PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
May 15, 2026CureusOpen Access

Performance of Artificial Intelligence Systems for Automated Segmentation and Quantification of Retinal Fluid and Pathology in Optical Coherence Tomography Scans: A Systematic Review and Meta-Analysis

View Full Paper
Ask AI
Bookmark
Share

Authors

BABakhtawar AwanMEMohamed ElsaighMGMohamed Hesham Gamal

Discussion

Loading...

Member takes

Overview

Systematic review assesses AI performance in segmenting retinal pathology in optical coherence tomography images, suggesting potential clinical applications.

Key Points

  • This review evaluates the performance of AI systems in segmenting retinal fluid and pathology in OCT images compared to expert manual segmentations.
  • Conducted systematic review and meta-analysis of 16 diagnostic-accuracy studies over five years.
  • Searched databases: PubMed, Web of Science, Scopus; assessed study quality using QUADAS-2.
  • Analyzed data with random-effects model using Review Manager software version 5.4.
  • AI achieved expert-level Dice scores for subretinal fluid (0.88-0.96) and geographic atrophy (0.94).
  • Intraretinal fluid segmentation was more challenging with Dice scores of 0.79-0.89; volumetric reliability strong (ICCs > 0.94).
  • Processing times for AI ranged from 100 milliseconds to several seconds, indicating significant time savings over manual methods.

Cite This Study

Awan et al. (2026) studied this question.

synapsesocial.com/papers/6a06b74ce7dec685947aa37bhttps://doi.org/10.7759/cureus.108662
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1The PRISMA 2020 statement: An updated guideline for reporting systematic reviews2021 · 11,851 citations
  2. 2Age-Related Macular Degeneration Is the Leading Cause of Blindness . . .2004 · 694 citations
  3. 3QUADAS-2: A Revised Tool for the Quality Assessment of Diagnostic Accuracy Studies2011 · 14,447 citations
  4. 4Machine Learning-Based Automated Detection and Quantification of Geographic Atrophy and Hypertransmission Defects Using Spectral Domain Optical Coherence Tomography2022 · 29 citations
  5. 5Methodological Challenges of Deep Learning in Optical Coherence Tomography for Retinal Diseases: A Review2020 · 100 citations