ANMAF: an automated neuronal morphology analysis framework using convolutional neural networks

Abstract Measurement of neuronal size is challenging due to their complex histology. Current practice includes manual or pseudo-manual measurement of somatic areas, which is labor-intensive and prone to human biases and intra-/inter-observer variances. We developed a novel high-throughput neuronal m...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ling Tong, Rachel Langton, Joseph Glykys, Stephen Baek
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/0b9ac4da742b4e18b54c5254bb314861
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:0b9ac4da742b4e18b54c5254bb314861
record_format dspace
spelling oai:doaj.org-article:0b9ac4da742b4e18b54c5254bb3148612021-12-02T14:28:00ZANMAF: an automated neuronal morphology analysis framework using convolutional neural networks10.1038/s41598-021-87471-w2045-2322https://doaj.org/article/0b9ac4da742b4e18b54c5254bb3148612021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87471-whttps://doaj.org/toc/2045-2322Abstract Measurement of neuronal size is challenging due to their complex histology. Current practice includes manual or pseudo-manual measurement of somatic areas, which is labor-intensive and prone to human biases and intra-/inter-observer variances. We developed a novel high-throughput neuronal morphology analysis framework (ANMAF), using convolutional neural networks (CNN) to automatically contour the somatic area of fluorescent neurons in acute brain slices. Our results demonstrate considerable agreements between human annotators and ANMAF on detection, segmentation, and the area of somatic regions in neurons expressing a genetically encoded fluorophore. However, in contrast to humans, who exhibited significant variability in repeated measurements, ANMAF produced consistent neuronal contours. ANMAF was generalizable across different imaging protocols and trainable even with a small number of humanly labeled neurons. Our framework can facilitate more rigorous and quantitative studies of neuronal morphology by enabling the segmentation of many fluorescent neurons in thick brain slices in a standardized manner.Ling TongRachel LangtonJoseph GlykysStephen BaekNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Ling Tong
Rachel Langton
Joseph Glykys
Stephen Baek
ANMAF: an automated neuronal morphology analysis framework using convolutional neural networks
description Abstract Measurement of neuronal size is challenging due to their complex histology. Current practice includes manual or pseudo-manual measurement of somatic areas, which is labor-intensive and prone to human biases and intra-/inter-observer variances. We developed a novel high-throughput neuronal morphology analysis framework (ANMAF), using convolutional neural networks (CNN) to automatically contour the somatic area of fluorescent neurons in acute brain slices. Our results demonstrate considerable agreements between human annotators and ANMAF on detection, segmentation, and the area of somatic regions in neurons expressing a genetically encoded fluorophore. However, in contrast to humans, who exhibited significant variability in repeated measurements, ANMAF produced consistent neuronal contours. ANMAF was generalizable across different imaging protocols and trainable even with a small number of humanly labeled neurons. Our framework can facilitate more rigorous and quantitative studies of neuronal morphology by enabling the segmentation of many fluorescent neurons in thick brain slices in a standardized manner.
format article
author Ling Tong
Rachel Langton
Joseph Glykys
Stephen Baek
author_facet Ling Tong
Rachel Langton
Joseph Glykys
Stephen Baek
author_sort Ling Tong
title ANMAF: an automated neuronal morphology analysis framework using convolutional neural networks
title_short ANMAF: an automated neuronal morphology analysis framework using convolutional neural networks
title_full ANMAF: an automated neuronal morphology analysis framework using convolutional neural networks
title_fullStr ANMAF: an automated neuronal morphology analysis framework using convolutional neural networks
title_full_unstemmed ANMAF: an automated neuronal morphology analysis framework using convolutional neural networks
title_sort anmaf: an automated neuronal morphology analysis framework using convolutional neural networks
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/0b9ac4da742b4e18b54c5254bb314861
work_keys_str_mv AT lingtong anmafanautomatedneuronalmorphologyanalysisframeworkusingconvolutionalneuralnetworks
AT rachellangton anmafanautomatedneuronalmorphologyanalysisframeworkusingconvolutionalneuralnetworks
AT josephglykys anmafanautomatedneuronalmorphologyanalysisframeworkusingconvolutionalneuralnetworks
AT stephenbaek anmafanautomatedneuronalmorphologyanalysisframeworkusingconvolutionalneuralnetworks
_version_ 1718391233282310144