AI Article Synopsis

  • Reticular pseudodrusen (RPD) are a key factor in vision loss related to age-related macular degeneration (AMD), making their detection essential for effective clinical management.
  • Researchers created a deep learning model that segments RPD from a dataset of 9,800 optical coherence tomography scans, achieving better agreement with retinal specialists compared to their own consensus.
  • The model demonstrated high performance in detecting RPD across multiple test datasets, matching the accuracy of experienced specialists, and is now publicly accessible for use.

Article Abstract

Reticular pseudodrusen (RPD) signify a critical phenotype driving vision loss in age-related macular degeneration (AMD). Their detection is paramount in the clinical management of those with AMD, yet they remain challenging to reliably identify. We thus developed a deep learning (DL) model to segment RPD from 9,800 optical coherence tomography B-scans, and this model produced RPD segmentations that had higher agreement with four retinal specialists (Dice similarity coefficient [DSC]=0·76 [95% confidence interval [CI] 0·71-0·81]) than the agreement amongst the specialists (DSC=0·68, 95% CI=0·63-0·73; <0·001). In five external test datasets consisting of 1,017 eyes from 812 individuals, the DL model detected RPD with a similar level of performance as two retinal specialists (area-under-the-curve of 0·94 [95% CI=0·92-0·97], 0·95 [95% CI=0·92-0·97] and 0·96 [95% CI=0·94-0·98] respectively; ≥0·32). This DL model enables the automatic detection and quantification of RPD with expert-level performance, which we have made publicly available.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11419239PMC
http://dx.doi.org/10.1101/2024.09.11.24312817DOI Listing

Publication Analysis

Top Keywords

reticular pseudodrusen
8
age-related macular
8
macular degeneration
8
optical coherence
8
coherence tomography
8
deep learning-based
4
learning-based detection
4
detection reticular
4
pseudodrusen age-related
4
degeneration optical
4

Similar Publications

Stage 1 Extensive Macular Atrophy with Pseudodrusen-Like Appearance Complicated by Multiple Evanescent White Dot Syndrome-Like Reaction.

Ocul Immunol Inflamm

December 2024

Harvard Retinal Imaging Lab, Retina Service, Department of Ophthalmology, Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachusetts, USA.

Purpose: To describe a case of early-stage Extensive Macular Atrophy with Pseudodrusen-like appearance (EMAP) presenting with acute monocular loss and atypical retinal lesions suggestive of posterior uveitis.

Methods: Case report with longitudinal follow-up including visual field testing and multimodal imaging.

Results: A 53-year-old woman presented with sudden vision loss in her right eye (RE).

View Article and Find Full Text PDF

Purpose: With the widespread availability of ultrawide field imaging, peripheral retinal abnormalities in age-related macular degeneration (AMD) have garnered attention. However, longitudinal studies on AMD peripheral findings are limited. This study aims to characterize and quantify these features over five years.

View Article and Find Full Text PDF

Purpose: To evaluate the relationship between the presence of reticular pseudodrusen (RPD) and the risk allele of ARMS2 rs10490924 variation in dry-AMD patients by using multimodal imaging. Also, to compare patients with and without RPD and healthy volunteers according to the distribution of the risk allele.

Methods: In this cross-sectional study, dry-AMD patients with (Group A, n = 50) and without (Group B, n = 50) RPD and healthy volunteers (Group C, n = 50) were enrolled.

View Article and Find Full Text PDF

Type 3 Macular Neovascularization in Age-related Macular Degeneration: Baseline Predictors of 3-Year Macular Atrophy Development.

Ophthalmol Retina

November 2024

School of Medicine, Vita-Salute San Raffaele University, Milan, Italy; Division of Head and Neck, Ophthalmology Unit, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), San Raffaele Scientific Institute, Milan, Italy. Electronic address:

Purpose: To identify baseline OCT predictors of the 3-year macular atrophy (MA) development for type 3 (T3) macular neovascularization (MNV) secondary to neovascular age-related macular degeneration (nAMD) treated by anti-VEGF therapy.

Design: Multicenter, retrospective, longitudinal study.

Participants: We included patients with treatment-naive T3 MNV secondary to nAMD at baseline, treated with anti-VEGF during a 3-year follow-up.

View Article and Find Full Text PDF

A high-fat plus high-sucrose diet induces age-related macular degeneration in an experimental rabbit model.

Dis Model Mech

November 2024

Department of Ophthalmology, Research Laboratory of Ophthalmology and Vision Sciences, Eye Research Institute, West China Hospital, Sichuan University, Chengdu 610041, China.

Article Synopsis
  • Age-related macular degeneration (AMD) is a major cause of blindness, influenced by metabolic disorders and dietary choices.
  • A study investigated the effects of different diets (normal, high-fat, high-sucrose, and a combination of high-fat and high-sucrose) on lipid profiles and retinal health in male Chinchilla rabbits over 6 months.
  • Findings revealed that the combination diet induced significant retinal damage, such as reticular pseudodrusen, without causing obesity, suggesting that these rabbits are a suitable model for studying early AMD.
View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!