Deep learning-enhanced light-field imaging with continuous validation
(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:
https://lup.lub.lu.se/record/08f256f9-fe0a-4f92-ad39-8af163e441bf
- author
- Wagner, Nils ; Beuttenmueller, Fynn ; Norlin, Nils LU ; Gierten, Jakob ; Wittbrodt, Joachim ; Weigert, Martin ; Hufnagel, Lars ; Prevedel, Robert and Kreshuk, Anna
- organization
- publishing date
- 2020-07-31
- 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}}, }