Automatic segmentation of blood vessels in fundus images is of great importance as eye diseases as well as some systemic diseases cause observable pathologic modifications. It is a binary classification problem: for each pixel we consider two possible classes (vessel or non-vessel). We use a GPU implementation of deep max-pooling convolutional neural networks to segment blood vessels. We test our method on publiclyavailable DRIVE dataset and our results demonstrate the high effectiveness of the deep learning approach. Our method achieves an average accuracy and AUC of 0.9466 and 0.9749, respectively.

Optical coherence tomography (OCT) images of the retina provide a structural representation and give an insight into the pathological changes present in age-related macular degeneration (AMD). Due to the three-dimensionality and complexity of the images, manual analysis of pathological features is difficult, time-consuming, and prone to subjectivity. Computer analysis of 3D OCT images is necessary to enable automated quantitative measuring of the features, objectively and repeatedly. As supervised and semi-supervised learning-based automatic segmentation depends on the training data and quality of annotations, we have created a new database of annotated retinal OCT images -the AROI database. It consists of 1136 images with annotations for pathological changes (fluid accumulation and related findings) and basic structures (layers) in patients with AMD. Inter-and intra-observer errors have been calculated in order to enable the validation of developed algorithms in relation to human variability. Also, we have performed the automatic segmentation with standard U-net architecture and two state-of-the-art architectures for medical image segmentation to set a baseline for further algorithm development and to get insight into challenges for automatic segmentation. To facilitate and encourage further research in the field, we have made the AROI database openly available.

No abstract