Channel Attention Residual U-Net for Retinal Vessel Segmentation (2020-04-07T00:00:00.000000Z)

TL;DR

This work proposes a new deep learning model, namely Channel Attention Residual U-Net (CAR-UNet), to accurately segment retinal vascular and non-vascular pixels, and introduced a novel Modified Efficient Channel Attention (MECA) to enhance the discriminative ability of the network by considering the interdependence between feature maps.

Abstract

Retinal vessel segmentation is a vital step for the diagnosis of many early eye-related diseases. In this work, we propose a new deep learning model, namely Channel Attention Residual U-Net (CAR-UNet), to accurately segment retinal vascular and non-vascular pixels. In this model, we introduced a novel Modified Efficient Channel Attention (MECA) to enhance the discriminative ability of the network by considering the interdependence between feature maps. On the one hand, we apply MECA to the "skip connections" in the traditional U-shaped networks, instead of simply copying the feature maps of the contracting path to the corresponding expansive path. On the other hand, we propose a Channel Attention Double Residual Block (CADRB), which integrates MECA into a residual structure as a core structure to construct the proposed CAR-UNet. The results show that our proposed CAR-UNet has reached the state-of-the-art performance on three publicly available retinal vessel datasets: DRIVE, CHASE DB1 and STARE.

Authors

Wei Zhou

2 papers

Changlu Guo

2 papers

Marton Szemenyei

2 papers

TL;DR

Abstract

Authors

References27 items

CABNet: Category Attention Block for Imbalanced Diabetic Retinopathy Grading

Dense Residual Network for Retinal Vessel Segmentation

Dense Dilated Network With Probability Regularized Walk for Vessel Detection

CS-Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation

Dual Encoding U-Net for Retinal Vessel Segmentation

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

RCA-U-Net: Residual Channel Attention U-Net for Fast Tissue Quantification in Magnetic Resonance Fingerprinting

SD-Unet: A Structured Dropout U-Net for Retinal Vessel Segmentation

VesselNet: A deep convolutional neural network with multi pathways for robust hepatic vessel segmentation

DUNet: A deformable network for retinal vessel segmentation

DropBlock: A regularization method for convolutional networks

LadderNet: Multi-path networks based on U-Net for medical image segmentation

Multiscale Network Followed Network Model for Retinal Vessel Segmentation

CBAM: Convolutional Block Attention Module

Deep supervision with additional labels for retinal vessel segmentation task

Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation

Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation

Squeeze-and-Excitation Networks

DeepVessel: Retinal Vessel Segmentation via Deep Learning and Conditional Random Field

Identity Mappings in Deep Residual Networks

Deep Residual Learning for Image Recognition

U-Net: Convolutional Networks for Biomedical Image Segmentation

An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation

Fast Retinal Vessel Detection and Measurement Using Wavelets and Edge Location Refinement

FABC: Retinal Vessel Segmentation Using AdaBoost

Ridge-based vessel segmentation in color images of the retina

Fine particles, thin films and exchange anisotropy, in Magnetism

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names