medical-6

Retinal Vessel Segmentation

3260 papers • 126 benchmarks • 313 datasets

Retinal vessel segmentation is the task of segmenting vessels in retina imagery. ( Image credit: LadderNet )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in retinal-vessel-segmentation-12

Trend

Dataset

Best Model

Actions

DRIVE

CHASE_DB1

STARE

Libraries

i

Use these libraries to find retinal-vessel-segmentation-12 models and implementations

nikhilroxtomar/semantic-segmentatio…

2 papers 135

Datasets

HRF

Subtasks

No subtasks available.

Most implemented papers

U-Net: Convolutional Networks for Biomedical Image Segmentation

O. Ronneberger, T. Brox, P. Fischer•Sun May 17 2015

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

90626

Content

ROSE-1 SVC

ROSE-1 SVC-DVC

ROSE-1 DVC

ROSE-2

HRF

0

Paper Graph

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

Md. Zahangir Alom, T. Taha, C. Yakopcic, Mahmudul Hasan, V. Asari•Mon Feb 19 2018

A Recurrent Convolutional Neural Network (RCNN) based on U-Net as well as a Recurrent Residual convolutional neural Network (RRCNN), which are named RU-Net and R2U-Net respectively are proposed, which show superior performance on segmentation tasks compared to equivalent models including U-nets and residual U- net.

1190 0

Paper Graph

Dynamic Deep Networks for Retinal Vessel Segmentation

Aashis Khanal, Rolando Estrada•Mon Mar 18 2019

A stochastic training scheme for deep neural networks that robustly balances precision and recall is proposed, which makes a neural network more robust to inter-sample differences in class ratios, which will prove particularly effective for settings with sparse training data, such as medical image analysis.

54 0

Paper Graph

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

Juntang Zhuang•Tue Oct 16 2018

A LadderNet has more paths for information flow because of skip connections and residual blocks, and can be viewed as an ensemble of Fully Convolutional Networks (FCN), which improves segmentation accuracy and the shared weights within each residual block reduce parameter number.

259 0

Paper Graph

SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation

Changlu Guo, Marton Szemenyei, Yugen Yi, Wenle Wang, Buer Chen, Changqi Fan•Mon Apr 06 2020

A lightweight network named Spatial Attention U-Net (SA-UNet) that does not require thousands of annotated training samples and can be utilized in a data augmentation manner to use the available annotated samples more efficiently.

434 0

Paper Graph

Retinal Vessel Segmentation in Fundoscopic Images with Generative Adversarial Networks

Jaemin Son, S. Park, Kyu-Hwan Jung•Tue Jun 27 2017

This paper presents a method that generates the precise map of retinal vessels using generative adversarial training and achieves dice coefficient of 0.829 on DRIVE dataset and0.834 on STARE dataset which is the state-of-the-art performance on both datasets.

161 0

Paper Graph

Accurate Retinal Vessel Segmentation via Octave Convolution Neural Network

Zhun Fan, Jiajie Mo, Benzhang Qiu•Thu Jun 27 2019

The proposed method adopts octave convolution for learning multiple-spatial-frequency features, thus can better capture retinal vasculatures with varying sizes and shapes and achieves better or comparable performance to the state-of-the-art methods with fast processing speed.

37 0

Paper Graph

Retinal Vessel Segmentation based on Fully Convolutional Networks

•Thu Nov 21 2019

This work proposes a method for retinal vessel segmentation based on fully convolutional networks that shows superior performance compared to recent state-of-the-art methods.

6 0

Paper Graph

IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks

Yuta Nakashima, Liangzhi Li, Manisha Verma, H. Nagahara, R. Kawasaki•Wed Dec 11 2019

This work proposes IterNet, a new model based on UNet, with the ability to find obscured details of the vessel from the segmented vessel image itself, rather than the raw input image, to improve the performance of vessel segmentation.

280 0

Paper Graph

Channel Attention Residual U-Net for Retinal Vessel Segmentation

Wei Zhou, Changlu Guo, Marton Szemenyei, Yugen Yi•Mon Apr 06 2020

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.

63 0

Paper Graph

Adding a benchmark result helps the community track progress.