AOSLO-net: A deep learning-based method for automatic segmentation of retinal microaneurysms from adaptive optics scanning laser ophthalmoscope images
This work addresses the need for high-throughput analysis of AOSLO images to aid in early detection of diabetic retinopathy, representing an incremental advance in domain-specific medical imaging.
The authors tackled the lack of automated methods for segmenting retinal microaneurysms from high-resolution AOSLO images by introducing AOSLO-net, a deep learning framework that outperforms state-of-the-art models in accuracy and cost, enabling correct morphological classification.
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 $μm$ 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.