Biomimetic IGA neuron growth modeling with neurite morphometric features and CNN-based prediction

Neuron growth is a complex, multi-stage process that neurons undergo to develop sophisticated morphologies and interwoven neurite networks. Recent experimental research advances have enabled us examine the effects of various neuron factors seek potential causes for neurodegenerative diseases, such as Alzheimer’s disease, Parkinson’s amyotrophic lateral sclerosis. A computational tool studies could shed crucial insights on potentially help find cure neurodegeneration. However, there lack tools accurately realistically simulate within reasonable time frames. Bio-phenomenon-based models ignore cannot generate realistic results, bio-physics-based require extensive, high-order governing equations are computationally expensive. In this paper, we incorporate features into phase field method-based model using an isogeometric analysis collocation (IGA-C) approach. Based semi-automated quantitative morphology, obtain relative turning angle, average tortuosity, endpoints, segment length, total length neurites. We use determine evolving days in vitro (DIV) select corresponding drive constrain growth. This approach archives biomimetic patterns with automatic stage transitions by incorporating DIV morphometric data based morphology. Furthermore, built convolutional neural network (CNN) significantly reduce associated costs predicting complex patterns. Our CNN adopts customized autoencoder backbone takes simulation initializations target iteration input predicts achieves high prediction accuracy (97.77%) while taking 7 orders magnitude less times when compared our IGA-C solver.