Optic Disc and Cup Image Segmentation Utilizing Contour-Based Transformation and Sequence Labeling Networks
- 20 March 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in Journal of Medical Systems
- Vol. 44 (5), 1-13
- https://doi.org/10.1007/s10916-020-01561-2
Abstract
Optic disc (OD) and optic cup (OC) segmentation are important steps for automatic screening and diagnosing of optic nerve head abnormalities such as glaucoma. Many recent works formulated the OD and OC segmentation as a pixel classification task. However, it is hard for these methods to explicitly model the spatial relations between the labels in the output mask. Furthermore, the proportion of the background, OD and OC are unbalanced which also may result in a biased model as well as introduce more noise. To address these problems, we developed an approach that follows a coarse-to-fine segmentation process. We start with a U-Net to obtain a rough segmenting boundary and then crop the area around the boundary to form a boundary contour centered image. Second, inspired by sequence labeling tasks in natural language processing, we regard the OD and OC segmentation as a sequence labeling task and propose a novel fully convolutional network called SU-Net and combine it with the Viterbi algorithm to jointly decode the segmentation boundary. We also introduced a geometric parameter-based data augmentation method to generate more training samples in order to minimize the differences between training and test sets and reduce overfitting. Experimental results show that our method achieved state-of-the-art results on 2 datasets for both OD and OC segmentation and our method outperforms most of the ophthalmologists in terms of achieving agreement out of 6 ophthalmologists on the MESSIDOR dataset for both OD and OC segmentation. In terms of glaucoma screening, we achieved the best cup-to-disc ratio (CDR) error and area under the ROC curve (AUC) for glaucoma classification on the Drishti-GS dataset.Keywords
Funding Information
- Ministry of Science and Technology of the People's Republic of China (2017YFC0112902)
This publication has 47 references indexed in Scilit:
- FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASEImage Analysis and Stereology, 2014
- Accurate and reliable segmentation of the optic disc in digital fundus imagesJournal of Medical Imaging, 2014
- Superpixel Classification Based Optic Disc and Optic Cup Segmentation for Glaucoma ScreeningIEEE Transactions on Medical Imaging, 2013
- Optic disc localization in retinal images using histogram matchingEURASIP Journal on Image and Video Processing, 2012
- Automated segmentation of the optic nerve head for diagnosis of glaucomaMedical Image Analysis, 2005
- Automated Optic Disc Localization and Contour Detection Using Ellipse Fitting and Wavelet TransformLecture Notes in Computer Science, 2004
- Boundary detection of optic disk by a modified ASM methodPattern Recognition, 2003
- Fast and robust optic disc detection using pyramidal decomposition and Hausdorff-based template matchingIEEE Transactions on Medical Imaging, 2001
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995
- Contrast Limited Adaptive Histogram EqualizationPublished by Elsevier BV ,1994