A neuronal imaging dataset for deep learning in the reconstruction of single-neuron axons

Neuron reconstruction is a critical step in quantifying neuronal structures from imaging data. Advances in molecular labeling techniques and optical imaging technologies have spurred extensive research into the patterns of long-range neuronal projections. However, mapping these projections incurs si...

Full description

Saved in:
Bibliographic Details
Main Authors: Liya Li, Ying Hu, Xiaojun Wang, Pei Sun, Tingwei Quan
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Neuroinformatics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fninf.2025.1628030/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849243354875822080
author Liya Li
Liya Li
Ying Hu
Ying Hu
Xiaojun Wang
Pei Sun
Tingwei Quan
author_facet Liya Li
Liya Li
Ying Hu
Ying Hu
Xiaojun Wang
Pei Sun
Tingwei Quan
author_sort Liya Li
collection DOAJ
description Neuron reconstruction is a critical step in quantifying neuronal structures from imaging data. Advances in molecular labeling techniques and optical imaging technologies have spurred extensive research into the patterns of long-range neuronal projections. However, mapping these projections incurs significant costs, as large-scale reconstruction of individual axonal arbors remains time-consuming. In this study, we present a dataset comprising axon imaging volumes along with corresponding annotations to facilitate the evaluation and development of axon reconstruction algorithms. This dataset, derived from 11 mouse brain samples imaged using fluorescence micro-optical sectioning tomography, contains carefully selected 852 volume images sized at 192 × 192 × 192 voxels. These images exhibit substantial variations in terms of axon density, image intensity, and signal-to-noise ratios, even within localized regions. Conventional methods often struggle when processing such complex data. To address these challenges, we propose a distance field-supervised segmentation network designed to enhance image signals effectively. Our results demonstrate significantly improved axon detection rates across both state-of-the-art and traditional methodologies. The released dataset and benchmark algorithm provide a data foundation for advancing novel axon reconstruction methods and are valuable for accelerating the reconstruction of long-range axonal projections.
format Article
id doaj-art-edcaec9e251b49c0bccc09df167746c2
institution Kabale University
issn 1662-5196
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neuroinformatics
spelling doaj-art-edcaec9e251b49c0bccc09df167746c22025-08-20T03:59:30ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962025-08-011910.3389/fninf.2025.16280301628030A neuronal imaging dataset for deep learning in the reconstruction of single-neuron axonsLiya Li0Liya Li1Ying Hu2Ying Hu3Xiaojun Wang4Pei Sun5Tingwei Quan6School of Mathematics and Statistics, Hubei University of Education, Wuhan, Hubei, ChinaInstitute of Big Data Analysis and Applied Mathematics, Hubei University of Education, Wuhan, Hubei, ChinaSchool of Mathematics and Statistics, Hubei University of Education, Wuhan, Hubei, ChinaInstitute of Big Data Analysis and Applied Mathematics, Hubei University of Education, Wuhan, Hubei, ChinaKey Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan University, Sanya, ChinaDepartment of Clinical Research Institute, Central People’s Hospital of Zhanjiang, Zhanjiang, Guangdong, ChinaBritton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and Technology, Wuhan, Hubei, ChinaNeuron reconstruction is a critical step in quantifying neuronal structures from imaging data. Advances in molecular labeling techniques and optical imaging technologies have spurred extensive research into the patterns of long-range neuronal projections. However, mapping these projections incurs significant costs, as large-scale reconstruction of individual axonal arbors remains time-consuming. In this study, we present a dataset comprising axon imaging volumes along with corresponding annotations to facilitate the evaluation and development of axon reconstruction algorithms. This dataset, derived from 11 mouse brain samples imaged using fluorescence micro-optical sectioning tomography, contains carefully selected 852 volume images sized at 192 × 192 × 192 voxels. These images exhibit substantial variations in terms of axon density, image intensity, and signal-to-noise ratios, even within localized regions. Conventional methods often struggle when processing such complex data. To address these challenges, we propose a distance field-supervised segmentation network designed to enhance image signals effectively. Our results demonstrate significantly improved axon detection rates across both state-of-the-art and traditional methodologies. The released dataset and benchmark algorithm provide a data foundation for advancing novel axon reconstruction methods and are valuable for accelerating the reconstruction of long-range axonal projections.https://www.frontiersin.org/articles/10.3389/fninf.2025.1628030/fullneuron morphologyaxon reconstructiondeep learningneuronal imaging datasetssegmentation network
spellingShingle Liya Li
Liya Li
Ying Hu
Ying Hu
Xiaojun Wang
Pei Sun
Tingwei Quan
A neuronal imaging dataset for deep learning in the reconstruction of single-neuron axons
Frontiers in Neuroinformatics
neuron morphology
axon reconstruction
deep learning
neuronal imaging datasets
segmentation network
title A neuronal imaging dataset for deep learning in the reconstruction of single-neuron axons
title_full A neuronal imaging dataset for deep learning in the reconstruction of single-neuron axons
title_fullStr A neuronal imaging dataset for deep learning in the reconstruction of single-neuron axons
title_full_unstemmed A neuronal imaging dataset for deep learning in the reconstruction of single-neuron axons
title_short A neuronal imaging dataset for deep learning in the reconstruction of single-neuron axons
title_sort neuronal imaging dataset for deep learning in the reconstruction of single neuron axons
topic neuron morphology
axon reconstruction
deep learning
neuronal imaging datasets
segmentation network
url https://www.frontiersin.org/articles/10.3389/fninf.2025.1628030/full
work_keys_str_mv AT liyali aneuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT liyali aneuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT yinghu aneuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT yinghu aneuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT xiaojunwang aneuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT peisun aneuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT tingweiquan aneuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT liyali neuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT liyali neuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT yinghu neuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT yinghu neuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT xiaojunwang neuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT peisun neuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons
AT tingweiquan neuronalimagingdatasetfordeeplearninginthereconstructionofsingleneuronaxons