Automated retinal image quality assessment on the UK Biobank dataset for epidemiological studies

• Published in: Computers in biology and medicine Vol. 71; pp. 67 - 76
• Main Authors: Welikala, R.A, Fraz, M.M, Foster, P.J, Whincup, P.H, Rudnicka, A.R, Owen, C.G, Strachan, D.P, Barman, S.A
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.04.2016; Elsevier Limited
• Subjects: Adult; Aged; Algorithms; Automation; Biomedical research; Cardiovascular disease; Classification; Consortia; Datasets; Datasets as Topic; Diabetes; Diabetic retinopathy; Epidemiological studies; Female; Hospitals; Humans; Image Enhancement - methods; Image quality; Internal Medicine; Large retinal datasets; Male; Middle Aged; Morphology; Other; Random Allocation; Retina - pathology; Retinal image; Retinal Vessels - pathology; Software; Studies; UK Biobank; United Kingdom; Vascular Diseases - pathology; Vessel segmentation; United Kingdom > UK; Image quality; Epidemiological studies; Vessel segmentation; Retinal image; Large retinal datasets; UK Biobank
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2016.01.027

Abstract Morphological changes in the retinal vascular network are associated with future risk of many systemic and vascular diseases. However, uncertainty over the presence and nature of some of these associations exists. Analysis of data from large population based studies will help to resolve these uncertainties. The QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) retinal image analysis system allows automated processing of large numbers of retinal images. However, an image quality assessment module is needed to achieve full automation. In this paper, we propose such an algorithm, which uses the segmented vessel map to determine the suitability of retinal images for use in the creation of vessel morphometric data suitable for epidemiological studies. This includes an effective 3-dimensional feature set and support vector machine classification. A random subset of 800 retinal images from UK Biobank (a large prospective study of 500,000 middle aged adults; where 68,151 underwent retinal imaging) was used to examine the performance of the image quality algorithm. The algorithm achieved a sensitivity of 95.33% and a specificity of 91.13% for the detection of inadequate images. The strong performance of this image quality algorithm will make rapid automated analysis of vascular morphometry feasible on the entire UK Biobank dataset (and other large retinal datasets), with minimal operator involvement, and at low cost.