Improved 3D image reconstruction via deep-learning-based fusion of light-field microscopy and Fourier light-field microscopy images.

Overview

1. Shenzhen University, Institute of Microscale Optoelectronics and Shenzhen Key Laboratory of Microscale Optical Information Technology, Nanophotonics Research Center, Shenzhen, China
2. Hunan Institute of Science and Technology, Yueyang, China

Abstract

Significance: Light-field microscopy (LFM) is a scanning-free 3D imaging technique that is useful for observing dynamic biological systems due to its unique capability to capture both spatial and angular information from samples in a single exposure. However, LFM suffers from the spatial–angular information trade-off associated with microlens arrays, and its spatial resolution is usually unsatisfactory for fine-structure imaging.

Aim: To overcome this bottleneck, we introduce a deep-learning-based image fusion technique that combines LFM images with Fourier LFM (FLFM) images. The high spatial resolution of FLFM is combined with the dense angular acquisition capability of LFM to improve 3D image reconstruction quality.

Approach: The deep learning network was trained with LFM, FLFM, and epipolar plane image data. The proposed neural network employs specialized feature extraction modules for each modality, with a U-Net backbone for 3D reconstruction, and integrates a hierarchical cascade-based result-level fusion strategy to jointly optimize multimodal features. This approach significantly enhances detail preservation and depth recovery in the final output.

Results: Results obtained using a publicly available dataset of synthetic tubulins demonstrate that the proposed method outperforms state-of-the-art techniques. Quantitatively, it achieved a peak signal-to-noise ratio (PSNR) of 38.4729 and a structural similarity index measure (SSIM) of 0.9876, significantly outperforming both traditional algorithms and single-modality deep learning approaches. Furthermore, validation on a mouse brain blood vessels dataset confirms the effectiveness of the method in reconstructing biological structures, achieving a PSNR of 35.0548 and an SSIM of 0.8424.

Conclusions: We introduce an approach that combines LFM with FLFM, providing an efficient and reliable solution for practical LFM applications. The deep-learning-based framework demonstrates significant potential to simultaneously accelerate imaging acquisition and enhance 3D reconstruction quality, offering further possibilities for computational microscopy.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repository

Its files are read in the Code ↔ Paper reader above.

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

• 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
• 0 scripts, each with its path and the digest of its content;
• no match between paragraphs and code yet;
• neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Code and Data Availability

The code used in this study will be published on https://github.com/yyy-ou/LFM-FLFM-Net to ensure reproducibility. Data and materials are available upon request from the authors.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 30 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 6 keywords, 7 MeSH terms, 1 funder, 44 references.

Cite

This paper

Ouyang, E., Liang, L., Zhou, X., Zhao, L., & Fang, H. (2026). Improved 3D image reconstruction via deep-learning-based fusion of light-field microscopy and Fourier light-field microscopy images. Journal of biomedical optics, 31(3), 036002. https://doi.org/10.1117/1.jbo.31.3.036002

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41467-026-74976-z [code]

Real-time robust autofocus method enabling sustained intravital scanning light field imaging.

Journal: Nature communications

In common: histology / microscopy, mouse, 4 references

[2] doi:10.1038/s41592-026-03179-7 [code]

Voltage imaging of neurons distributed across entire brains of larval zebrafish.

Journal: Nature methods

In common: histology / microscopy, 3 references

[3] doi:10.1038/s41467-026-72437-1 [code]

High-speed whole-brain imaging in Drosophila.

Journal: Nature communications

In common: 3 references

[4] doi:10.1016/j.isci.2026.116769 [code]

Graph-based modeling of optical system enables adaptive optics on dynamic samples with self-calibration.

Journal: iScience

In common: 2 references

[5] doi:10.1038/s41592-026-03066-1 [code]

A multimodal adaptive optical microscope for in vivo imaging from molecules to organisms.

Journal: Nature methods

In common: histology / microscopy, mouse, 1 reference

[6] doi:10.1038/s41467-026-71746-9

Double-helix optical point spread function enables real-time mesoscopic 3D functional microangiography in the living mouse brain and skull.

Journal: Nature communications

In common: histology / microscopy, mouse, 1 reference

[7] doi:10.1038/s41377-026-02337-y [code]

Multispectral extended depth-of-field fluorescence microscopy with co-designed meta-optics and neural reconstruction.

Journal: Light, science & applications

In common: histology / microscopy, 1 reference

[8] doi:10.1007/s12021-026-09785-2

Template-Based Label Propagation for Mouse Brain MRI Skull Stripping.

Journal: Neuroinformatics

In common: methods / tools, mouse, 1 reference

[9] doi:10.1016/j.neuron.2026.07.016 [code]

Inferring brain-wide interactions using data-constrained recurrent neural network models.

Journal: Neuron

In common: mouse, 1 reference

[10] doi:10.3390/diagnostics16172806

Brain Tumor Segmentation and Grading on MRI Using Deep Learning: A Systematic Literature Review and Benchmark-Driven Comparative Analysis.

Journal: Diagnostics (Basel, Switzerland)

In common: methods / tools, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.