Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning

TL;DR

This paper introduces a two-stage deep learning framework for accurate optic disc localization and glaucoma classification in retinal images, achieving state-of-the-art results and emphasizing the importance of comprehensive performance evaluation.

Contribution

It proposes a novel two-stage deep learning approach combined with a semi-automatic ground truth generation method for improved optic disc detection and glaucoma classification.

Findings

Achieved 100% accuracy on four datasets for optic disc localization.

Improved glaucoma classification AUC to 0.874 on ORIGA dataset.

Highlighted the need for multiple metrics beyond AUC for performance assessment.

Abstract

With the advancement of powerful image processing and machine learning techniques, CAD has become ever more prevalent in all fields of medicine including ophthalmology. Since optic disc is the most important part of retinal fundus image for glaucoma detection, this paper proposes a two-stage framework that first detects and localizes optic disc and then classifies it into healthy or glaucomatous. The first stage is based on RCNN and is responsible for localizing and extracting optic disc from a retinal fundus image while the second stage uses Deep CNN to classify the extracted disc into healthy or glaucomatous. In addition to the proposed solution, we also developed a rule-based semi-automatic ground truth generation method that provides necessary annotations for training RCNN based model for automated disc localization. The proposed method is evaluated on seven publicly available datasets for disc localization and on ORIGA dataset, which is the largest publicly available dataset for glaucoma classification. The results of automatic localization mark new state-of-the-art on six datasets with accuracy reaching 100% on four of them. For glaucoma classification we achieved AUC equal to 0.874 which is 2.7% relative improvement over the state-of-the-art results previously obtained for classification on ORIGA. Once trained on carefully annotated data, Deep Learning based methods for optic disc detection and localization are not only robust, accurate and fully automated but also eliminates the need for dataset-dependent heuristic algorithms. Our empirical evaluation of glaucoma classification on ORIGA reveals that reporting only AUC, for datasets with class imbalance and without pre-defined train and test splits, does not portray true picture of the classifier's performance and calls for additional performance metrics to substantiate the results.