Automatic detection of the region of interest in corneal endothelium images using dense convolutional neural networks

Conference paper (2019)

Authors

J.P. Vigueras Guillén ImPhys/Quantitative Imaging , Rotterdam Ophthalmic Institute
Hans G. Lemij Rotterdam Eye Hospital
Jeroen G.J. van Rooij Rotterdam Eye Hospital
K.A. Vermeer Rotterdam Ophthalmic Institute, ImPhys/Quantitative Imaging
L.J. van Vliet ImPhys/Quantitative Imaging
Research Group
ImPhys/Quantitative Imaging
Copyright: © 2019 J.P. Vigueras Guillén, Hans G. Lemij, Jeroen Van Rooij, K.A. Vermeer, L.J. van Vliet
DOI
help_outline
https://doi.org/10.1117/12.2512641
Segmentation Biomarkers Dense U-net Fully CNN Specular microscopy
More Info
expand_more

Published Date

2019

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Research Group

ImPhys/Quantitative Imaging

Abstract

In images of the corneal endothelium (CE) acquired by specular microscopy, endothelial cells are commonly only visible in a part of the image due to varying contrast, mainly caused by challenging imaging conditions as a result of a strongly curved endothelium. In order to estimate the morphometric parameters of the corneal endothelium, the analyses need to be restricted to trustworthy regions - the region of interest (ROI) - where individual cells are discernible. We developed an automatic method to find the ROI by Dense U-nets, a densely connected network of convolutional layers. We tested the method on a heterogeneous dataset of 140 images, which contains a large number of blurred, noisy, and/or out of focus images, where the selection of the ROI for automatic biomarker extraction is vital. By using edge images as input, which can be estimated after retraining the same network, Dense U-net detected the trustworthy areas with an accuracy of 98.94% and an area under the ROC curve (AUC) of 0.998, without being affected by the class imbalance (9:1 in our dataset). After applying the estimated ROI to the edge images, the mean absolute percentage error (MAPE) in the estimated endothelial parameters was 0.80% for ECD, 3.60% for CV, and 2.55% for HEX.