QUARTZ: Quantitative Analysis of Retinal Vessel Topology and size – An automated system for quantification of retinal vessels morphology

Fraz, Muhammad Moazam; Welikala, Roshan Alex; Rudnicka, Alicja R.; Owen, Christopher G.; Strachan, David P.; Barman, Sarah

doi:10.1016/j.eswa.2015.05.022

Cited by 66 publications

(56 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The change in vessel diameters is used to calculate AVR and it is significant in determining the presence of hypertensive retinopathy and grading its severity [25,26]. Table 2 Table 3 displays statistical performance of the proposed method on MESSIDOR dataset.…”

Section: Grading Of Hypertensive Retinopathymentioning

confidence: 99%

Measurement of Arterio-Venous Ratio for Detection of Hypertensive Retinopathy through Digital Color Fundus Images

Rani

Mittal

2015

JBEMi

View full text Add to dashboard Cite

Hypertensive retinopathy is a retinal vascular damage caused by high blood pressure which results in loss of vision. In the present work, effort has been devoted to enhance and segment the retinal vasculature which is required to calculate its anatomical characteristics such as width, length for the quantitative measurement of arterio-venous ratio (AVR). Enhancement of the retinal fundus images is done using tophat transform and segmentation of the vessels using iterative thresholding. The performance of the proposed method is tested on 50 digital fundus images of publicly available MESSIDOR dataset. The hypertensive retinopathy can be measured quantitatively by detecting the decrement in the ratio of width of retinal artery-vein to that of the normal images. The arterio-venous ratio obtained by applying the proposed methodology was found to be 0.62-0.735 in normal cases and 0.203-0.495 in case of patients suffering from hypertensive retinopathy on MESSIDOR dataset which was not performed earlier. This measurement of arterio-venous ratio will be further helpful to identify the stages of hypertensive retinopathy.

show abstract

Section: Grading Of Hypertensive Retinopathymentioning

confidence: 99%

Measurement of Arterio-Venous Ratio for Detection of Hypertensive Retinopathy through Digital Color Fundus Images

Rani

Mittal

2015

JBEMi

View full text Add to dashboard Cite

show abstract

“…This allows the software to be structured into modules which include vessel segmentation, vessel analysis, arteriole/venule (a/v) classification, optic disc localization and image quality assessment. Brief algorithm details of these modules are presented in this section; see [16,26,27] for full details. This is accompanied by evaluation of the modules using a subset of 4,692 retinal images, attained from 2,346 random UK Biobank participants.…”

Section: Quartz Overviewmentioning

confidence: 99%

“…QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) is a retinal image analysis system developed by our research group, which is an automated processing system for large numbers of retinal images and obtains quantitative measures of vessel morphology to be used in epidemiological studies [16]. Other notable systems exist, which include VAMPIRE [17][18][19], SIRIUS [20], ARIA [21], CAIAR [22,23] and SIVA [24].…”

Section: Introductionmentioning

confidence: 99%

Automated quantification of retinal vessel morphometry in the UK biobank cohort

Welikala

Fraz

Habib

et al. 2017

2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA)

Self Cite

View full text Add to dashboard Cite

Abstract-The morphometric characteristics of the retinal vascular network have been associated with risk markers of many systemic and vascular diseases. However, analysis of data from large population based studies is needed to help resolve uncertainties in these associations. QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) is a fully automated retinal image analysis system that has been designed to process large numbers of retinal images and obtains quantitative measures of vessel morphology to be used in epidemiological studies. QUARTZ has been used to process retinal images from UK Biobank which is a large population-based cohort study. In this paper, we address issues of robustness with respect to processing large datasets and validate QUARTZ using a subset of 4,692 UK Biobank retinal images. Ground truth data produced by human observers for validation have been made available online. Following validation, 135,867 retinal images (68,549 participants) from the UK Biobank study were processed by QUARTZ. 71.53% of these images were classified as being of adequate quality, which equated to 80.90% participants with at least one image of adequate quality. The vessel morphometric data are currently being used in epidemiological studies. The intention of the UK Biobank Eye and Vision Consortium is to include these derived measures in the UK Biobank data archive.

show abstract

“…The application of a hysteresis thresholding based morphological reconstruction then followed to produce the segmented vasculature. A full description on this methodology is provided in [10].…”

Section: Vessel Segmentationmentioning

confidence: 99%

“…Additional steps, to those documented in [10], of pre-processing and post-processing were performed to further improve the segmentation. For epidemiological studies, the need to keep the segmentation of non-vessel objects to a minimum is more important than the segmentation of the complete vasculature.…”

Section: Vessel Segmentationmentioning

confidence: 99%

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

Welikala

Fraz

Foster

et al. 2016

Computers in Biology and Medicine

Self Cite

View full text Add to dashboard Cite

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.

show abstract

QUARTZ: Quantitative Analysis of Retinal Vessel Topology and size – An automated system for quantification of retinal vessels morphology

Cited by 66 publications

References 40 publications

Measurement of Arterio-Venous Ratio for Detection of Hypertensive Retinopathy through Digital Color Fundus Images

Measurement of Arterio-Venous Ratio for Detection of Hypertensive Retinopathy through Digital Color Fundus Images

Automated quantification of retinal vessel morphometry in the UK biobank cohort

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

Contact Info

Product

Resources

About