Multi-Task Neural Networks with Spatial Activation for Retinal Vessel Segmentation and Artery/Vein Classification

TL;DR

This paper introduces a multi-task neural network with spatial activation that simultaneously segments retinal vessels and classifies arteries and veins without needing prior vessel segmentation, achieving state-of-the-art accuracy.

Contribution

It proposes a novel multi-task deep neural network with spatial activation and deep supervision, improving retinal vessel segmentation and artery/vein classification without pre-segmented vessels.

Findings

Achieves 95.70% vessel segmentation accuracy

Attains 94.50% artery/vein classification accuracy

Performs well on multiple retinal datasets

Abstract

Retinal artery/vein (A/V) classification plays a critical role in the clinical biomarker study of how various systemic and cardiovascular diseases affect the retinal vessels. Conventional methods of automated A/V classification are generally complicated and heavily depend on the accurate vessel segmentation. In this paper, we propose a multi-task deep neural network with spatial activation mechanism that is able to segment full retinal vessel, artery and vein simultaneously, without the pre-requirement of vessel segmentation. The input module of the network integrates the domain knowledge of widely used retinal preprocessing and vessel enhancement techniques. We specially customize the output block of the network with a spatial activation mechanism, which takes advantage of a relatively easier task of vessel segmentation and exploits it to boost the performance of A/V classification. In addition, deep supervision is introduced to the network to assist the low level layers to extract more semantic information. The proposed network achieves pixel-wise accuracy of 95.70% for vessel segmentation, and A/V classification accuracy of 94.50%, which is the state-of-the-art performance for both tasks on the AV-DRIVE dataset. Furthermore, we have also tested the model performance on INSPIRE-AVR dataset, which achieves a skeletal A/V classification accuracy of 91.6%.