Multi-Task Neural Networks with Spatial Activation for Retinal Vessel Segmentation and Artery/Vein Classification
This work addresses a critical need in clinical biomarker studies for systemic and cardiovascular diseases by improving automated retinal analysis, though it appears incremental as it builds on existing multi-task and spatial activation techniques.
The paper tackled the problem of retinal artery/vein classification by proposing a multi-task neural network that simultaneously segments vessels and classifies arteries/veins without requiring prior segmentation, achieving 95.70% pixel-wise accuracy for vessel segmentation and 94.50% accuracy for A/V classification on the AV-DRIVE dataset.
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%.