Pathological myopia classification with simultaneous lesion segmentation using deep learning
Authors:
- Ruben HemelingsRHRuben Hemelings
- Ingeborg StalmansISIngeborg Stalmans
- Patrick De BoeverPBPatrick De Boever
Preprint
Abstract
This investigation reports on the results of convolutional neural networks developed for the recently introduced PathologicAL Myopia (PALM) dataset, which consists of 1200 fundus images. We propose a new Optic Nerve Head (ONH)-based prediction enhancement for the segmentation of atrophy and fovea. Models trained with 400 available training images achieved an AUC of 0.9867 for pathological myopia classification, and a Euclidean distance of 58.27 pixels on the fovea localization task, evaluated on a test set of 400 images. Dice and F1 metrics for semantic segmentation of lesions scored 0.9303 and 0.9869 on optic disc, 0.8001 and 0.9135 on retinal atrophy, and 0.8073 and 0.7059 on retinal detachment, respectively. Our work was acknowledged with an award in the context of the "PathologicAL Myopia detection from retinal images" challenge held during the IEEE International Symposium on Biomedical Imaging (April 2019). Considering that (pathological) myopia cases are often identified as false positives and negatives in classification systems for glaucoma, we envision that the current work could aid in future research to discriminate between glaucomatous and highly-myopic eyes, complemented by the localization and segmentation of landmarks such as fovea, optic disc and atrophy.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographsMedical Image Analysis, 2020
- Development and Validation of a Deep Learning System to Detect Glaucomatous Optic Neuropathy Using Fundus PhotographsJAMA Ophthalmology, 2019
- Semi-supervised Segmentation of Salt Bodies in Seismic Images Using an Ensemble of Convolutional Neural Networks2019
- Artery–vein segmentation in fundus images using a fully convolutional networkComputerized Medical Imaging and Graphics, 2019
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Lamina cribrosa depth according to the level of axial length in normal and glaucomatous eyesGraefe's Archive for Clinical and Experimental Ophthalmology, 2015
- Influence of Refractive Error on Optic Disc Topographic Parameters: The Singapore Malay Eye StudyAmerican Journal of Ophthalmology, 2011
- Refractive Errors in an Elderly Japanese PopulationOphthalmology, 2008