Study: Multi-task deep-learning system for Assessment of Dia
Researchers aimed to develop and test a deep-learning (DL) system to perform image quality and diabetic macular ischemia (DMI) assessment on OCTA images.

This study included 7,194 OCTA images with diabetes mellitus for training and primary validation, and 960 images from three independent datasets for external testing. A trinary classification for image quality assessment and presence or absence of DMI for DMI assessment were labelled on all OCTA images.

--For the image quality assessment, analyses for gradability and measurability assessment were performed.

--DL system achieved the AUROCs more than 0.948 and AUPRCs more than 0.866 for the gradability assessment, AUROCs more than 0.960 and AUPRCs more than 0.822 for the measurability assessment, and AUROCs more than 0.939 and AUPRCs more than 0.899 for the DMI assessment across three external validation datasets.

--Grad-CAM demonstrated the capability of our DL system paying attention to regions related to DMI identification.

Conclusively, this multi-task DL system might facilitate the development of a simplified assessment of DMI on OCTA images among individuals with DM at high risk for visual loss.