An efficient method to map a regular mesh into a 3D neural network

In 3D computer vision a relevant problem is to match a "source" image dataset with a "target" image dataset. The matching problem can be faced using a neural net approach, where the nodes are related with the image voxels and the synapses to the voxel information. This paper presents an improvement of the "Volume-Matcher" project, n approach to the data-driver and registration of three-dimensional images based on 3D neural networks. The approach has been improved by introducing a method for an efficient mapping of a regular mesh into a 3D neural network in order to reduce the computational complexity. The algorithms developed have been tested on real cases of interest in the field of medical imaging.