A framework for retinal vessel segmentation from fundus images using hybrid feature set and hierarchical classification

Retinal vessels are the only deep micro vessels that can be observed in human body, the accurate identification of which has great significance on the diagnosis of hypertension, diabetes and other diseases. To this end, a retinal vessel segmentation algorithm based on residual convolution neural network is proposed according to the characteristics of the retinal vessels on fundus images. Improved residual attention module and deep supervision module are utilized, in which the low-level and high-level feature graphs are joined to construct the encoder-decoder network structure, and atrous convolution is introduced to the pyramid pooling. The experiments result on the fundus image data set DRIVE and STARE show that this algorithm can obtain complete retinal vessel segmentation as well as connected vessel stems and terminals. The average accuracy on DRIVE and STARE reaches 95.90 and 96.88%, and the average specificity is 98.85 and 97.85%, which shows superior performance compared to other methods. This algorithm is verified feasible and effective for retinal vessel segmentation of fundus images and has the ability to detect more capillaries.

Download Full-text

An Ensemble Retinal Vessel Segmentation Based on Supervised Learning in Fundus Images

Chinese Journal of Electronics ◽

10.1049/cje.2016.05.016 ◽

2016 ◽

Vol 25 (3) ◽

pp. 503-511 ◽

Cited By ~ 12

Author(s):

Chengzhang Zhu ◽

Beiji Zou ◽

Jinkai Cui ◽

Yao Xiang ◽

Hui Wu

Keyword(s):

Supervised Learning ◽

Retinal Vessel ◽

Vessel Segmentation ◽

Fundus Images ◽

Retinal Vessel Segmentation

Download Full-text

A Review on Recent Developments for the Retinal Vessel Segmentation Methodologies and Exudate Detection in Fundus Images Using Deep Learning Algorithms

Computational Vision and Bio-Inspired Computing - Advances in Intelligent Systems and Computing ◽

10.1007/978-3-030-37218-7_143 ◽

2020 ◽

pp. 1363-1370

Author(s):

Silpa Ajith Kumar ◽

J. Satheesh Kumar

Keyword(s):

Deep Learning ◽

Learning Algorithms ◽

Retinal Vessel ◽

Vessel Segmentation ◽

Fundus Images ◽

Recent Developments ◽

Retinal Vessel Segmentation

Download Full-text

Real-Time Retinal Vessel Segmentation on High-Resolution Fundus Images Using Laplacian Pyramids

Image and Video Technology - Lecture Notes in Computer Science ◽

10.1007/978-3-030-34879-3_26 ◽

2019 ◽

pp. 337-350 ◽

Cited By ~ 2

Author(s):

Robert Dachsel ◽

Annika Jöster ◽

Michael Breuß

Keyword(s):

High Resolution ◽

Real Time ◽

Retinal Vessel ◽

Vessel Segmentation ◽

Fundus Images ◽

Retinal Vessel Segmentation

Download Full-text

Retinal vessel segmentation in colour fundus images using Extreme Learning Machine

Computerized Medical Imaging and Graphics ◽

10.1016/j.compmedimag.2016.05.004 ◽

2017 ◽

Vol 55 ◽

pp. 68-77 ◽

Cited By ~ 62

Author(s):

Chengzhang Zhu ◽

Beiji Zou ◽

Rongchang Zhao ◽

Jinkai Cui ◽

Xuanchu Duan ◽

...

Keyword(s):

Extreme Learning Machine ◽

Retinal Vessel ◽

Vessel Segmentation ◽

Fundus Images ◽

Retinal Vessel Segmentation ◽

Learning Machine

Download Full-text

Hybrid UNet Architecture based on Residual Learning of Fundus Images for Retinal Vessel Segmentation

Journal of Physics Conference Series ◽

10.1088/1742-6596/2070/1/012104 ◽

2021 ◽

Vol 2070 (1) ◽

pp. 012104

Author(s):

Sushma Nagdeote ◽

Sapna Prabhu

Keyword(s):

Blood Vessels ◽

Retinal Vessel ◽

Vessel Segmentation ◽

Intensity Difference ◽

Fundus Images ◽

The Past ◽

Retinal Blood Vessels ◽

Retinal Fundus Image ◽

Retinal Vessel Segmentation ◽

Retinal Fundus

Abstract This paper deals with the new segmentation techniques for retinal blood vessels on fundus images. This technique aims at extracting thin vessels to reduce the intensity difference between thick and thin vessels. This paper proposes the modified UNet model by incorporating ResNet blocks into it which includes structured prediction. In this work we generate the visualization of blood vessels from retinal fundus image for two loss functions namely cross entropy loss and Dice loss where the network classifies several pixels simultaneously. The results shows higher accuracy by considering a much more expressive UNet algorithm and outperforms the past algorithms for Retinal Vessel Segmentation. The benefits of this approach will be demonstrated empirically.

Download Full-text