Deep learning-enhanced light-field imaging with continuous validation

• Verfasst von: Wagner, Nils [VerfasserIn]
• Verfasst von: Beuttenmueller, Fynn [VerfasserIn]
• Verfasst von: Norlin, Nils [VerfasserIn]
• Verfasst von: Gierten, Jakob [VerfasserIn]
• Verfasst von: Boffi, Juan Carlos [VerfasserIn]
• Verfasst von: Wittbrodt, Joachim [VerfasserIn]
• Verfasst von: Weigert, Martin [VerfasserIn]
• Verfasst von: Hufnagel, Lars [VerfasserIn]
• Verfasst von: Prevedel, Robert [VerfasserIn]
• Verfasst von: Kreshuk, Anna [VerfasserIn]
• Titel: Deep learning-enhanced light-field imaging with continuous validation
• Verf.angabe: Nils Wagner, Fynn Beuttenmueller, Nils Norlin, Jakob Gierten, Juan Carlos Boffi, Joachim Wittbrodt, Martin Weigert, Lars Hufnagel, Robert Prevedel and Anna Kreshuk
• E-Jahr: 2021
• Jahr: 7 May 2021
• Umfang: 7 S.
• Teil: volume:18
• Teil: year:2021
• Teil: number:5
• Teil: pages:557-563
• Teil: extent:7
• Fussnoten: 13 Seiten Anhang ; Gesehen am 29.06.2021
• Titel Quelle: Enthalten in: Nature methods
• Ort Quelle: London [u.a.] : Nature Publishing Group, 2004
• Jahr Quelle: 2021
• Band/Heft Quelle: 18(2021), 5, Seite 557-563
• ISSN Quelle: 1548-7105
• DOI: doi:10.1038/s41592-021-01136-0
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1761425226

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 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.