An End to End System for Measuring Axon Growth

Zewen Liu, Timothy F. Cootes, Christoph Ballestrem

Abstract: To study how axon growth is affected by the local environment biologists perform extensive experiments, watching the axons develop on different substrates. As axons grow from the neuron cell body they form tree-like structures, with branches forming and withering as they explore their surroundings. In this paper, we propose a system which can track individual axons as they grow and branch over time, enabling quantitative evaluation of different aspects of the axon behaviour. The system includes a novel segmentation network with Gabor kernels. It uses less than 0.5% of the number of parameters required in an equivalent U-Net or other related CNN but gives better overall performance on a standard test set. We evaluate the complete axon tracking system and demonstrating that it achieves results comparable to a human annotator, but gives a far richer description and is much faster.