Send to

Choose Destination
Comput Biol Med. 2017 Nov 1;90:23-32. doi: 10.1016/j.compbiomed.2017.09.005. Epub 2017 Sep 8.

Automated arteriole and venule classification using deep learning for retinal images from the UK Biobank cohort.

Author information

School of Computer Science and Mathematics, Kingston University, Surrey, KT1 2EE, United Kingdom. Electronic address:
NIHR Biomedical Research Centre, Moorfields Eye Hospital, London, EC1V 2PD, United Kingdom; UCL Institute of Ophthalmology, London, EC1V 9EL, United Kingdom.
Population Health Research Institute, St. George's, University of London, London, SW17 0RE, United Kingdom.
School of Computer Science and Mathematics, Kingston University, Surrey, KT1 2EE, United Kingdom.


The morphometric characteristics of the retinal vasculature are associated with future risk of many systemic and vascular diseases. However, analysis of data from large population based studies is needed to help resolve uncertainties in some of these associations. This requires automated systems that extract quantitative measures of vessel morphology from large numbers of retinal images. Associations between retinal vessel morphology and disease precursors/outcomes may be similar or opposing for arterioles and venules. Therefore, the accurate detection of the vessel type is an important element in such automated systems. This paper presents a deep learning approach for the automatic classification of arterioles and venules across the entire retinal image, including vessels located at the optic disc. This comprises of a convolutional neural network whose architecture contains six learned layers: three convolutional and three fully-connected. Complex patterns are automatically learnt from the data, which avoids the use of hand crafted features. The method is developed and evaluated using 835,914 centreline pixels derived from 100 retinal images selected from the 135,867 retinal images obtained at the UK Biobank (large population-based cohort study of middle aged and older adults) baseline examination. This is a challenging dataset in respect to image quality and hence arteriole/venule classification is required to be highly robust. The method achieves a significant increase in accuracy of 8.1% when compared to the baseline method, resulting in an arteriole/venule classification accuracy of 86.97% (per pixel basis) over the entire retinal image.


Arteriole/venule classification; Convolutional neural networks; Deep learning; Epidemiological studies; Retinal images; UK Biobank

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center