Low complexity convolutional neural network for vessel segmentation in portable retinal diagnostic devices

TL;DR

This paper proposes a simplified CNN model for retinal vessel segmentation suitable for portable diagnostic devices, combining quantization and pruning to reduce complexity while maintaining acceptable accuracy.

Contribution

A novel CNN simplification method using quantization and pruning tailored for portable retinal diagnostic devices.

Findings

The simplified network effectively segments retinal vessels.

The approach reduces computational complexity significantly.

Maintains acceptable segmentation accuracy on STARE dataset.

Abstract

Retinal vessel information is helpful in retinal disease screening and diagnosis. Retinal vessel segmentation provides useful information about vessels and can be used by physicians during intraocular surgery and retinal diagnostic operations. Convolutional neural networks (CNNs) are powerful tools for classification and segmentation of medical images. Complexity of CNNs makes it difficult to implement them in portable devices such as binocular indirect ophthalmoscopes. In this paper a simplification approach is proposed for CNNs based on combination of quantization and pruning. Fully connected layers are quantized and convolutional layers are pruned to have a simple and efficient network structure. Experiments on images of the STARE dataset show that our simplified network is able to segment retinal vessels with acceptable accuracy and low complexity.