DUNet: A deformable network for retinal vessel segmentation

Abstract

Automatic segmentation of retinal vessels in fundus images plays an important role in the diagnosis of some diseases such as diabetes and hypertension. In this paper, we propose Deformable U-Net (DUNet), which exploits the retinal vessels' local features with a U-shape architecture, in an end to end manner for retinal vessel segmentation. Inspired by the recently introduced deformable convolutional networks, we integrate the deformable convolution into the proposed network. The DUNet, with upsampling operators to increase the output resolution, is designed to extract context information and enable precise localization by combining low-level feature maps with high-level ones. Furthermore, DUNet captures the retinal vessels at various shapes and scales by adaptively adjusting the receptive fields according to vessels' scales and shapes. Three public datasets DRIVE, STARE and CHASE_DB1 are used to train and test our model. Detailed comparisons between the proposed network and the deformable neural network, U-Net are provided in our study. Results show that more detailed vessels are extracted by DUNet and it exhibits state-of-the-art performance for retinal vessel segmentation with a global accuracy of 0.9697/0.9722/0.9724 and AUC of 0.9856/0.9868/0.9863 on DRIVE, STARE and CHASE_DB1 respectively. Moreover, to show the generalization ability of the DUNet, we used another two retinal vessel data sets, one is named WIDE and the other is a synthetic data set with diverse styles, named SYNTHE, to qualitatively and quantitatively analyzed and compared with other methods. Results indicates that DUNet outperforms other state-of-the-arts.

References in corpus (5)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Retinal Vessel Segmentation Using the 2-D Morlet Wavelet and Supervised Classification
• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
• Ensemble of Deep Convolutional Neural Networks for Learning to Detect Retinal Vessels in Fundus Images
• A Labeling-Free Approach to Supervising Deep Neural Networks for Retinal Blood Vessel Segmentation

Cited by in corpus (49)

• U-Net and its variants for medical image segmentation: theory and applications
• RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans
• RV-GAN: Segmenting Retinal Vascular Structure in Fundus Photographs using a Novel Multi-scale Generative Adversarial Network
• ELEMENT: Multi-Modal Retinal Vessel Segmentation Based on a Coupled Region Growing and Machine Learning Approach
• GT U-Net: A U-Net Like Group Transformer Network for Tooth Root Segmentation
• Leveraging Regular Fundus Images for Training UWF Fundus Diagnosis Models via Adversarial Learning and Pseudo-Labeling
• Simultaneous segmentation and classification of the retinal arteries and veins from color fundus images
• IterMiUnet: A lightweight architecture for automatic blood vessel segmentation
• SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation
• CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging
• Segmenting Transparent Object in the Wild with Transformer
• EOCSA: Predicting Prognosis of Epithelial Ovarian Cancer with Whole Slide Histopathological Images
• Medical Image Segmentation Using Squeeze-and-Expansion Transformers
• DPN: Detail-Preserving Network with High Resolution Representation for Efficient Segmentation of Retinal Vessels
• Evolutionary Neural Architecture Search for Retinal Vessel Segmentation
• Deep Learning Methods for Retinal Blood Vessel Segmentation: Evaluation on Images with Retinopathy of Prematurity
• RRWNet: Recursive Refinement Network for effective retinal artery/vein segmentation and classification
• ROSE: A Retinal OCT-Angiography Vessel Segmentation Dataset and New Model
• OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation
• Deep Dilated Convolutional Nets for the Automatic Segmentation of Retinal Vessels
• Joint Learning of Vessel Segmentation and Artery/Vein Classification with Post-processing
• Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation
• Hierarchical Attention Networks for Medical Image Segmentation
• Segmenting Transparent Objects in the Wild
• FakeMix Augmentation Improves Transparent Object Detection
• An Analysis of the Influence of Transfer Learning When Measuring the Tortuosity of Blood Vessels
• Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation
• Blindness (Diabetic Retinopathy) Severity Scale Detection
• Local-sensitive connectivity filter (ls-cf): A post-processing unsupervised improvement of the frangi, hessian and vesselness filters for multimodal vessel segmentation
• Channel Attention Residual U-Net for Retinal Vessel Segmentation
• Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation
• HybridNetSeg: A Compact Hybrid Network for Retinal Vessel Segmentation
• Universal Vessel Segmentation for Multi-Modality Retinal Images
• Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
• Multimodal Transfer Learning-based Approaches for Retinal Vascular Segmentation
• A Thickness Sensitive Vessel Extraction Framework for Retinal and Conjunctival Vascular Tortuosity Analysis
• Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation
• On the Evaluation and Real-World Usage Scenarios of Deep Vessel Segmentation for Retinography
• Automatic Lumbar Spinal CT Image Segmentation with a Dual Densely Connected U-Net
• The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation
• The Application of Deep Learning for Lymph Node Segmentation: A Systematic Review
• DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactions
• BEFD: Boundary Enhancement and Feature Denoising for Vessel Segmentation
• Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World
• OMSN and FAROS: OCTA Microstructure Segmentation Network and Fully Annotated Retinal OCTA Segmentation Dataset
• Cell image segmentation by Feature Random Enhancement Module
• Analysis of Macula on Color Fundus Images Using Heightmap Reconstruction Through Deep Learning
• Image Magnification Network for Vessel Segmentation in OCTA Images
• AOSLO-net: A deep learning-based method for automatic segmentation of retinal microaneurysms from adaptive optics scanning laser ophthalmoscope images