Automatic detection of arteriovenous nicking in retinal images

Morphological changes of retinal vessels such as arteriovenous (AV) nicking are signs of many systemic diseases. In this paper, an automatic method for AV-nicking detection is proposed. The proposed method includes crossover point detection and AV-nicking identification. Vessel segmentation, vessel thinning, and feature point recognition are performed to detect crossover point. A method of vessel diameter measurement is proposed with processing of removing voids, hidden vessels and micro-vessels in segmentation. The AV-nicking is detected based on the features of vessel diameter measurement. The proposed algorithms have been tested using clinical images. The results show that nicking points in retinal images can be detected successfully in most cases.