Hard Attention Net for Automatic Retinal Vessel Segmentation.

Automated retinal vessel segmentation is among the most significant application and research topics in ophthalmologic image analysis. Deep learning based retinal vessel segmentation models have attracted much attention in the recent years. However, current deep network designs tend to predominantly focus on vessels which are easy to segment, while overlooking vessels which are more difficult to segment, such as thin vessels or those with uncertain boundaries.

Automated retinal microvascular velocimetry based on erythrocyte mediated angiography.

Retinal blood flow is an emerging biomarker in ocular and systemic disease. Erythrocyte mediated angiography (EMA) is a novel technique that provides an easily interpretable blood flow velocity quantification by directly tracing individual moving erythrocyte ghosts over time in vivo, imaged using a scanning laser ophthalmoscope (Heidelberg Retina Angiograph platform). This tracking procedure, however, requires time-consuming manual analysis to determine blood flow.