Optic disc and optic cup segmentation based on anatomy guided cascade network. (December 2020)

• Record Type: Journal Article
• Authors: Bian, Xuesheng; Luo, Xiongbiao; Wang, Cheng; Liu, Weiquan; Lin, Xiuhong
• Is Part Of: Computer methods and programs in biomedicine. Volume 197(2020)
• Publication Date: 2020-12
• Subjects: Glaucoma -- Segmentation -- Attention -- Generative adversarial learning; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105717
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We propose introducing the anatomical knowledge of the optic disc and optic cup into a novel end-to-end cascade network architecture to segment small targets, via an attention mechanism, which trains rapidly from the start of training to convergence. To refine the prediction, instead of post-processing, we propose segmenting the optic disc and optic cup with generative adversarial learning, which uses fully labels generated by the elliptical fitting provided in the training dataset and voids the non-elliptical fitting error in real fundus images. The network framework proposed in this paper obtained state-of-the-art results in the MICCAI 2018 Retinal Fundus Glaucoma Challenge. Abstract: Background and Objective: Glaucoma, a worldwide eye disease, may cause irreversible vision damage. If not treated properly at an early stage, glaucoma eventually deteriorates into blindness. Various glaucoma screening methods, e.g. Ultrasound Biomicroscopy (UBM), Optical Coherence Tomography (OCT), and Heidelberg Retinal Scanner (HRT), are available. However, retinal fundus image photography examination, because of its low cost, is one of the most common solutions used to diagnose glaucoma. Clinically, the cup-to-disk ratio is an important indicator in glaucoma diagnosis. Therefore, precise fundus image segmentation to calculate the cup-to-disk ratio is the basis for screening glaucoma. Methods: In this paper, we propose a deep neural network that uses anatomical knowledge to guide the segmentation of fundus images, which accurately segments the optic cup and the optic disc in a fundus image to accurately calculate the cup-to-disk ratio. Optic disc and optic cup segmentation are typical small target segmentation problems in biomedical images. We propose to use an attention-based cascade network to effectively accelerate the convergence of small target segmentation during training and accurately reserve detailed contours of small targets. Results: Our method, which was validated in the MICCAI REFUGE fundus image segmentation competition, achieves 93.31% dice score in optic disc segmentation and 88.04% dice score in optic cup segmentation. Moreover, we win a high CDR evaluation score, which is useful for glaucoma screening. Conclusions: The proposed method successfully introduce anatomical knowledge into segmentation task, and achieve state-of-the-art performance in fundus image segmentation. It also can be used for both automatic segmentation and semiautomatic segmentation with human interaction.