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

05/28/2020
by   Muhammad Naseer Bajwa, et al.
18

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 equal to 0.874 which is 2.7 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.

READ FULL TEXT

page 1

page 3

page 7

page 8

page 11

page 13

research
10/01/2020

Utilizing Transfer Learning and a Customized Loss Function for Optic Disc Segmentation from Retinal Images

Accurate segmentation of the optic disc from a retinal image is vital to...
research
10/14/2019

Vertebrae Detection and Localization in CT with Two-Stage CNNs and Dense Annotations

We propose a new, two-stage approach to the vertebrae centroid detection...
research
07/21/2017

Retinal Microaneurysms Detection using Local Convergence Index Features

Retinal microaneurysms are the earliest clinical sign of diabetic retino...
research
07/28/2022

Automated Classification of Nanoparticles with Various Ultrastructures and Sizes

Accurately measuring the size, morphology, and structure of nanoparticle...
research
01/29/2018

Deep Learning based Retinal OCT Segmentation

Our objective is to evaluate the efficacy of methods that use deep learn...
research
12/10/2021

Deep Learning based Framework for Automatic Diagnosis of Glaucoma based on analysis of Focal Notching in the Optic Nerve Head

Automatic evaluation of the retinal fundus image is emerging as one of t...
research
03/18/2022

SHREC 2021: Classification in cryo-electron tomograms

Cryo-electron tomography (cryo-ET) is an imaging technique that allows t...

Please sign up or login with your details

Forgot password? Click here to reset