale line detectors for retinal vessel segmentation

AU - Khan, M.A.U.

AU - Khan, T.M.

AU - Naqvi, S.S.

AU - Aurangzeb Khan, M.

N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/s11760-019-01515-3

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Persistent changes in the diameter of retinal blood vessels may indicate some chronic eye diseases. Computer-assisted change observation attempts may become challenging due to the emergence of interfering pathologies around blood vessels in retinal fundus images. The end result is lower sensitivity to thin vessels for certain computerized detection methods. Quite recently, multi-scale line detection method proved to be worthy for improved sensitivity toward lower-caliber vessels detection. This happens largely due to its adaptive property that responds more to the longevity patterns than width of a given vessel. However, the method suffers from the lack of a better aggregation process for individual line detectors. This paper investigates a scenario that introduces a supervised generalized Gaussian mixture classifier as a robust solution for the aggregate process. The classifier is built with class-conditional probability density functions as a logistic function of linear mixtures. To boost the classifier’s performance, the weighted scale images are modeled as Gaussian mixtures. The classifier is trained with weighted images modeled on a Gaussian mixture. The net effect is increased sensitivity for small vessels. The classifier’s performance has been tested with three commonly available data sets: DRIVE, SATRE, and CHASE_DB1. The results of the proposed method (with an accuracy of 96%, 96.1% and 95% on DRIVE, STARE, and CHASE_DB1, respectively) demonstrate its competitiveness against the state-of-the-art methods and its reliability for vessel segmentation.

AB - Persistent changes in the diameter of retinal blood vessels may indicate some chronic eye diseases. Computer-assisted change observation attempts may become challenging due to the emergence of interfering pathologies around blood vessels in retinal fundus images. The end result is lower sensitivity to thin vessels for certain computerized detection methods. Quite recently, multi-scale line detection method proved to be worthy for improved sensitivity toward lower-caliber vessels detection. This happens largely due to its adaptive property that responds more to the longevity patterns than width of a given vessel. However, the method suffers from the lack of a better aggregation process for individual line detectors. This paper investigates a scenario that introduces a supervised generalized Gaussian mixture classifier as a robust solution for the aggregate process. The classifier is built with class-conditional probability density functions as a logistic function of linear mixtures. To boost the classifier’s performance, the weighted scale images are modeled as Gaussian mixtures. The classifier is trained with weighted images modeled on a Gaussian mixture. The net effect is increased sensitivity for small vessels. The classifier’s performance has been tested with three commonly available data sets: DRIVE, SATRE, and CHASE_DB1. The results of the proposed method (with an accuracy of 96%, 96.1% and 95% on DRIVE, STARE, and CHASE_DB1, respectively) demonstrate its competitiveness against the state-of-the-art methods and its reliability for vessel segmentation.

KW - Diabetic retinopathy

KW - Image segmentation

KW - Retinal images

KW - Vessel segmentation

KW - Classification (of information)

KW - Digital storage

KW - Eye protection

KW - Gaussian distribution

KW - Large scale systems

KW - Ophthalmology

KW - Probability density function

KW - Scales (weighing instruments)

KW - Conditional probability density

KW - Retinal blood vessels

KW - Retinal fundus images

KW - Retinal image

KW - Retinal vessel segmentations

KW - State-of-the-art methods

KW - Blood vessels

U2 - 10.1007/s11760-019-01515-3

DO - 10.1007/s11760-019-01515-3

M3 - Journal article

VL - 13

SP - 1667

EP - 1675

JO - Signal, Image and Video Processing

JF - Signal, Image and Video Processing

SN - 1863-1703

IS - 8

ER -