Automated Machine Learning versus Expert-Designed Models in Ocular Toxoplasmosis: Detection and Lesion Localization Using Fundus Images.

Journal: Ocular immunology and inflammation
Published Date: Nov 1, 2024

Abstract

PURPOSE: Automated machine learning (AutoML) allows clinicians without coding experience to build their own deep learning (DL) models. This study assesses the performance of AutoML in detecting and localizing ocular toxoplasmosis (OT) lesions in fundus images and compares it to expert-designed models.

Authors

  • Daniel Milad
    Faculty of Medicine, University of Montreal, Montreal, QC, Canada; Department of Ophthalmology, Centre Hospitalier de l'Université de Montréal, Montreal, QC, Canada.
  • Fares Antaki
    Department of Ophthalmology, University of Montreal, Montreal, QC H3T 1J4, Canada.
  • Allison Bernstein
    Department of Ophthalmology, Université de Montréal, Montreal, Québec, Canada.
  • Samir Touma
    Department of Ophthalmology, Université de Montréal, Montréal, QC, Canada.
  • Renaud Duval
    Department of Ophthalmology, University of Montreal, Montreal, QC H3T 1J4, Canada.

Keywords

External Resources

Popular Topics
Recent Journals