Deep-3D microscope: 3D volumetric microscopy of thick scattering samples using a wide-field microscope and machine learning

Simple item page
dc.citation.firstpage284
dc.citation.issueNumber1
dc.citation.journalTitleBiomedical Optics Express
dc.citation.lastpage299
dc.citation.volumeNumber13
dc.contributor.authorLi, Bowen
dc.contributor.authorTan, Shiyu
dc.contributor.authorDong, Jiuyang
dc.contributor.authorLian, Xiaocong
dc.contributor.authorZhang, Yongbing
dc.contributor.authorJi, Xiangyang
dc.contributor.authorJi, Xiangyang
dc.contributor.authorVeeraraghavan, Ashok
dc.contributor.authorVeeraraghavan, Ashok
dc.date.accessioned2022-01-21T16:24:01Z
dc.date.available2022-01-21T16:24:01Z
dc.date.issued2022
dc.description.abstractConfocal microscopy is a standard approach for obtaining volumetric images of a sample with high axial and lateral resolution, especially when dealing with scattering samples. Unfortunately, a confocal microscope is quite expensive compared to traditional microscopes. In addition, the point scanning in confocal microscopy leads to slow imaging speed and photobleaching due to the high dose of laser energy. In this paper, we demonstrate how the advances in machine learning can be exploited to "teach" a traditional wide-field microscope, one that’s available in every lab, into producing 3D volumetric images like a confocal microscope. The key idea is to obtain multiple images with different focus settings using a wide-field microscope and use a 3D generative adversarial network (GAN) based neural network to learn the mapping between the blurry low-contrast image stacks obtained using a wide-field microscope and the sharp, high-contrast image stacks obtained using a confocal microscope. After training the network with widefield-confocal stack pairs, the network can reliably and accurately reconstruct 3D volumetric images that rival confocal images in terms of its lateral resolution, z-sectioning and image contrast. Our experimental results demonstrate generalization ability to handle unseen data, stability in the reconstruction results, high spatial resolution even when imaging thick (∼40 microns) highly-scattering samples. We believe that such learning-based microscopes have the potential to bring confocal imaging quality to every lab that has a wide-field microscope.
dc.identifier.citationLi, Bowen, Tan, Shiyu, Dong, Jiuyang, et al.. "Deep-3D microscope: 3D volumetric microscopy of thick scattering samples using a wide-field microscope and machine learning." <i>Biomedical Optics Express,</i> 13, no. 1 (2022) Optica Publishing Group: 284-299. https://doi.org/10.1364/BOE.444488.
dc.identifier.digitalboe-13-1-284
dc.identifier.doihttps://doi.org/10.1364/BOE.444488
dc.identifier.urihttps://hdl.handle.net/1911/111934
dc.language.isoeng
dc.publisherOptica Publishing Group
dc.rightsPublished under the terms of the Optica Open Access Publishing Agreement
dc.rights.urihttps://www.osapublishing.org/library/license_v2.cfm#VOR-OA
dc.titleDeep-3D microscope: 3D volumetric microscopy of thick scattering samples using a wide-field microscope and machine learning
dc.typeJournal article
dc.type.dcmiText
dc.type.publicationpublisher version
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
boe-13-1-284.pdf
Size:
16.28 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications
ECE Publications