Developing a Continuous Severity Scale for Macular Telangiectasia Type 2 Using Deep Learning and Implications for Disease Grading.

Journal: Ophthalmology
Published Date: Sep 20, 2023

Abstract

PURPOSE: Deep learning (DL) models have achieved state-of-the-art medical diagnosis classification accuracy. Current models are limited by discrete diagnosis labels, but could yield more information with diagnosis in a continuous scale. We developed a novel continuous severity scaling system for macular telangiectasia (MacTel) type 2 by combining a DL classification model with uniform manifold approximation and projection (UMAP).

Authors

  • Yue Wu
    Key Laboratory of Luminescence and Real-Time Analytical Chemistry (Ministry of Education), College of Pharmaceutical Sciences, Southwest University, Chongqing 400716, China.
  • Catherine Egan
    NIHR Biomedical Research Centre at Moorfields Eye Hospital and UCL Institute of Ophthalmology, London, UK.
  • Abraham Olvera-Barrios
    Medical Retina, Moorfields Eye Hospital NHS Foundation Trust, London, UK a.olvera@nhs.net.
  • Lea Scheppke
    Lowy Medical Research Institute, La Jolla, California; The Scripps Research Institute, La Jolla, California.
  • Tunde Peto
    Centre for Public Health, Queen's University Belfast, Belfast, United Kingdom.
  • Peter Charbel Issa
    Oxford Eye Hospital, Oxford University Hospitals National Health Service Foundation Trust, Oxford, United Kingdom.
  • Tjebo F C Heeren
    Moorfields Eye Hospital National Health Service Foundation Trust, London, United Kingdom.
  • Irene Leung
    Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom.
  • Anand E Rajesh
    Department of Ophthalmology, University of Washington, Seattle, Washington; The Roger and Angie Karalis Johnson Retina Center, Seattle, Washington.
  • Adnan Tufail
    London, United Kingdom. Electronic address: Adnan.Tufail@moorfields.nhs.uk.
  • Cecilia S Lee
    Department of Ophthalmology, University of Washington, Seattle, Washington, USA.
  • Emily Y Chew
    National Eye Institute, National Institutes of Health, Bethesda, Maryland. Electronic address: echew@nei.nih.gov.
  • Martin Friedlander
    Department of Molecular Medicine, The Scripps Research Institute, La Jolla, California, USA.
  • Aaron Y Lee
    Department of Ophthalmology, University of Washington, Seattle, Washington.

Keywords

External Resources

Popular Topics
Recent Journals