A multi-task deep learning model for the classification of Age-related Macular Degeneration
This work addresses the need for efficient and accurate diagnosis of AMD, a leading cause of blindness, by providing an automated tool that reduces reliance on manual grading, though it builds incrementally on prior deep learning methods.
The researchers tackled the problem of automating the classification of Age-related Macular Degeneration severity from color fundus images, which is time-consuming and expensive to do manually, and achieved a result where their model's accuracy exceeded the current state-of-the-art by over 10% on two datasets.
Age-related Macular Degeneration (AMD) is a leading cause of blindness. Although the Age-Related Eye Disease Study group previously developed a 9-step AMD severity scale for manual classification of AMD severity from color fundus images, manual grading of images is time-consuming and expensive. Built on our previous work DeepSeeNet, we developed a novel deep learning model for automated classification of images into the 9-step scale. Instead of predicting the 9-step score directly, our approach simulates the reading center grading process. It first detects four AMD characteristics (drusen area, geographic atrophy, increased pigment, and depigmentation), then combines these to derive the overall 9-step score. Importantly, we applied multi-task learning techniques, which allowed us to train classification of the four characteristics in parallel, share representation, and prevent overfitting. Evaluation on two image datasets showed that the accuracy of the model exceeded the current state-of-the-art model by > 10%.