Deep Classification and Segmentation Model for Vessel Extraction in Retinal Images

摘要

The shape of retinal blood vessels is critical in the early diagnosis of diabetes and diabetic retinopathy. Segmentation of retinal vessels, particularly the capillaries, remains a significant challenge. To address this challenge, in this paper, we adopt the "divide-and-conque" strategy, and thus propose a deep neural network-based classification and segmentation (CAS) model to extract blood vessels in color retinal images. We first use the network in network (NIN) to divide the retinal patches extracted from preprocessed fundus retinal images into wide vessel, middle-vessel and capillary patches. Then we train three U-Nets to segment three classes of vessels, respectively. Finally, this algorithm has been evaluated on the digital retinal images for vessel extraction (DRIVE) database against seven existing algorithms and achieved the highest AUC of 97.93% and top three accuracy, sensitivity and specificity. Our comparison results indicate that the proposed algorithm is able to segment blood vessels in retinal images with better performance.