Learning to Reconstruct Confocal Microscopy Stacks From Single Light Field Images

Vizcaino, Josue Page; Saltarin, Federico; Belyaev, Yury; Lyck, Ruth; Lasser, Tobias; Favaro, Paolo (2021). Learning to Reconstruct Confocal Microscopy Stacks From Single Light Field Images. IEEE transactions on computational imaging, 7, pp. 775-788. IEEE 10.1109/TCI.2021.3097611

[img] Text
Learning_to_Reconstruct_Confocal_Microscopy_Stacks_From_Single_Light_Field_Images.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (3MB)

We present a novel deep learning approach to reconstruct confocal microscopy stacks from single light field images. To perform the reconstruction, we introduce LFMNet, a fully convolutional neural network architecture inspired by the U-Net design. A property of LFMNet is its ability to reconstruct with near confocal accuracy a 112 ×112 ×57.6 μm 3 volume (1287×1287×64 voxels) in 50 ms given a single light field image of 1287×1287 pixels, thus dramatically reducing 720-fold the capture time compared to confocal scanning of assays at the same volumetric resolution and 64-fold the required storage. To prove its applicability in life sciences, our approach is evaluated both quantitatively and qualitatively on mouse brain slices with fluorescently labeled blood vessels. Because of the drastic reduction in image acquisition time, our setup and method are suitable for imaging highly dynamic and light-sensitive events, and in closed-loop systems, where latency due to the reconstruction time is crucial. We provide empirical analysis of the optical design, of the network architecture and of our training procedure to reconstruct confocal-like volumes for a given target depth range. To train our network, we built a data set of 362 light field images of the mouse brain sample and the corresponding aligned set of 3D confocal scans, which we use as ground truth. The data set will be made available for research purposes.

Item Type:

Journal Article (Original Article)

Division/Institute:

09 Interdisciplinary Units > Microscopy Imaging Center (MIC)
04 Faculty of Medicine > Pre-clinic Human Medicine > Theodor Kocher Institute

UniBE Contributor:

Saltarin, Federico, Belyaev, Yury, Lyck, Ruth

Subjects:

600 Technology > 610 Medicine & health
500 Science > 570 Life sciences; biology

ISSN:

2333-9403

Publisher:

IEEE

Language:

English

Submitter:

Cindy Carolyn Alpinice Schumacher

Date Deposited:

26 Jan 2022 07:50

Last Modified:

05 Dec 2022 16:00

Publisher DOI:

10.1109/TCI.2021.3097611

BORIS DOI:

10.48350/163638

URI:

https://boris.unibe.ch/id/eprint/163638

Actions (login required)

Edit item Edit item
Provide Feedback