Although deep learning for Diabetic Retinopathy (DR) screening has shown great success in achieving clinically acceptable accuracy for referable versus non-referable DR, there remains a need to provide more fine-grained grading of the DR severity level as well as automated segmentation of lesions (if any) in the retina images. We observe that the DR severity level of an image is dependent on the presence of different types of lesions and their prevalence. In this work, we adopt a multi-task learning approach to perform the DR grading and lesion segmentation tasks. In light of the lack of lesion segmentation mask ground-truths, we further propose a semi-supervised learning process to obtain the segmentation masks for the various datasets. Experiments results on publicly available datasets and a real world dataset obtained from population screening demonstrate the effectiveness of the multi-task solution over state-of-the-art networks.

A fundamental factor limiting the effectiveness of classification algorithms, especially in the medical imaging domain, has been an insufficient quantity of relevant class-specific data. In particular, positive examples of disease conditions tend to be rare, and represent a common bottleneck in improving model performance. In this paper, we introduce GAN-based generative data augmentation methods with dynamic input sampling, and compare their performance against an image feature transfer technique, towards improving the performance of real-world diabetic retinopathy classification tasks. Results suggest that generative data augmentation has the potential to significantly improve classification performance over the baseline.

Ischemic stroke is a leading cause of death and long-term disability that is difficult to predict reliably. Retinal fundus photography has been proposed for stroke risk assessment, due to its non-invasiveness and the similarity between retinal and cerebral microcirculations, with past studies claiming a correlation between venular caliber and stroke risk. However, it may be that other retinal features are more appropriate. In this paper, extensive experiments with deep learning on six retinal datasets are described. Feature isolation involving segmented vascular tree images is applied to establish the effectiveness of vessel caliber and shape alone for stroke classification, and dataset ablation is applied to investigate model generalizability on unseen sources. The results suggest that vessel caliber and shape could be indicative of ischemic stroke, and sourcespecific features could influence model performance.

Vessel type classification is a preliminary step in quantifying the severity of various diseases. This paper proposes DBA, a simple yet effective vessel type classification method based on the principle that arteries are brighter than veins at the local scale. The weighted local difference of the red channel intensity of the main trunk of each vessel is compared with that of its two immediately neighbouring vessels, a feature that is highly correlated with vessel-rectified oxygen capacity, and in turn, vessel type. Experiments on the publicly-available INSPIRE-AVR and DRIVE datasets obtained average vessel accuracies of 0.9217/0.9071, and average pixel accuracies of 0.9602/0.9634 respectively, with particular effectiveness on images with low contrast, non-uniform illumination and colour variation confirmed on the SiMES 1 dataset.

Glaucoma is a widespread ocular disorder leading to irreversible loss of vision. Therefore, there is a pressing need for cost-effective screening, such that preventive measures can be taken. This can be achieved with an accurate segmentation of the optic disc and cup from retinal images to obtain the cup-to-disc ratio. We describe a comprehensive solution based on applying convolutional neural networks to feature exaggerated inputs emphasizing disc pallor without blood vessel obstruction, as well as the degree of vessel kinking. The produced raw probability maps then undergo a robust refinement procedure that takes into account prior knowledge about retinal structures. Analysis of these probability maps further allows us to obtain a confidence estimate on the correctness of the segmentation, which can be used to direct the most challenging cases for manual inspection. Tests on two large real-world databases, including the publicly-available MESSIDOR collection, demonstrate the effectiveness of our proposed system.