Dataset Information

Multimode optical fiber transmission with a deep learning network.

ABSTRACT: Multimode fibers (MMFs) are an example of a highly scattering medium, which scramble the coherent light propagating within them to produce seemingly random patterns. Thus, for applications such as imaging and image projection through an MMF, careful measurements of the relationship between the inputs and outputs of the fiber are required. We show, as a proof of concept, that a deep neural network can learn the input-output relationship in a 0.75?m long MMF. Specifically, we demonstrate that a deep convolutional neural network (CNN) can learn the nonlinear relationships between the amplitude of the speckle pattern (phase information lost) obtained at the output of the fiber and the phase or the amplitude at the input of the fiber. Effectively, the network performs a nonlinear inversion task. We obtained image fidelities (correlations) as high as ~98% for reconstruction and ~94% for image projection in the MMF compared with the image recovered using the full knowledge of the system transmission characterized with the complex measured matrix. We further show that the network can be trained for transfer learning, i.e., it can transmit images through the MMF, which belongs to another class not used for training/testing.

SUBMITTER: Rahmani B

PROVIDER: S-EPMC6168552 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multimode optical fiber transmission with a deep learning network.

Rahmani Babak B Loterie Damien D Konstantinou Georgia G Psaltis Demetri D Moser Christophe C

Light, science & applications 20181003

Multimode fibers (MMFs) are an example of a highly scattering medium, which scramble the coherent light propagating within them to produce seemingly random patterns. Thus, for applications such as imaging and image projection through an MMF, careful measurements of the relationship between the inputs and outputs of the fiber are required. We show, as a proof of concept, that a deep neural network can learn the input-output relationship in a 0.75 m long MMF. Specifically, we demonstrate that a de ...[more]

PMID: 30302240

Similar Datasets

Project description:SIGNIFICANCE:Noninvasive in vivo fast pulsatile blood flow measurement in deep tissue is important because the blood flow waveform is correlated with physiological parameters, such as blood pressure and elasticity of blood vessels. Compromised blood flow may cause diseases, such as stroke, foot ulcer, and myocardial ischemia. There is great clinical demand for a portable and cost-effective device for noninvasive pulsatile blood flow measurement. AIM:A diffuse-optics-based method, diffuse speckle pulsatile flowmetry (DSPF), was developed for fast measurement (?300??Hz) of deep tissue blood flow noninvasively. To validate its performance, both a phantom experiment and in vivo demonstration were conducted. APPROACH:Over the past two decades, single-mode fibers have been used as detection fibers in most diffuse-optics-based deep tissue blood flow measurement modalities. We used a multimode (MM) detection fiber with a core size of 200???m for diffused speckle pattern detection. A background intensity correction algorithm was implemented for speckle contrast calculation. The MM detection fiber helped to achieve a level of deep tissue blood flow measurement similar to that of conventional modalities, such as diffuse correlation spectroscopy and diffuse speckle contrast analysis, but it increases the measurement rate of blood flow to 300 Hz. RESULTS:The design and implementation of the DSPF system were introduced. The theory of the background intensity correction for the diffused speckle pattern detected by the MM fiber was explained. A flow phantom was built for validation of the performance of the DSPF system. An in vivo cuff-induced occlusion experiment was performed to demonstrate the capability of the proposed DSPF system. CONCLUSIONS:An MM detection fiber can help to achieve fast (?300??Hz) pulsatile blood flow measurement in the proposed DSPF method. The cost-effective device and the fiber-based flexible probe increase the usability of the DSPF system significantly.

Dataset Information

Multimode optical fiber transmission with a deep learning network.

Publications

Multimode optical fiber transmission with a deep learning network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure