# VMseg: Using spatial variance to automatically segment retinal non-perfusion on OCT-angiography

## TL;DR

This paper introduces VMseg, an algorithm that automatically segments retinal non-perfusion in OCT-A images to estimate non-perfusion indexes in diabetic retinopathy patients.

## Contribution

The novel contribution is VMseg, a fast and accurate algorithm for automatic retinal non-perfusion segmentation in widefield OCT-A images.

## Key findings

- VMseg achieved a mean Dice coefficient of 0.683 for test set segmentations.
- The algorithm showed strong correlation (rs = 0.877) between estimated and ground truth non-perfusion indexes.
- 3 out of 51 eyes were significantly under-segmented by VMseg.

## Abstract

To develop and test VMseg, a new image processing algorithm performing automatic segmentation of retinal non-perfusion in widefield OCT-Angiography images, in order to estimate the non-perfusion index in diabetic patients.

We included diabetic patients with severe non-proliferative or proliferative diabetic retinopathy. We acquired images using the PlexElite 9000 OCT-A device with a photomontage of 5 images of size 12 x 12 mm. We then developed VMseg, a Python algorithm for non-perfusion detection, which binarizes a variance map calculated through convolution and morphological operations. We used 70% of our data set (development set) to fine-tune the algorithm parameters (convolution and morphological parameters, binarization thresholds) and evaluated the algorithm performance on the remaining 30% (test set). The obtained automatic segmentations were compared to a ground truth corresponding to manual segmentation from a retina expert and the inference processing time was estimated.

We included 51 eyes of 30 patients (27 severe non-proliferative, 24 proliferative diabetic retinopathy). Using the optimal parameters found on the development set to tune the algorithm, the mean dice for the test set was 0.683 (sd = 0.175). We found a higher dice coefficient for images with a higher area of retinal non-perfusion (rs = 0.722, p < 10−4). There was a strong correlation (rs = 0.877, p < 10−4) between VMseg estimated non-perfusion indexes and indexes estimated using the ground truth segmentation. The Bland-Altman plot revealed that 3 eyes (5.9%) were significantly under-segmented by VMseg.

We developed VMseg, an automatic algorithm for retinal non-perfusion segmentation on 12 x 12 mm OCT-A widefield photomontages. This simple algorithm was fast at inference time, segmented images in full-resolution and for the OCT-A format, was accurate enough for automatic estimation of retinal non-perfusion index in diabetic patients with diabetic retinopathy.