Translator Disclaimer
15 March 2019 Computerized assessment of glaucoma severity based on color fundus images
Author Affiliations +
Abstract
In this study, the deep learning technology was used to grade the severity of glaucoma depicted on color fundus images. We retrospectively collected a dataset of 5,978 fundus images acquired on different subjects and their glaucoma severities were annotated as none, mild, moderate, or severe, respectively, by the consensus of two experienced ophthalmologists. These images were preprocessed to generate global and local regions of interest (ROIs), namely the global field-of-view images and the local disc region images. These ROIs were separately fed into eight classical convolutional neural networks (CNNs) (i.e., VGG16, VGG19, ResNet, DenseNet, InceptionV3, InceptionResNet, Xception, and NASNetMobile) for classification purposes. Experimental results demonstrated that the available CNNs, except VGG16 and VGG19, achieved average quadratic kappa scores of 80.36% and 78.22% when trained from scratch on global and local ROIs, and 85.29% and 82.72% when fine-tuned using the imagenet weights, respectively. VGG16 and VGG19 achieved reasonable accuracy when trained from scratch, but they failed when using imagenet weights for both global and local ROIs. Among these CNNs, DenseNet had the highest classification accuracy (i.e., 75.50%) based on pre-trained weights when using global images, as compared to 65.50% when using local optic disc images.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lei Wang, Han Liu, Jian Zhang, Hang Chen, and Jiantao Pu "Computerized assessment of glaucoma severity based on color fundus images", Proc. SPIE 10953, Medical Imaging 2019: Biomedical Applications in Molecular, Structural, and Functional Imaging, 1095322 (15 March 2019); https://doi.org/10.1117/12.2510446
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

High-accurate and noise-tolerant texture descriptor
Proceedings of SPIE (February 13 2015)
Coarse-to-fine strategy for motion estimation
Proceedings of SPIE (December 16 1993)
Automatic inspection of leather surfaces
Proceedings of SPIE (October 02 1994)

Back to Top