# Retinal vessel segmentation based on Fully Convolutional Neural Networks

## TL;DR

This paper introduces a novel retinal vessel segmentation method combining multiscale wavelet analysis with a rotation-augmented Fully Convolutional Neural Network, achieving high accuracy and robustness across multiple datasets.

## Contribution

It presents a new approach integrating wavelet transforms and rotation-based data augmentation within a FCN for improved retinal vessel segmentation.

## Key findings

- Achieved high accuracy on DRIVE, STARE, and CHASE_DB1 datasets.
- Demonstrated robustness to training set variations and inter-rater variability.
- Provided a method suitable for real-world clinical applications.

## 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.