Conexiant
Login
  • Corneal Physician
  • Glaucoma Physician
  • New Retinal Physician
  • Ophthalmology Management
  • Ophthalmic Professional
  • Presbyopia Physician
  • Retinal Physician
The Ophthalmologist
  • Explore

    Explore

    • Latest
    • Insights
    • Case Studies
    • Opinion & Personal Narratives
    • Research & Innovations
    • Product Profiles

    Featured Topics

    • Anterior Segment
    • Glaucoma
    • Retina

    Issues

    • Latest Issue
    • Archive
  • Subspecialties
    • Cataract
    • Cornea
    • Glaucoma
    • Neuro-ophthalmology
    • Oculoplastics
    • Optometry
    • Pediatric
    • Retina
  • Business

    Business & Profession

    • Professional Development
    • Business and Entrepreneurship
    • Practice Management
    • Health Economics & Policy
  • Training & Education

    Career Development

    • Professional Development
    • Career Pathways

    Events

    • Webinars
    • Live Events
  • Events
    • Live Events
    • Webinars
  • Community

    People & Profiles

    • Power List
    • Voices in the Community
    • Authors & Contributors
  • Multimedia
    • Video
    • Podcasts
Subscribe
Subscribe

False

Advertisement
The Ophthalmologist / Issues / 2025 / Apr / Deep Learning for Retinal Anomalies

Deep Learning for Retinal Anomalies

System can detect retinal anomalies without pathological labels

By The Ophthalmologist 4/10/2025 3 min read

Share

0425005-AI-news-Deep-Learning-for-Retinal-Anomalies.png

Credit: Adobestock.com

A new TVST study has introduced an unsupervised deep learning system capable of detecting anomalies in retinal OCT scans – without requiring any labeled pathological data. Developed by researchers at the Medical University of Vienna, the AI model leverages knowledge distillation to distinguish between healthy and abnormal retinal structures, offering a promising tool for automated screening of a diverse range of eye diseases.

The method is based on a teacher-student neural network framework. The “teacher” model, pretrained on natural images, guides a smaller “student” model, which learns to replicate the teacher’s outputs, but only using normal retinal OCT scans. At test time, deviations between the two models’ responses highlight anomalous regions, generating both anomaly scores and heatmaps that point to abnormal structures in the retina.

The system was trained and tested on a large in-house dataset of 3,247 OCT volumes, including a wide range of retinal diseases, such as diabetic macular edema (DME), age-related macular degeneration (AMD), Stargardt disease, and retinal vein occlusion (RVO). An average area under the curve (AUC) of 0.94 was achieved for detecting anomalous volumes, with particularly strong performance in diseases involving retinal deformation or fluid accumulation.

When tested on external public datasets (RETOUCH and Kermany), the model also performed well, with AUCs ranging from 0.81 to 0.87 at the B-scan level. Importantly, anomaly scores correlated strongly with disease severity, and the AI-generated maps successfully highlighted diagnostically relevant areas in the scans.

The authors believe this system could significantly reduce the workload of clinicians by better identifying slices of diagnostic relevance. The system’s explainability – via heatmaps that visualize abnormalities – also enhances clinical trust and integration. Unlike traditional AI systems that require thousands of labeled examples, this unsupervised approach only needs healthy data, making it scalable and adaptable for real-world settings. And while the system doesn’t yet identify specific diseases, and struggles with some large fluid regions, it represents a major step toward efficient, general-purpose OCT screening tools.

About the Author(s)

The Ophthalmologist

More Articles by The Ophthalmologist

Related Content

Newsletters

Receive the latest Ophthalmology news, personalities, education, and career development – weekly to your inbox.

Newsletter Signup Image

False

Advertisement

False

Advertisement

Explore More in Ophthalmology

Dive deeper into the world of Ophthalmology. Explore the latest articles, case studies, expert insights, and groundbreaking research.

False

Advertisement
The Ophthalmologist
Subscribe

About

  • About Us
  • Work at Conexiant Europe
  • Terms and Conditions
  • Privacy Policy
  • Advertise With Us
  • Contact Us

Copyright © 2025 Texere Publishing Limited (trading as Conexiant), with registered number 08113419 whose registered office is at Booths No. 1, Booths Park, Chelford Road, Knutsford, England, WA16 8GS.

Disclaimer

The Ophthalmologist website is intended solely for the eyes of healthcare professionals. Please confirm below: