NeuriteNet: A convolutional neural network for assessing morphological parameters of neurite growth

Joseph T Vecchi; Sean Mullan; Josue A Lopez; Marlan R Hansen; Milan Sonka; Amy Lee

doi:10.1016/j.jneumeth.2021.109349

Back

NeuriteNet: A convolutional neural network for assessing morphological parameters of neurite growth

Journal article

Peer reviewed

NeuriteNet: A convolutional neural network for assessing morphological parameters of neurite growth

Joseph T Vecchi, Sean Mullan, Josue A Lopez, Marlan R Hansen, Milan Sonka and Amy Lee

Journal of neuroscience methods, Vol.363, pp.109349-109349

11/01/2021

DOI: 10.1016/j.jneumeth.2021.109349

PMID: 34480956

Files and links (1)

url

https://www.ncbi.nlm.nih.gov/pmc/articles/9252595View

Open Access

Abstract

During development or regeneration, neurons extend processes (i.e., neurites) via mechanisms that can be readily analyzed in culture. However, defining the impact of a drug or genetic manipulation on such mechanisms can be challenging due to the complex arborization and heterogeneous patterns of neurite growth in vitro. New Method: NeuriteNet is a Convolutional Neural Network (CNN) sorting model that uses a novel adaptation of the XRAI saliency map overlay, which is a region-based attribution method. NeuriteNet compares neuronal populations based on differences in neurite growth patterns, sorts them into respective groups, and overlays a saliency map indicating which areas differentiated the image for the sorting procedure. In this study, we demonstrate that NeuriteNet effectively sorts images corresponding to dissociated neurons into control and treatment groups according to known morphological differences. Furthermore, the saliency map overlay highlights the distinguishing features of the neuron when sorting the images into treatment groups. NeuriteNet also identifies novel morphological differences in neurons cultured from control and genetically modified mouse strains. Comparison with Existing Methods: Unlike other neurite analysis platforms, NeuriteNet does not require manual manipulations, such as segmentation of neurites prior to analysis, and is more accurate than experienced researchers for categorizing neurons according to their pattern of neurite growth. NeuriteNet can be used to effectively screen for morphological differences in a heterogeneous group of neurons and to provide feedback on the key features distinguishing those groups via the saliency map overlay. •NeuriteNet is a novel machine learning platform for analysis of neurite growth.•A saliency map highlights the distinguishing features of a neuron’s morphology.•NeuriteNet outperforms researchers in assigning neurons to control or experimental groups.

Automatic classification

Axon

Dendrite

High-content image analysis

Machine learning

Neurite outgrowth

Details

Title: Subtitle: NeuriteNet: A convolutional neural network for assessing morphological parameters of neurite growth
Creators: Joseph T Vecchi - University of Iowa
Sean Mullan - University of Iowa
Josue A Lopez - University of Iowa
Marlan R Hansen - University of Iowa
Milan Sonka - University of Iowa
Amy Lee - The University of Texas at Austin
Resource Type: Journal article
Publication Details: Journal of neuroscience methods, Vol.363, pp.109349-109349
DOI: 10.1016/j.jneumeth.2021.109349
PMID: 34480956
NLM abbreviation: J Neurosci Methods
ISSN: 0165-0270
eISSN: 1872-678X
Publisher: Elsevier B.V
Grant note: DOI: 10.13039/100000002, name: National Institutes of Health, award: R01 DC012578, R01-EB004640, R01-EY026817, T32-GM007337, T32-HL144461
Language: English
Date published: 11/01/2021
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Molecular Physiology and Biophysics; Radiation Oncology; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Computer Science; Neurosurgery; Otolaryngology; Ophthalmology and Visual Sciences
Record Identifier: 9984186703202771

Metrics

21 Record Views

5 Times Cited - Web of Science