Home > Research > Publications & Outputs > Automatic detection and distinction of retinal ...

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Automatic detection and distinction of retinal vessel bifurcations and crossings in colour fundus photography

Research output: Contribution to journalJournal article

Published

Standard

Automatic detection and distinction of retinal vessel bifurcations and crossings in colour fundus photography. / Pratt, Harry; Williams, Bryan M.; Ku, Jae Yee; Vas, Charles; McCann, Emma; Al-Bander, Baidaa; Zhao, Yitian; Coenen, Frans; Zheng, Yalin.

In: Journal of Imaging, Vol. 4, No. 1, 4, 01.01.2018.

Research output: Contribution to journalJournal article

Harvard

Pratt, H, Williams, BM, Ku, JY, Vas, C, McCann, E, Al-Bander, B, Zhao, Y, Coenen, F & Zheng, Y 2018, 'Automatic detection and distinction of retinal vessel bifurcations and crossings in colour fundus photography', Journal of Imaging, vol. 4, no. 1, 4. https://doi.org/10.3390/jimaging4010004

APA

Pratt, H., Williams, B. M., Ku, J. Y., Vas, C., McCann, E., Al-Bander, B., Zhao, Y., Coenen, F., & Zheng, Y. (2018). Automatic detection and distinction of retinal vessel bifurcations and crossings in colour fundus photography. Journal of Imaging, 4(1), [4]. https://doi.org/10.3390/jimaging4010004

Vancouver

Author

Pratt, Harry ; Williams, Bryan M. ; Ku, Jae Yee ; Vas, Charles ; McCann, Emma ; Al-Bander, Baidaa ; Zhao, Yitian ; Coenen, Frans ; Zheng, Yalin. / Automatic detection and distinction of retinal vessel bifurcations and crossings in colour fundus photography. In: Journal of Imaging. 2018 ; Vol. 4, No. 1.

Bibtex

@article{8d9540b398934de59a56e5d84d4e62b5,
title = "Automatic detection and distinction of retinal vessel bifurcations and crossings in colour fundus photography",
abstract = "The analysis of retinal blood vessels present in fundus images, and the addressing of problems such as blood clot location, is important to undertake accurate and appropriate treatment of the vessels. Such tasks are hampered by the challenge of accurately tracing back problems along vessels to their source. This is due to the unresolved issue of distinguishing automatically between vessel bifurcations and vessel crossings in colour fundus photographs. In this paper, we present a new technique for addressing this problem using a convolutional neural network approach to firstly locate vessel bifurcations and crossings and then to classifying them as either bifurcations or crossings. Our method achieves high accuracies for junction detection and classification on the DRIVE dataset and we show further validation on an unseen dataset from which no data has been used for training. Combined with work in automated segmentation, this method has the potential to facilitate: reconstruction of vessel topography, classification of veins and arteries and automated localisation of blood clots and other disease symptoms leading to improved management of eye disease.",
keywords = "Convolutional neural networks, Fundus photography, Machine learning, Medical image analysis, Retinal imaging, Retinal vessels, Vessel classification",
author = "Harry Pratt and Williams, {Bryan M.} and Ku, {Jae Yee} and Charles Vas and Emma McCann and Baidaa Al-Bander and Yitian Zhao and Frans Coenen and Yalin Zheng",
year = "2018",
month = jan
day = "1",
doi = "10.3390/jimaging4010004",
language = "English",
volume = "4",
journal = "Journal of Imaging",
number = "1",

}

RIS

TY - JOUR

T1 - Automatic detection and distinction of retinal vessel bifurcations and crossings in colour fundus photography

AU - Pratt, Harry

AU - Williams, Bryan M.

AU - Ku, Jae Yee

AU - Vas, Charles

AU - McCann, Emma

AU - Al-Bander, Baidaa

AU - Zhao, Yitian

AU - Coenen, Frans

AU - Zheng, Yalin

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The analysis of retinal blood vessels present in fundus images, and the addressing of problems such as blood clot location, is important to undertake accurate and appropriate treatment of the vessels. Such tasks are hampered by the challenge of accurately tracing back problems along vessels to their source. This is due to the unresolved issue of distinguishing automatically between vessel bifurcations and vessel crossings in colour fundus photographs. In this paper, we present a new technique for addressing this problem using a convolutional neural network approach to firstly locate vessel bifurcations and crossings and then to classifying them as either bifurcations or crossings. Our method achieves high accuracies for junction detection and classification on the DRIVE dataset and we show further validation on an unseen dataset from which no data has been used for training. Combined with work in automated segmentation, this method has the potential to facilitate: reconstruction of vessel topography, classification of veins and arteries and automated localisation of blood clots and other disease symptoms leading to improved management of eye disease.

AB - The analysis of retinal blood vessels present in fundus images, and the addressing of problems such as blood clot location, is important to undertake accurate and appropriate treatment of the vessels. Such tasks are hampered by the challenge of accurately tracing back problems along vessels to their source. This is due to the unresolved issue of distinguishing automatically between vessel bifurcations and vessel crossings in colour fundus photographs. In this paper, we present a new technique for addressing this problem using a convolutional neural network approach to firstly locate vessel bifurcations and crossings and then to classifying them as either bifurcations or crossings. Our method achieves high accuracies for junction detection and classification on the DRIVE dataset and we show further validation on an unseen dataset from which no data has been used for training. Combined with work in automated segmentation, this method has the potential to facilitate: reconstruction of vessel topography, classification of veins and arteries and automated localisation of blood clots and other disease symptoms leading to improved management of eye disease.

KW - Convolutional neural networks

KW - Fundus photography

KW - Machine learning

KW - Medical image analysis

KW - Retinal imaging

KW - Retinal vessels

KW - Vessel classification

U2 - 10.3390/jimaging4010004

DO - 10.3390/jimaging4010004

M3 - Journal article

AN - SCOPUS:85050393066

VL - 4

JO - Journal of Imaging

JF - Journal of Imaging

IS - 1

M1 - 4

ER -