QUARTZ: Cross-Dataset Artificial Intelligence-Enabled Retinal Vasculometry
- 1Kingston University, London, UK
Abstract
Examination of retinal images provides a non-invasive means to assess the body's microvascular system, with vessel morphology linked to ocular and systemic diseases. QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) is an automated, artificial intelligence-enabled retinal vasculometry system designed for processing large-scale retinal image datasets, including over 4 million images from within the National Health Service, to facilitate epidemiological studies. The system is uniquely capable of extracting useful information from lower quality images, including those which are partially illuminated, enabling analysis of a greater proportion of images. To enhance cross-dataset generalisation of the system from an earlier dataset-tailored approach, this work leverages 26 annotated retinal image datasets spanning diverse demographics, diseases, camera types, and imaging protocols. Evaluation on the external EPIC-Norfolk dataset demonstrates robust performance with F1 scores of 0.8305, 0.8477, 0.8741, 0.9532, and 0.8677 for arteriole, venule, vessel, optic disc, and optic cup segmentation, respectively, and 0.9197 for image quality classification. The cross-dataset generalisation approach demonstrated increased performance for arteriole/venule segmentation and optic disc segmentation. However, improvements in performance were not observed for optic cup segmentation, or for image quality classification. An online tool is provided to support wider adoption and reproducible biomarker research across diverse populations and imaging settings. In addition, the new public CHASE-AV database is introduced for arteriole and venule segmentation.
Related
- Artificial intelligence-enabled mental health applications for adolescents: a scoping review of safety, effectiveness and clinical implementation
- Building smarter surveillance: a framework for artificial intelligence-enabled monitoring of overuse injuries in youth sports.
- Artificial intelligence-enabled healthcare access and user experience: comparative institutional analysis and survey evidence from China
- A prebill control plane for record integrity in inpatient artificial intelligence-enabled clinical documentation workflows.
- Artificial Intelligence-Enabled Medical Diagnosis in the Internet of Medical Things: An End-to-End Survey of Connected Sensing, Distributed Intelligence, Clinical Applications, and Validation.
BibTeX
@misc{welikala2026quartz,
title = {{QUARTZ: Cross-Dataset Artificial Intelligence-Enabled Retinal Vasculometry}},
author = {R. A. Welikala and J. Fajtl and G. Johnson and F. Rahman and P. Remagnino and E. E. Freeman and M. Kolko and R. Chambers and L. Bolter and J. Anderson and A. Olvera-Barrios and A. Warwick and P. J. Foster and A. P. Khawaja and R. Shakespeare and M. Ramesh and C. Egan and A. Tufail and C. G. Owen and A. R. Rudnicka and S. Barman and UK Biobank Eye and Vision Consortium and EPIC-Norfolk Investigators and ARIAS Research Group},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.28.26363792},
url = {https://www.medrxiv.org/content/10.64898/2026.10.28.26363792v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - QUARTZ: Cross-Dataset Artificial Intelligence-Enabled Retinal Vasculometry
AU - R. A. Welikala
AU - J. Fajtl
AU - G. Johnson
AU - F. Rahman
AU - P. Remagnino
AU - E. E. Freeman
AU - M. Kolko
AU - R. Chambers
AU - L. Bolter
AU - J. Anderson
AU - A. Olvera-Barrios
AU - A. Warwick
AU - P. J. Foster
AU - A. P. Khawaja
AU - R. Shakespeare
AU - M. Ramesh
AU - C. Egan
AU - A. Tufail
AU - C. G. Owen
AU - A. R. Rudnicka
AU - S. Barman
AU - UK Biobank Eye and Vision Consortium
AU - EPIC-Norfolk Investigators
AU - ARIAS Research Group
PY - 2026
DA - 2026/10/28
PB - medRxiv
DO - 10.64898/2026.10.28.26363792
UR - https://www.medrxiv.org/content/10.64898/2026.10.28.26363792v1
AB - Examination of retinal images provides a non-invasive means to assess the body's microvascular system, with vessel morphology linked to ocular and systemic diseases. QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) is an automated, artificial intelligence-enabled retinal vasculometry system designed for processing large-scale retinal image datasets, including over 4 million images from within the National Health Service, to facilitate epidemiological studies. The system is uniquely capable of extracting useful information from lower quality images, including those which are partially illuminated, enabling analysis of a greater proportion of images. To enhance cross-dataset generalisation of the system from an earlier dataset-tailored approach, this work leverages 26 annotated retinal image datasets spanning diverse demographics, diseases, camera types, and imaging protocols. Evaluation on the external EPIC-Norfolk dataset demonstrates robust performance with F1 scores of 0.8305, 0.8477, 0.8741, 0.9532, and 0.8677 for arteriole, venule, vessel, optic disc, and optic cup segmentation, respectively, and 0.9197 for image quality classification. The cross-dataset generalisation approach demonstrated increased performance for arteriole/venule segmentation and optic disc segmentation. However, improvements in performance were not observed for optic cup segmentation, or for image quality classification. An online tool is provided to support wider adoption and reproducible biomarker research across diverse populations and imaging settings. In addition, the new public CHASE-AV database is introduced for arteriole and venule segmentation.
ER -