Generating Realistic Neuronal Morphologies in 3D using a Generative Adversarial Network

Abstract: Neuronal morphology is primarily responsible for the structure of the connectivity among the neurons and is an important determinant for neuronal activity. This raises questions about the relationship between neuron shape and neuron function. To further investigate the structure-function relationship in neurons, extensive modelling with more morphological data is key. Digitally reconstructing neurons is tedious and requires a lot of manual labour and hence several generative methods have been proposed. However these generative models utilizes the current understanding of neuronal morphology, often by imposing a priori constraints, and thus may be biased or do not capture reality fully. We present an alternative technique using a Generative Adversarial Network that generates neurons without being constrained by current human understanding. The model was trained on digital reconstructions of pyramidal cells from rats and mice in a voxelized representation with dimensionality 1283. The results show that the model can generate objects that exhibit realistic neuronal features with a wide variety of shapes. Even though realistic feature are present in the generated objects they are often easily distinguishable from real neurons because of small discontinuous parts and noise in the complex arborizations. Nevertheless, this work can be seen as a proof of concept for generating realistic three dimensional morphologies in an unbiased manner.