Retinal vessel segmentation based on Fully Convolutional Neural Networks

2018/06/18 by Américo Oliveira, Sérgio Pereira, Carlos A. Silva
Computer Science · Engineering · Mathematics · Medicine · #Artificial intelligence #Artificial neural network #Computer science #Computer vision #Convolutional neural network #Digital Imaging for Blood Diseases #Glaucoma and retinal disorders #Pattern recognition (psychology) #Retinal Imaging and Analysis #Segmentation #Set (abstract data type) #Training set #Wavelet #cs.LG #eess.IV #stat.ML

paper · pdf · doi:10.1016/j.eswa.2018.06.034

published as Expert Systems with Applications Volume 112, 1 December 2018, Pages 229-242 · Support repository for this work: https://github.com/americofmoliveira/VesselSegmentation_ESWA

openalex publication_date 2018/06/18 · arxiv created 2018/12/19 · arxiv updated 2018/12/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

The retinal vascular condition is a reliable biomarker of several ophthalmologic and cardiovascular diseases, so automatic vessel segmentation may be crucial to diagnose and monitor them. In this paper, we propose a novel method that combines the multiscale analysis provided by the Stationary Wavelet Transform with a multiscale Fully Convolutional Neural Network to cope with the varying width and direction of the vessel structure in the retina. Our proposal uses rotation operations as the basis of a joint strategy for both data augmentation and prediction, which allows us to explore the information learned during training to refine the segmentation. The method was evaluated on three publicly available databases, achieving an average accuracy of 0.9576, 0.9694, and 0.9653, and average area under the ROC curve of 0.9821, 0.9905, and 0.9855 on the DRIVE, STARE, and CHASE_DB1 databases, respectively. It also appears to be robust to the training set and to the inter-rater variability, which shows its potential for real-world applications.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
• Retinal image analysis: Concepts, applications and potential
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response
• ImageNet classification with deep convolutional neural networks
• Representation Learning: A Review and New Perspectives
• Exploiting Cyclic Symmetry in Convolutional Neural Networks
• Deep learning
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Harmonic Networks: Deep Translation and Rotation Equivariance
• Learning Deconvolution Network for Semantic Segmentation
• Fully Convolutional Networks for Semantic Segmentation