AOSLO-net: A deep learning-based method for automatic segmentation of retinal microaneurysms from adaptive optics scanning laser ophthalmoscope images

TL;DR

AOSLO-net is a deep learning framework designed to automatically segment microaneurysms in high-resolution retinal images from adaptive optics scanning laser ophthalmoscopy, aiding early diabetic retinopathy detection.

Contribution

This paper introduces AOSLO-net, a novel deep neural network tailored for high-throughput automatic segmentation of microaneurysms in AOSLO retinal images, improving accuracy over existing models.

Findings

AOSLO-net outperforms existing segmentation models in accuracy.

The model enables correct morphological classification of microaneurysms.

Demonstrated effectiveness on 87 DR AOSLO images.

Abstract

Microaneurysms (MAs) are one of the earliest signs of diabetic retinopathy (DR), a frequent complication of diabetes that can lead to visual impairment and blindness. Adaptive optics scanning laser ophthalmoscopy (AOSLO) provides real-time retinal images with resolution down to 2 $\mu m$ and thus allows detection of the morphologies of individual MAs, a potential marker that might dictate MA pathology and affect the progression of DR. In contrast to the numerous automatic models developed for assessing the number of MAs on fundus photographs, currently there is no high throughput image protocol available for automatic analysis of AOSLO photographs. To address this urgency, we introduce AOSLO-net, a deep neural network framework with customized training policies to automatically segment MAs from AOSLO images. We evaluate the performance of AOSLO-net using 87 DR AOSLO images and our results demonstrate that the proposed model outperforms the state-of-the-art segmentation model both in accuracy and cost and enables correct MA morphological classification.