Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural network

Abstract Recent advances in deep learning-based image reconstruction techniques have led to significant progress in phase retrieval using digital in-line holographic microscopy (DIHM). However, existing phase retrieval methods have technical limitations in 3D morphology reconstruction from single-sh...

Full description

Saved in:
Bibliographic Details
Main Authors: Jihwan Kim, Youngdo Kim, Hyo Seung Lee, Eunseok Seo, Sang Joon Lee
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-60200-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769005575831552
author Jihwan Kim
Youngdo Kim
Hyo Seung Lee
Eunseok Seo
Sang Joon Lee
author_facet Jihwan Kim
Youngdo Kim
Hyo Seung Lee
Eunseok Seo
Sang Joon Lee
author_sort Jihwan Kim
collection DOAJ
description Abstract Recent advances in deep learning-based image reconstruction techniques have led to significant progress in phase retrieval using digital in-line holographic microscopy (DIHM). However, existing phase retrieval methods have technical limitations in 3D morphology reconstruction from single-shot holograms of biological cells. In this study, we propose a deep learning model, named MorpHoloNet, for single-shot reconstruction of 3D morphology by integrating physics-driven and coordinate-based neural networks. By simulating optical diffraction of coherent light through a 3D phase shift distribution, MorpHoloNet is optimized by minimizing the loss between simulated and input holograms on the detector plane. MorpHoloNet enables direct reconstruction of 3D complex light field and 3D morphology of a test sample from its single-shot hologram without requiring multiple phase-shifted holograms or angular scanning. It would be utilized to reconstruct spatiotemporal variations in 3D translational and rotational behaviors, as well as morphological deformations of biological cells from consecutive single-shot holograms captured using DIHM.
format Article
id doaj-art-2279c1c635f44e3fb509f3366fbd8d40
institution DOAJ
issn 2041-1723
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-2279c1c635f44e3fb509f3366fbd8d402025-08-20T03:03:37ZengNature PortfolioNature Communications2041-17232025-05-0116111510.1038/s41467-025-60200-xSingle-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural networkJihwan Kim0Youngdo Kim1Hyo Seung Lee2Eunseok Seo3Sang Joon Lee4Department of Mechanical Engineering, Pohang University of Science and TechnologyDepartment of Mechanical Engineering, Pohang University of Science and TechnologyDepartment of Mechanical Engineering, Pohang University of Science and TechnologyDepartment of Mechanical Engineering, Sogang UniversityDepartment of Mechanical Engineering, Pohang University of Science and TechnologyAbstract Recent advances in deep learning-based image reconstruction techniques have led to significant progress in phase retrieval using digital in-line holographic microscopy (DIHM). However, existing phase retrieval methods have technical limitations in 3D morphology reconstruction from single-shot holograms of biological cells. In this study, we propose a deep learning model, named MorpHoloNet, for single-shot reconstruction of 3D morphology by integrating physics-driven and coordinate-based neural networks. By simulating optical diffraction of coherent light through a 3D phase shift distribution, MorpHoloNet is optimized by minimizing the loss between simulated and input holograms on the detector plane. MorpHoloNet enables direct reconstruction of 3D complex light field and 3D morphology of a test sample from its single-shot hologram without requiring multiple phase-shifted holograms or angular scanning. It would be utilized to reconstruct spatiotemporal variations in 3D translational and rotational behaviors, as well as morphological deformations of biological cells from consecutive single-shot holograms captured using DIHM.https://doi.org/10.1038/s41467-025-60200-x
spellingShingle Jihwan Kim
Youngdo Kim
Hyo Seung Lee
Eunseok Seo
Sang Joon Lee
Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural network
Nature Communications
title Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural network
title_full Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural network
title_fullStr Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural network
title_full_unstemmed Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural network
title_short Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural network
title_sort single shot reconstruction of three dimensional morphology of biological cells in digital holographic microscopy using a physics driven neural network
url https://doi.org/10.1038/s41467-025-60200-x
work_keys_str_mv AT jihwankim singleshotreconstructionofthreedimensionalmorphologyofbiologicalcellsindigitalholographicmicroscopyusingaphysicsdrivenneuralnetwork
AT youngdokim singleshotreconstructionofthreedimensionalmorphologyofbiologicalcellsindigitalholographicmicroscopyusingaphysicsdrivenneuralnetwork
AT hyoseunglee singleshotreconstructionofthreedimensionalmorphologyofbiologicalcellsindigitalholographicmicroscopyusingaphysicsdrivenneuralnetwork
AT eunseokseo singleshotreconstructionofthreedimensionalmorphologyofbiologicalcellsindigitalholographicmicroscopyusingaphysicsdrivenneuralnetwork
AT sangjoonlee singleshotreconstructionofthreedimensionalmorphologyofbiologicalcellsindigitalholographicmicroscopyusingaphysicsdrivenneuralnetwork