Deep learning-enhanced light-field imaging with continuous validation
(2021) In Nature Methods 18(5). p.557-563- Abstract
Visualizing dynamic processes over large, three-dimensional fields of view at high speed is essential for many applications in the life sciences. Light-field microscopy (LFM) has emerged as a tool for fast volumetric image acquisition, but its effective throughput and widespread use in biology has been hampered by a computationally demanding and artifact-prone image reconstruction process. Here, we present a framework for artificial intelligence-enhanced microscopy, integrating a hybrid light-field light-sheet microscope and deep learning-based volume reconstruction. In our approach, concomitantly acquired, high-resolution two-dimensional light-sheet images continuously serve as training data and validation for the convolutional neural... (More)
Visualizing dynamic processes over large, three-dimensional fields of view at high speed is essential for many applications in the life sciences. Light-field microscopy (LFM) has emerged as a tool for fast volumetric image acquisition, but its effective throughput and widespread use in biology has been hampered by a computationally demanding and artifact-prone image reconstruction process. Here, we present a framework for artificial intelligence-enhanced microscopy, integrating a hybrid light-field light-sheet microscope and deep learning-based volume reconstruction. In our approach, concomitantly acquired, high-resolution two-dimensional light-sheet images continuously serve as training data and validation for the convolutional neural network reconstructing the raw LFM data during extended volumetric time-lapse imaging experiments. Our network delivers high-quality three-dimensional reconstructions at video-rate throughput, which can be further refined based on the high-resolution light-sheet images. We demonstrate the capabilities of our approach by imaging medaka heart dynamics and zebrafish neural activity with volumetric imaging rates up to 100 Hz.
(Less)
- author
- Wagner, Nils ; Beuttenmueller, Fynn ; Norlin, Nils LU ; Gierten, Jakob ; Boffi, Juan Carlos ; Wittbrodt, Joachim ; Weigert, Martin ; Hufnagel, Lars ; Prevedel, Robert and Kreshuk, Anna
- organization
- publishing date
- 2021-05
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Nature Methods
- volume
- 18
- issue
- 5
- pages
- 557 - 563
- publisher
- Nature Publishing Group
- external identifiers
-
- pmid:33963344
- scopus:85105450059
- ISSN
- 1548-7105
- DOI
- 10.1038/s41592-021-01136-0
- language
- English
- LU publication?
- yes
- id
- 24dfdeda-5006-482b-ba55-0d120dd89f7c
- date added to LUP
- 2021-05-14 20:02:22
- date last changed
- 2024-11-18 03:37:47
@article{24dfdeda-5006-482b-ba55-0d120dd89f7c, abstract = {{<p>Visualizing dynamic processes over large, three-dimensional fields of view at high speed is essential for many applications in the life sciences. Light-field microscopy (LFM) has emerged as a tool for fast volumetric image acquisition, but its effective throughput and widespread use in biology has been hampered by a computationally demanding and artifact-prone image reconstruction process. Here, we present a framework for artificial intelligence-enhanced microscopy, integrating a hybrid light-field light-sheet microscope and deep learning-based volume reconstruction. In our approach, concomitantly acquired, high-resolution two-dimensional light-sheet images continuously serve as training data and validation for the convolutional neural network reconstructing the raw LFM data during extended volumetric time-lapse imaging experiments. Our network delivers high-quality three-dimensional reconstructions at video-rate throughput, which can be further refined based on the high-resolution light-sheet images. We demonstrate the capabilities of our approach by imaging medaka heart dynamics and zebrafish neural activity with volumetric imaging rates up to 100 Hz.</p>}}, author = {{Wagner, Nils and Beuttenmueller, Fynn and Norlin, Nils and Gierten, Jakob and Boffi, Juan Carlos and Wittbrodt, Joachim and Weigert, Martin and Hufnagel, Lars and Prevedel, Robert and Kreshuk, Anna}}, issn = {{1548-7105}}, language = {{eng}}, number = {{5}}, pages = {{557--563}}, publisher = {{Nature Publishing Group}}, series = {{Nature Methods}}, title = {{Deep learning-enhanced light-field imaging with continuous validation}}, url = {{http://dx.doi.org/10.1038/s41592-021-01136-0}}, doi = {{10.1038/s41592-021-01136-0}}, volume = {{18}}, year = {{2021}}, }