Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Deep learning-enhanced light-field imaging with continuous validation

Wagner, Nils ; Beuttenmueller, Fynn ; Norlin, Nils LU ; Gierten, Jakob ; Wittbrodt, Joachim ; Weigert, Martin ; Hufnagel, Lars ; Prevedel, Robert and Kreshuk, Anna (2020) In bioRxiv
Abstract
Light field microscopy (LFM) has emerged as a powerful tool for fast volumetric image acquisition in biology, but its effective throughput and widespread use has been hampered by a computationally demanding and artefact-prone image reconstruction process. Here, we present a novel framework consisting of a hybrid light-field light-sheet microscope and deep learning-based volume reconstruction, where single light-sheet acquisitions continuously serve as training data and validation for the convolutional neural network reconstructing the LFM volume. Our network delivers high-quality reconstructions at video-rate throughput and we demonstrate the capabilities of our approach by imaging medaka heart dynamics and zebrafish neural activity.
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; and
organization
publishing date
type
Working paper/Preprint
publication status
published
subject
in
bioRxiv
pages
24 pages
publisher
bioRxiv
DOI
10.1101/2020.07.30.228924
language
English
LU publication?
yes
id
08f256f9-fe0a-4f92-ad39-8af163e441bf
date added to LUP
2020-09-09 18:23:46
date last changed
2022-06-29 10:53:23
@misc{08f256f9-fe0a-4f92-ad39-8af163e441bf,
  abstract     = {{Light field microscopy (LFM) has emerged as a powerful tool for fast volumetric image acquisition in biology, but its effective throughput and widespread use has been hampered by a computationally demanding and artefact-prone image reconstruction process. Here, we present a novel framework consisting of a hybrid light-field light-sheet microscope and deep learning-based volume reconstruction, where single light-sheet acquisitions continuously serve as training data and validation for the convolutional neural network reconstructing the LFM volume. Our network delivers high-quality reconstructions at video-rate throughput and we demonstrate the capabilities of our approach by imaging medaka heart dynamics and zebrafish neural activity.}},
  author       = {{Wagner, Nils and Beuttenmueller, Fynn and Norlin, Nils and Gierten, Jakob and Wittbrodt, Joachim and Weigert, Martin and Hufnagel, Lars and Prevedel, Robert and Kreshuk, Anna}},
  language     = {{eng}},
  month        = {{07}},
  note         = {{Preprint}},
  publisher    = {{bioRxiv}},
  series       = {{bioRxiv}},
  title        = {{Deep learning-enhanced light-field imaging with continuous validation}},
  url          = {{http://dx.doi.org/10.1101/2020.07.30.228924}},
  doi          = {{10.1101/2020.07.30.228924}},
  year         = {{2020}},
}