UCLA

The reliable segmentation and quantification of retinal vasculature can provide the means to diagnose and monitor the progression of a variety of diseases affecting the blood vessel network, including diabetes and hypertension. In this thesis, we address this problem in depth, leveraging the power of artificial intelligence to devise automated approaches for the segmentation and width estimation of vessels in two ophthalmological image modalities. First, we investigate the automated segmentation of retinal vessels in color fundus images. We propose a novel, fully convolutional deep neural network with an encoder-decoder architecture that employs dilated spatial pyramid pooling with multiple dilation rates to recover the lost content in the encoder and add multiscale contextual information to the decoder. We also propose a simple yet effective way of quantifying and tracking the widths of retinal vessels through direct use of the segmentation predictions. The proposed methodology takes a whole-image approach and is tested on two publicly available datasets, DRIVE and CHASE-DB1. Second, we introduce the first deep-learning based method for the semantic segmentation of retinal arteries and veins in infrared imaging along with a novel dataset dubbed AVIR, and propose an innovative encoder-decoder that is regularized by variational autoencoders. Additionally, our method automatically quantifies the morphological changes of the segmented arteries and veins, which is important for establishing automated vessel tracking systems.