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.
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.
This review provides guidance for building robust, interpretable, and deployable retinal visual computing systems in fusion-centric systems and foundation-model-centric systems.
Ou-Xiang Li, Yue-Cheng He, Chen Wang et al.· The Visual Computer· 0 citations
A systematic comparative evaluation of three deep learning-based segmentation architectures — U-Net, U-Net++, and Y-Net — for automated identification of DME and Intraretinal Fluid regions in OCT scans demonstrates the feasibility of deep learning-based OCT segmentation as a diagnostic support tool in resource-constrai...
Dhiraj Pyakurel, Yokisha Poudel, S. Prasai et al.· Journal of Hillside College...· 0 citations
This systematic review synthesizes the state-of-the-art computational pipelines, training paradigms, and explainability frameworks that enable the extraction of predictive systemic biomarkers from retinal imaging and highlights a methodological mandate for eXplainable Artificial Intelligence (XAI) in clinical translati...
Hítalo Silva, Arlington Rodrigues, Rafael Albuquerque et al.· Research on Biomedical Engin...· 0 citations
Retinal diseases such as hypertensive retinopathy (HR), myopia, and retinitis pigmentosa (RP) may remain undiagnosed until irreversible visual impairment occurs. Retinal multi disease classification models are often developed by integrating multiple public fundus datasets and evaluated using internal validation. We e...
A. Manal, Fathima Hafsa, Z. Khalid et al.· Scientific Reports· 0 citations
Automated retinal vessel segmentation can support quantitative analysis of fundus photographs and facilitate measurement of vascular characteristics associated with ocular and systemic disease. Although deep-learning methods achieve high segmentation performance on benchmark datasets, their reliability may decrease whe...
R. Abbasi, Oyewale Ibrahim Abdulrasheed, Madiha Jabeen Abbasi et al.· Bioengineering· 0 citations