Cargando…

Accurate Neuronal Soma Segmentation Using 3D Multi-Task Learning U-Shaped Fully Convolutional Neural Networks

Neuronal soma segmentation is a crucial step for the quantitative analysis of neuronal morphology. Automated neuronal soma segmentation methods have opened up the opportunity to improve the time-consuming manual labeling required during the neuronal soma morphology reconstruction for large-scale ima...

Descripción completa

Detalles Bibliográficos
Autores principales: Hu, Tianyu, Xu, Xiaofeng, Chen, Shangbin, Liu, Qian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7860594/
https://www.ncbi.nlm.nih.gov/pubmed/33551758
http://dx.doi.org/10.3389/fnana.2020.592806
_version_ 1783646910716837888
author Hu, Tianyu
Xu, Xiaofeng
Chen, Shangbin
Liu, Qian
author_facet Hu, Tianyu
Xu, Xiaofeng
Chen, Shangbin
Liu, Qian
author_sort Hu, Tianyu
collection PubMed
description Neuronal soma segmentation is a crucial step for the quantitative analysis of neuronal morphology. Automated neuronal soma segmentation methods have opened up the opportunity to improve the time-consuming manual labeling required during the neuronal soma morphology reconstruction for large-scale images. However, the presence of touching neuronal somata and variable soma shapes in images brings challenges for automated algorithms. This study proposes a neuronal soma segmentation method combining 3D U-shaped fully convolutional neural networks with multi-task learning. Compared to existing methods, this technique applies multi-task learning to predict the soma boundary to split touching somata, and adopts U-shaped architecture convolutional neural network which is effective for a limited dataset. The contour-aware multi-task learning framework is applied to the proposed method to predict the masks of neuronal somata and boundaries simultaneously. In addition, a spatial attention module is embedded into the multi-task model to improve neuronal soma segmentation results. The Nissl-stained dataset captured by the micro-optical sectioning tomography system is used to validate the proposed method. Following comparison to four existing segmentation models, the proposed method outperforms the others notably in both localization and segmentation. The novel method has potential for high-throughput neuronal soma segmentation in large-scale optical imaging data for neuron morphology quantitative analysis.
format Online
Article
Text
id pubmed-7860594
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-78605942021-02-05 Accurate Neuronal Soma Segmentation Using 3D Multi-Task Learning U-Shaped Fully Convolutional Neural Networks Hu, Tianyu Xu, Xiaofeng Chen, Shangbin Liu, Qian Front Neuroanat Neuroscience Neuronal soma segmentation is a crucial step for the quantitative analysis of neuronal morphology. Automated neuronal soma segmentation methods have opened up the opportunity to improve the time-consuming manual labeling required during the neuronal soma morphology reconstruction for large-scale images. However, the presence of touching neuronal somata and variable soma shapes in images brings challenges for automated algorithms. This study proposes a neuronal soma segmentation method combining 3D U-shaped fully convolutional neural networks with multi-task learning. Compared to existing methods, this technique applies multi-task learning to predict the soma boundary to split touching somata, and adopts U-shaped architecture convolutional neural network which is effective for a limited dataset. The contour-aware multi-task learning framework is applied to the proposed method to predict the masks of neuronal somata and boundaries simultaneously. In addition, a spatial attention module is embedded into the multi-task model to improve neuronal soma segmentation results. The Nissl-stained dataset captured by the micro-optical sectioning tomography system is used to validate the proposed method. Following comparison to four existing segmentation models, the proposed method outperforms the others notably in both localization and segmentation. The novel method has potential for high-throughput neuronal soma segmentation in large-scale optical imaging data for neuron morphology quantitative analysis. Frontiers Media S.A. 2021-01-21 /pmc/articles/PMC7860594/ /pubmed/33551758 http://dx.doi.org/10.3389/fnana.2020.592806 Text en Copyright © 2021 Hu, Xu, Chen and Liu. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Hu, Tianyu
Xu, Xiaofeng
Chen, Shangbin
Liu, Qian
Accurate Neuronal Soma Segmentation Using 3D Multi-Task Learning U-Shaped Fully Convolutional Neural Networks
title Accurate Neuronal Soma Segmentation Using 3D Multi-Task Learning U-Shaped Fully Convolutional Neural Networks
title_full Accurate Neuronal Soma Segmentation Using 3D Multi-Task Learning U-Shaped Fully Convolutional Neural Networks
title_fullStr Accurate Neuronal Soma Segmentation Using 3D Multi-Task Learning U-Shaped Fully Convolutional Neural Networks
title_full_unstemmed Accurate Neuronal Soma Segmentation Using 3D Multi-Task Learning U-Shaped Fully Convolutional Neural Networks
title_short Accurate Neuronal Soma Segmentation Using 3D Multi-Task Learning U-Shaped Fully Convolutional Neural Networks
title_sort accurate neuronal soma segmentation using 3d multi-task learning u-shaped fully convolutional neural networks
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7860594/
https://www.ncbi.nlm.nih.gov/pubmed/33551758
http://dx.doi.org/10.3389/fnana.2020.592806
work_keys_str_mv AT hutianyu accurateneuronalsomasegmentationusing3dmultitasklearningushapedfullyconvolutionalneuralnetworks
AT xuxiaofeng accurateneuronalsomasegmentationusing3dmultitasklearningushapedfullyconvolutionalneuralnetworks
AT chenshangbin accurateneuronalsomasegmentationusing3dmultitasklearningushapedfullyconvolutionalneuralnetworks
AT liuqian accurateneuronalsomasegmentationusing3dmultitasklearningushapedfullyconvolutionalneuralnetworks