Add to Favourites
To login click here
Diabetic retinopathy (DR) is a diabetes complication that can cause vision loss due to damage to the blood vessels in the retina. Early retinal screening can avoid the severe consequences of DR and enable timely treatment. To address the problem of unavailability of larger training data with consistent and fine-grained annotations, a semi-supervised multitask learning approach is proposed that exploits widely available unlabelled data to improve DR segmentation performance. The proposed technique is rigorously evaluated on two publicly available datasets and results show that it outperforms existing state-of-the-art techniques and exhibits improved generalisation and robustness for cross-data evaluation.