Angle-Closure Detection in Anterior Segment OCT based on Multi-Level Deep Network

Abstract

Irreversible visual impairment is often caused by primary angle-closure glaucoma, which could be detected via Anterior Segment Optical Coherence Tomography (AS-OCT). In this paper, an automated system based on deep learning is presented for angle-closure detection in AS-OCT images. Our system learns a discriminative representation from training data that captures subtle visual cues not modeled by handcrafted features. A Multi-Level Deep Network (MLDN) is proposed to formulate this learning, which utilizes three particular AS-OCT regions based on clinical priors: the global anterior segment structure, local iris region, and anterior chamber angle (ACA) patch. In our method, a sliding window based detector is designed to localize the ACA region, which addresses ACA detection as a regression task. Then, three parallel sub-networks are applied to extract AS-OCT representations for the global image and at clinically-relevant local regions. Finally, the extracted deep features of these sub-networks are concatenated into one fully connected layer to predict the angle-closure detection result. In the experiments, our system is shown to surpass previous detection methods and other deep learning systems on two clinical AS-OCT datasets.

9 pages, accepted by IEEE Transactions on Cybernetics

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Learning in Neural Networks: An Overview
• Conditional Random Fields as Recurrent Neural Networks
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation
• Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image
• Deep Learning for Generic Object Detection: A Survey
• YoTube: Searching Action Proposal via Recurrent and Static Regression Networks
• Person Re-Identification by Semantic Region Representation and Topology Constraint

Cited by in corpus (5)

• A Survey on Deep Learning of Small Sample in Biomedical Image Analysis
• AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography
• Open-Narrow-Synechiae Anterior Chamber Angle Classification in AS-OCT Sequences
• Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image
• Reconstruction and Quantification of 3D Iris Surface for Angle-Closure Glaucoma Detection in Anterior Segment OCT