Julie Meystre

This paper presents a deep learning framework that classifies neuronal morphologies using topology and graph neural networks, achieving accuracy comparable to human experts.

The paper compares dendritic architecture in human and mice neuronal networks, finding that human pyramidal cells have greater dendritic complexity, contributing to increased network complexity despite lower neuron density.

The paper objectively classifies neocortical pyramidal cells using algebraic topology, identifying seventeen types in the rat somatosensory cortex without expert input.