Cellular neural network with virtual template expansion for retinal vessel segmentation

A retinal vessel segmentation method based on cel- lular neural networks (CNNs) is proposed. The CNN design is char- acterized by a virtual template expansion obtained through a mul- tistep operation. It is based on linear space-invariant 3 3 tem- plates and can be realized using existing chip prototypes like the ACE16K. The proposed design is capable of performing vessel seg- mentation within a short computation time. It was tested on a pub- licly available database of color images of the retina, using receiver operating characteristic curves. The simulation results show good performance comparable with that of the best existing methods.