Meesam Abbas

RESEARCH PAPER

Publication

Weakly Supervised Optic Disc and Cup Segmentation Using Pseudo Labels for Automated Glaucoma Analysis

UnderReview in AI MDPI JOUNRAL

Overview:

Developed a weakly supervised deep learning framework for optic disc and cup segmentation using unlabelled retinal fundus images (~9,000 samples). The pipeline combines heuristic computer vision–based pseudo-label generation with geometric quality control to mitigate annotation scarcity. A U-Net model trained with noise-robust loss functions demonstrates strong zero-shot generalization on external datasets, enabling reliable vertical cup-to-disc ratio (vCDR) estimation for glaucoma screening.

Abstract:

Glaucoma is a leading cause of irreversible blindness worldwide, where early detection relies heavily on morphological assessment of the optic nerve head, particularly the vertical Cup-to-Disc Ratio (vCDR). Although deep learning-based segmentation methods have demonstrated strong performance, their dependence on expert pixel-level annotations limits scalability and clinical deployment. In this work, we propose an anatomically guided weakly supervised framework for optic disc and optic cup segmentation that eliminates the need for manual masks. Anatomically plausible pseudo-labels are automatically generated from unannotated retinal fundus images and filtered using physiological quality control criteria to construct a reliable silver-standard training set. The source code and detailed results are available at GitHub

Page updated

Google Sites

Report abuse