Real-time and universal network for volumetric imaging from microscale to macroscale at high resolution

Abstract Light-field imaging has wide applications in various domains, including microscale life science imaging, mesoscale neuroimaging, and macroscale fluid dynamics imaging. The development of deep learning-based reconstruction methods has greatly facilitated high-resolution light-field image pro...

Full description

Saved in:
Bibliographic Details
Main Authors: Bingzhi Lin, Feng Xing, Liwei Su, Kekuan Wang, Yulan Liu, Diming Zhang, Xusan Yang, Huijun Tan, Zhijing Zhu, Depeng Wang
Format: Article
Language:English
Published: Nature Publishing Group 2025-04-01
Series:Light: Science & Applications
Online Access:https://doi.org/10.1038/s41377-025-01842-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849314806744481792
author Bingzhi Lin
Feng Xing
Liwei Su
Kekuan Wang
Yulan Liu
Diming Zhang
Xusan Yang
Huijun Tan
Zhijing Zhu
Depeng Wang
author_facet Bingzhi Lin
Feng Xing
Liwei Su
Kekuan Wang
Yulan Liu
Diming Zhang
Xusan Yang
Huijun Tan
Zhijing Zhu
Depeng Wang
author_sort Bingzhi Lin
collection DOAJ
description Abstract Light-field imaging has wide applications in various domains, including microscale life science imaging, mesoscale neuroimaging, and macroscale fluid dynamics imaging. The development of deep learning-based reconstruction methods has greatly facilitated high-resolution light-field image processing, however, current deep learning-based light-field reconstruction methods have predominantly concentrated on the microscale. Considering the multiscale imaging capacity of light-field technique, a network that can work over variant scales of light-field image reconstruction will significantly benefit the development of volumetric imaging. Unfortunately, to our knowledge, no one has reported a universal high-resolution light-field image reconstruction algorithm that is compatible with microscale, mesoscale, and macroscale. To fill this gap, we present a real-time and universal network (RTU-Net) to reconstruct high-resolution light-field images at any scale. RTU-Net, as the first network that works over multiscale light-field image reconstruction, employs an adaptive loss function based on generative adversarial theory and consequently exhibits strong generalization capability. We comprehensively assessed the performance of RTU-Net through the reconstruction of multiscale light-field images, including microscale tubulin and mitochondrion dataset, mesoscale synthetic mouse neuro dataset, and macroscale light-field particle imaging velocimetry dataset. The results indicated that RTU-Net has achieved real-time and high-resolution light-field image reconstruction for volume sizes ranging from 300 μm × 300 μm × 12 μm to 25 mm × 25 mm × 25 mm, and demonstrated higher resolution when compared with recently reported light-field reconstruction networks. The high-resolution, strong robustness, high efficiency, and especially the general applicability of RTU-Net will significantly deepen our insight into high-resolution and volumetric imaging.
format Article
id doaj-art-0817523955fd4b5a959ca777053edee8
institution Kabale University
issn 2047-7538
language English
publishDate 2025-04-01
publisher Nature Publishing Group
record_format Article
series Light: Science & Applications
spelling doaj-art-0817523955fd4b5a959ca777053edee82025-08-20T03:52:20ZengNature Publishing GroupLight: Science & Applications2047-75382025-04-0114111910.1038/s41377-025-01842-wReal-time and universal network for volumetric imaging from microscale to macroscale at high resolutionBingzhi Lin0Feng Xing1Liwei Su2Kekuan Wang3Yulan Liu4Diming Zhang5Xusan Yang6Huijun Tan7Zhijing Zhu8Depeng Wang9College of Energy and Power Engineering, Nanjing University of Aeronautics and AstronauticsCollege of Energy and Power Engineering, Nanjing University of Aeronautics and AstronauticsCollege of Energy and Power Engineering, Nanjing University of Aeronautics and AstronauticsCollege of Energy and Power Engineering, Nanjing University of Aeronautics and AstronauticsCollege of Energy and Power Engineering, Nanjing University of Aeronautics and AstronauticsKey Laboratory of Soybean Molecular Design Breeding, National Key Laboratory of Black Soils Conservation and Utilization, Northeast Institute of Geography and Agroecology, Chinese Academy of SciencesInstitute of Physics Chinese Academy of SciencesCollege of Energy and Power Engineering, Nanjing University of Aeronautics and AstronauticsKey Laboratory of Novel Targets and Drug Study for Neural Repair of Zhejiang Province, School of Medicine, Hangzhou City UniversityCollege of Energy and Power Engineering, Nanjing University of Aeronautics and AstronauticsAbstract Light-field imaging has wide applications in various domains, including microscale life science imaging, mesoscale neuroimaging, and macroscale fluid dynamics imaging. The development of deep learning-based reconstruction methods has greatly facilitated high-resolution light-field image processing, however, current deep learning-based light-field reconstruction methods have predominantly concentrated on the microscale. Considering the multiscale imaging capacity of light-field technique, a network that can work over variant scales of light-field image reconstruction will significantly benefit the development of volumetric imaging. Unfortunately, to our knowledge, no one has reported a universal high-resolution light-field image reconstruction algorithm that is compatible with microscale, mesoscale, and macroscale. To fill this gap, we present a real-time and universal network (RTU-Net) to reconstruct high-resolution light-field images at any scale. RTU-Net, as the first network that works over multiscale light-field image reconstruction, employs an adaptive loss function based on generative adversarial theory and consequently exhibits strong generalization capability. We comprehensively assessed the performance of RTU-Net through the reconstruction of multiscale light-field images, including microscale tubulin and mitochondrion dataset, mesoscale synthetic mouse neuro dataset, and macroscale light-field particle imaging velocimetry dataset. The results indicated that RTU-Net has achieved real-time and high-resolution light-field image reconstruction for volume sizes ranging from 300 μm × 300 μm × 12 μm to 25 mm × 25 mm × 25 mm, and demonstrated higher resolution when compared with recently reported light-field reconstruction networks. The high-resolution, strong robustness, high efficiency, and especially the general applicability of RTU-Net will significantly deepen our insight into high-resolution and volumetric imaging.https://doi.org/10.1038/s41377-025-01842-w
spellingShingle Bingzhi Lin
Feng Xing
Liwei Su
Kekuan Wang
Yulan Liu
Diming Zhang
Xusan Yang
Huijun Tan
Zhijing Zhu
Depeng Wang
Real-time and universal network for volumetric imaging from microscale to macroscale at high resolution
Light: Science & Applications
title Real-time and universal network for volumetric imaging from microscale to macroscale at high resolution
title_full Real-time and universal network for volumetric imaging from microscale to macroscale at high resolution
title_fullStr Real-time and universal network for volumetric imaging from microscale to macroscale at high resolution
title_full_unstemmed Real-time and universal network for volumetric imaging from microscale to macroscale at high resolution
title_short Real-time and universal network for volumetric imaging from microscale to macroscale at high resolution
title_sort real time and universal network for volumetric imaging from microscale to macroscale at high resolution
url https://doi.org/10.1038/s41377-025-01842-w
work_keys_str_mv AT bingzhilin realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution
AT fengxing realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution
AT liweisu realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution
AT kekuanwang realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution
AT yulanliu realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution
AT dimingzhang realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution
AT xusanyang realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution
AT huijuntan realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution
AT zhijingzhu realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution
AT depengwang realtimeanduniversalnetworkforvolumetricimagingfrommicroscaletomacroscaleathighresolution