Share Email Print

Proceedings Paper

Convolutional neural network transfer for automated glaucoma identification
Author(s): José Ignacio Orlando; Elena Prokofyeva; Mariana del Fresno; Matthew B. Blaschko
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Most current systems for automated glaucoma detection in fundus images rely on segmentation-based features, which are known to be influenced by the underlying segmentation methods. Convolutional Neural Networks (CNNs) are powerful tools for solving image classification tasks as they are able to learn highly discriminative features from raw pixel intensities. However, their applicability to medical image analysis is limited by the non-availability of large sets of annotated data required for training. In this article we present results of analysis of the viability of using CNNs that are pre-trained from non-medical data for automated glaucoma detection. Two different CNNs, namely OverFeat and VGG-S, were applied to fundus images to generate feature vectors. Preprocessing techniques such as vessel inpainting, contrast-limited adaptive histogram equalization (CLAHE) or cropping around the optic nerve head (ONH) area were explored within this framework to evaluate the improvement in feature discrimination, combined with both ℓ1 and ℓ2 regularized logistic regression models. Results on the Drishti-GS1 dataset, evaluated in terms of area under the average ROC curve, suggests the viability of this approach and offer significant evidence of the importance of well-chosen image pre-processing for transfer learning when the amount of data is not sufficient for fine-tuning the network.

Paper Details

Date Published: 26 January 2017
PDF: 10 pages
Proc. SPIE 10160, 12th International Symposium on Medical Information Processing and Analysis, 101600U (26 January 2017); doi: 10.1117/12.2255740
Show Author Affiliations
José Ignacio Orlando, CONICET (Argentina)
Pladema Institute (Argentina)
Elena Prokofyeva, Scientific Institute of Public Health (Belgium)
Federal Agency for Medicines and Health Products (Belgium)
Mariana del Fresno, Pladema Institute (Argentina)
Comisión de Investigaciones Científicas de la Provincia de Buenos Aires (Argentina)
Matthew B. Blaschko, KU Leuven (Belgium)

Published in SPIE Proceedings Vol. 10160:
12th International Symposium on Medical Information Processing and Analysis
Eduardo Romero; Natasha Lepore; Jorge Brieva; Jorge Brieva; Ignacio Larrabide; , Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?