Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image

Abstract

Glaucoma is a chronic eye disease that leads to irreversible vision loss. Most of the existing automatic screening methods firstly segment the main structure, and subsequently calculate the clinical measurement for detection and screening of glaucoma. However, these measurement-based methods rely heavily on the segmentation accuracy, and ignore various visual features. In this paper, we introduce a deep learning technique to gain additional image-relevant information, and screen glaucoma from the fundus image directly. Specifically, a novel Disc-aware Ensemble Network (DENet) for automatic glaucoma screening is proposed, which integrates the deep hierarchical context of the global fundus image and the local optic disc region. Four deep streams on different levels and modules are respectively considered as global image stream, segmentation-guided network, local disc region stream, and disc polar transformation stream. Finally, the output probabilities of different streams are fused as the final screening result. The experiments on two glaucoma datasets (SCES and new SINDI datasets) show our method outperforms other state-of-the-art algorithms.

arXiv commentProject homepage: https://hzfu.github.io/proj_glaucoma_fundus.html , and Accepted by IEEE Transactions on Medical Imaging

References in corpus (1)

• Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation

Cited by in corpus (16)

• Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation
• Evaluation of Retinal Image Quality Assessment Networks in Different Color-spaces
• DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
• Application of Deep Learning in Fundus Image Processing for Ophthalmic Diagnosis -- A Review
• SDFN: Segmentation-based Deep Fusion Network for Thoracic Disease Classification in Chest X-ray Images
• Deep learning on fundus images detects glaucoma beyond the optic disc
• VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers
• Angle-Closure Detection in Anterior Segment OCT based on Multi-Level Deep Network
• ADAM Challenge: Detecting Age-related Macular Degeneration from Fundus Images
• Leveraging Regular Fundus Images for Training UWF Fundus Diagnosis Models via Adversarial Learning and Pseudo-Labeling
• Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks
• GS-Net: Global Self-Attention Guided CNN for Multi-Stage Glaucoma Classification
• U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images of the Degenerated Retina
• Rapid Classification of Glaucomatous Fundus Images
• Label uncertainty-guided multi-stream model for disease screening
• Soft Dice Confidence: A Near-Optimal Confidence Estimator for Selective Prediction in Semantic Segmentation