This research aims to develop a deep learning method for diagnosing vitreoretinal lymphoma compared to uveitis using optical coherence tomography (OCT).
Developed a deep learning model for OCT image analysis.
Applied the model to differentiate between vitreoretinal lymphoma and uveitis.
Evaluated model performance as a triage tool for surgical intervention.
The deep learning model successfully identified patients requiring pars plana vitrectomy.
Indicated potential for non-invasive diagnosis of vitreoretinal disorders.
Abstract
The proposed deep learning method may serve as a non-invasive triage tool by identifying patients who need confirmatory pars plana vitrectomy.