Light Advanced Manufacturing · 2024 · 15 citations · 58 references
EngineeringBioengineeringBiomedical EngineeringBiomedical ImagingBiomedical OpticsDiagnostic Imaging3D ImagingBrain ImagingCellular ImagingFluorescence ImagingMedical ImagingOptical ImagingBiomedical ApplicationsFiber-optic EndoscopesFiber-optic EndoscopyFluorescence EndoscopyIncoherent ImagingReal-time ImagingSingle ShotSingle-shot Imaging
Minimally invasive endoscopy offers a high potential for biomedical imaging applications. However, conventional fiberoptic endoscopes require lens systems which are not suitable for real-time 3D imaging. Instead, a diffuser is utilized for passively encoding incoherent 3D objects into 2D speckle patterns. Neural networks are employed for fast computational image reconstruction beyond the optical memory effect. In this paper, we demonstrate single-shot 3D incoherent fiber imaging with keyhole access at video rate. Applying the diffuser fiber endoscope for fluorescence imaging is promising for in vivo deep brain diagnostics with cellular resolution.
58
On the use of deep learning for computational imaging
George Barbastathis, Aydogan Özcan, Guohai Situ · Optica · 2019 · 830 citations · Full text
Deep learning enables cross-modality super-resolution in fluorescence microscopy
Hongda Wang, Yair Rivenson, Yiyin Jin et al. · Nature Methods · 2018 · 802 citations · Full text