Purpose: To determine the prevalence of glaucoma among patients referred to a glaucoma service with suspicious disc photographs from the diabetic retinopathy (DR) screening program.
Methods: A clinical audit of all patients attending a single-center DR screening program in the Mater Misericordiae University Hospital, Dublin, between July 2010 and October 2011 was conducted with a minimum follow-up of 30 months. The DR screening service uses trained technician graders to assess 2-field color retinal photographs for the features of DR. Recently, the service was enhanced so that optic discs are also assessed for signs of glaucoma.
Results: In the 16-month study period, 3,697 diabetic patients were photographed. Following photograph grading, 91 (2.46%) were judged to require referral for assessment at the glaucoma clinic. Of these, 63 (69.23%) presented for assessment. Thirteen patients (20.63%) were diagnosed with glaucoma, comprising 7 cases of low-tension glaucoma and 6 cases of primary open-angle glaucoma. Thirty-six patients (57.14%) were classified as glaucoma suspects and 14 patients (22.22%) were discharged back to the DR screening program following normal ocular examination. Only 6 (9.52%) of the 63 patients examined had an intraocular pressure greater than 21 mm Hg.
Conclusions: The assessment of DR screening photographs for signs of glaucomatous optic nerve damage should be considered as part of a strategy to improve glaucoma case detection and to reduce the burden of this disease on society.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.5301/ejo.5000722 | DOI Listing |
J Glaucoma
January 2025
Department of Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, MI.
Precis: Current optical coherence tomography normative sample data may not represent diverse human optic nerve anatomy to accurately classify all individuals with true glaucomatous optic neuropathy.
Purpose: To compare optic nerve head (ONH) measurements between published values from an optical coherence tomography (OCT) normative database and a more diverse cohort of healthy individuals.
Patients And Methods: ONH parameters from healthy participants of the Michigan Screening and Intervention for Glaucoma and Eye Health through Telemedicine (MI-SIGHT) program and the Topcon Maestro-1 normative cohort were compared.
Ophthalmol Sci
November 2024
Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California.
Purpose: The aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations.
Design: Evaluation of multimodal large language models for reviewing fundus images in glaucoma.
Subjects: A total of 300 fundus images from 3 public datasets (ACRIMA, ORIGA, and RIM-One v3) that included 139 glaucomatous and 161 nonglaucomatous cases were analyzed.
Sci Rep
January 2025
School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia.
Glaucoma poses a growing health challenge projected to escalate in the coming decades. However, current automated diagnostic approaches on Glaucoma diagnosis solely rely on black-box deep learning models, lacking explainability and trustworthiness. To address the issue, this study uses optical coherence tomography (OCT) images to develop an explainable artificial intelligence (XAI) tool for diagnosing and staging glaucoma, with a focus on its clinical applicability.
View Article and Find Full Text PDFPhotodiagnosis Photodyn Ther
January 2025
Department of Ophthalmology, Ankara Bilkent City Hospital, University of Health Sciences, Ankara, Turkey.
Purpose: In this study, it was planned to compare the macular ganglion cell analysis (GCA) and peripapillary retinal nerve fiber layer (pRNFL) of the patients with preperimetric glaucoma (PPG), early stage glaucoma (EG) and the control group.
Methods: This retrospective study included a total of 103 eyes: 38 from EG patients, 30 from PPG patients, and 35 from healthy individuals at Ankara Bilkent City Hospital Glaucoma Unit between January 2018 and September 2021. Eyes were categorized into control, PPG, and EG groups based on visual field (VF) classification.
Transl Vis Sci Technol
January 2025
Glaucoma Service, Wills Eye Hospital, Philadelphia, PA, USA.
Purpose: The integration of artificial intelligence (AI), particularly deep learning (DL), with optical coherence tomography (OCT) offers significant opportunities in the diagnosis and management of glaucoma. This article explores the application of various DL models in enhancing OCT capabilities and addresses the challenges associated with their clinical implementation.
Methods: A review of articles utilizing DL models was conducted, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), autoencoders, and large language models (LLMs).
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!