Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation

Abstract

Glaucoma is a leading cause of irreversible blindness. Accurate segmentation of the optic disc (OD) and cup (OC) from fundus images is beneficial to glaucoma screening and diagnosis. Recently, convolutional neural networks demonstrate promising progress in joint OD and OC segmentation. However, affected by the domain shift among different datasets, deep networks are severely hindered in generalizing across different scanners and institutions. In this paper, we present a novel patchbased Output Space Adversarial Learning framework (pOSAL) to jointly and robustly segment the OD and OC from different fundus image datasets. We first devise a lightweight and efficient segmentation network as a backbone. Considering the specific morphology of OD and OC, a novel morphology-aware segmentation loss is proposed to guide the network to generate accurate and smooth segmentation. Our pOSAL framework then exploits unsupervised domain adaptation to address the domain shift challenge by encouraging the segmentation in the target domain to be similar to the source ones. Since the whole-segmentationbased adversarial loss is insufficient to drive the network to capture segmentation details, we further design the pOSAL in a patch-based fashion to enable fine-grained discrimination on local segmentation details. We extensively evaluate our pOSAL framework and demonstrate its effectiveness in improving the segmentation performance on three public retinal fundus image datasets, i.e., Drishti-GS, RIM-ONE-r3, and REFUGE. Furthermore, our pOSAL framework achieved the first place in the OD and OC segmentation tasks in MICCAI 2018 Retinal Fundus Glaucoma Challenge.

IEEE Transactions on Medical Imaging (In press)

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation
• Random Erasing Data Augmentation
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Generalization via Invariant Feature Representation
• Optic Disc and Cup Segmentation Methods for Glaucoma Detection with Modification of U-Net Convolutional Neural Network
• Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image
• Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation
• Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
• Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation

Cited by in corpus (26)

• Domain Adaptation for Medical Image Analysis: A Survey
• REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
• ADAM Challenge: Detecting Age-related Macular Degeneration from Fundus Images
• Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation
• ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation
• Boundary and Entropy-driven Adversarial Learning for Fundus Image Segmentation
• HST-MRF: Heterogeneous Swin Transformer with Multi-Receptive Field for Medical Image Segmentation
• Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
• Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation
• Hierarchical Attention Networks for Medical Image Segmentation
• AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography
• Deep Mining External Imperfect Data for Chest X-ray Disease Screening
• Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation
• U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images of the Degenerated Retina
• Applications of Deep Learning in Fundus Images: A Review
• Perceptual-assisted Adversarial Adaptation for Choroid Segmentation in optical coherence tomography
• CADA: Multi-scale Collaborative Adversarial Domain Adaptation for Unsupervised Optic Disc and Cup Segmentation
• Leveraging Undiagnosed Data for Glaucoma Classification with Teacher-Student Learning
• Self-Adaptive Transfer Learning for Multicenter Glaucoma Classification in Fundus Retina Images
• Meta-learners for few-shot weakly-supervised optic disc and cup segmentation on fundus images
• Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models
• Unsupervised Domain Adaptation Network with Category-Centric Prototype Aligner for Biomedical Image Segmentation
• Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation
• Few-Shot Domain Adaptation with Polymorphic Transformers