Share Email Print

Proceedings Paper

Deep learning for objective OCTA detection of diabetic retinopathy
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Early detection of diabetic retinopathy (DR) is an essential step to prevent vision losses. This study is the first effort to explore convolutional neural networks (CNNs) for transfer-learning based optical coherence tomography angiography (OCTA) detection and classification of DR. We employed transfer-learning using a pre-trained CNN, VGG16, based on the ImageNet dataset for classification of OCTA images. To prevent overfitting, data augmentation, e.g. rotations, flips, and zooming, and 5-fold cross-validation were implemented. A dataset comprising of 131 OCTA images from 20 control, 17 diabetic patients without DR (NoDR), and 60 nonproliferative DR (NPDR) patients were used for preliminary validation. Best classification performance was achieved with fine-tuning nine layers of the sixteen-layer CNN model.

Paper Details

Date Published: 19 February 2020
PDF: 6 pages
Proc. SPIE 11218, Ophthalmic Technologies XXX, 112181P (19 February 2020); doi: 10.1117/12.2546586
Show Author Affiliations
David Le, Univ. of Illinois at Chicago (United States)
Minhaj Nur Alam, Univ. of Illinois at Chicago (United States)
Jennifer I. Lim, Univ. of Illinois at Chicago (United States)
R. V. P. Chan, Univ. of Illinois at Chicago (United States)
Xincheng Yao, Univ. of Illinois at Chicago (United States)

Published in SPIE Proceedings Vol. 11218:
Ophthalmic Technologies XXX
Fabrice Manns; Arthur Ho; Per G. Söderberg, 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?