A publicly available vessel segmentation algorithm for SLO images

TL;DR

This paper presents a new deep learning-based vessel segmentation algorithm specifically designed for IRSLO images, achieving high accuracy and made publicly available for research use.

Contribution

The authors developed and released the first open-source vessel segmentation algorithm tailored for IRSLO images using a U-Net model.

Findings

Achieved an AUC of 0.981 on test images

Attained an F1 score of 0.857

Model demonstrated high sensitivity and specificity

Abstract

Background and Objective: Infra-red scanning laser ophthalmoscope (IRSLO) images are akin to colour fundus photographs in displaying the posterior pole and retinal vasculature fine detail. While there are many trained networks readily available for retinal vessel segmentation in colour fundus photographs, none cater to IRSLO images. Accordingly, we aimed to develop (and release as open source) a vessel segmentation algorithm tailored specifically to IRSLO images. Materials and Methods: We used 23 expertly annotated IRSLO images from the RAVIR dataset, combined with 7 additional images annotated in-house. We trained a U-Net (convolutional neural network) to label pixels as 'vessel' or 'background'. Results: On an unseen test set (4 images), our model achieved an AUC of 0.981, and an AUPRC of 0.815. Upon thresholding, it achieved a sensitivity of 0.844, a specificity of 0.983, and an F1 score of 0.857. Conclusion: We have made our automatic segmentation algorithm publicly available and easy to use. Researchers can use the generated vessel maps to compute metrics such as fractal dimension and vessel density.