Show simple item record

dc.contributor.authorStröhl, Florian
dc.contributor.authorJadhav, Suyog
dc.contributor.authorAhluwalia, Balpreet Singh
dc.contributor.authorAgarwal, Krishna
dc.contributor.authorPrasad, Dilip K.
dc.date.accessioned2020-12-23T10:54:10Z
dc.date.available2020-12-23T10:54:10Z
dc.date.issued2020-11-23
dc.description.abstractHigh resolution microscopy is heavily dependent on superb optical elements and superresolution microscopy even more so. Correcting unavoidable optical aberrations during post-processing is an elegant method to reduce the optical system’s complexity. A prime method that promises superresolution, aberration correction, and quantitative phase imaging is Fourier ptychography. This microscopy technique combines many images of the sample, recorded at differing illumination angles akin to computed tomography and uses error minimisation between the recorded images with those generated by a forward model. The more precise knowledge of those illumination angles is available for the image formation forward model, the better the result. Therefore, illumination estimation from the raw data is an important step and supports correct phase recovery and aberration correction. Here, we derive how illumination estimation can be cast as an object detection problem that permits the use of a fast convolutional neural network (CNN) for this task. We find that faster-RCNN delivers highly robust results and outperforms classical approaches by far with an up to 3-fold reduction in estimation errors. Intriguingly, we find that conventionally beneficial smoothing and filtering of raw data is counterproductive in this type of application. We present a detailed analysis of the network’s performance and provide all our developed software openly.en_US
dc.identifier.citationStröhl F, Jadhav, Ahluwalia BS, Agarwal K, Prasad DK. Object detection neural network improves Fourier ptychography reconstruction. Optics Express. 2020;28(25):37199-37208en_US
dc.identifier.cristinIDFRIDAID 1851422
dc.identifier.doi10.1364/OE.409679
dc.identifier.issn1094-4087
dc.identifier.urihttps://hdl.handle.net/10037/20131
dc.language.isoengen_US
dc.publisherThe Optical Society of America (OSA)en_US
dc.relation.journalOptics Express
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/BIOTEK2021/285571/Norway/Optimalisering: High-throughput and high-resolution pathology using chip-based nanoscopy//en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/FP7/336716/EU/High-speed chip-based nanoscopy to discover real-time sub-cellular dynamics/NANOSCOPY/en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/804233/EU/Label-free 3D morphological nanoscopy for studying sub-cellular dynamics in live cancer cells with high spatio-temporal resolution/3D-nanoMorph/en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/836355/EU/Development of Deep-UV Quantitative Microscopy for the Study of Mitochondrial Dysfunction/MitoQuant/en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2020 Optical Society of Americaen_US
dc.subjectVDP::Mathematics and natural science: 400::Physics: 430::Electromagnetism, acoustics, optics: 434en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Fysikk: 430::Elektromagnetisme, akustikk, optikk: 434en_US
dc.titleObject detection neural network improves Fourier ptychography reconstructionen_US
dc.type.versionpublishedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record