Abstract

Imaging through multicore fiber (MCF) is of great significance in the biomedical domain. Although several techniques have been developed to image an object from a signal passing through MCF, these methods are strongly dependent on the surroundings, such as vibration and the temperature fluctuation of the fiber’s environment. In this paper, we apply a new, strong technique called deep learning to reconstruct the phase image through a MCF in which each core is multimode. To evaluate the network, we employ the binary cross-entropy as the loss function of a convolutional neural network (CNN) with improved U-net structure. The high-quality reconstruction of input objects upon spatial light modulation (SLM) can be realized from the speckle patterns of intensity that contain the information about the objects. Moreover, we study the effect of MCF length on image recovery. It is shown that the shorter the fiber, the better the imaging quality. Based on our findings, MCF may have applications in fields such as endoscopic imaging and optical communication.

PDF Article

References

  • View by:
  • |

  1. I. N. Papadopoulos, S. Farahi, C. Moser, and D. PsaltisHigh-resolution, lensless endoscope based on digital scanning through a multimode optical fiberBiomed. Opt. Express20134260270
  2. T. Čižmár and K. DholakiaExploiting multimode waveguides for pure fibre-based imagingNat. Commun.201231027
  3. Y. Choi, C. Yoon, M. Kim, T. D. Yang, C. Fang-Yen, R. R. Dasari, K. J. Lee, and W. ChoiScanner-free and wide-field endoscopic imaging by using a single multimode optical fiberPhys. Rev. Lett.2012109203901
  4. K. Krupa, A. Tonello, B. M. Shalaby, M. Fabert, A. Barthélémy, G. Millot, S. Wabnitz, and V. CoudercSpatial beam self-cleaning in multimode fibresNat. Photonics201711237241
  5. M. Hughes, T. P. Chang, and G.-Z. YangFiber bundle endocytoscopyBiomed. Opt. Express2013427812794
  6. V. Tsvirkun, S. Sivankutty, G. Bouwmans, O. Katz, E. R. Andresen, and H. RigneaultWidefield lensless endoscopy with a multicore fiberOpt. Lett.20164147714774
  7. A. Porat, E. R. Andresen, H. Rigneault, D. Oron, S. Gigan, and O. KatzWidefield lensless imaging through a fiber bundle via speckle correlationsOpt. Express2016241683516855
  8. N. Stasio, C. Moser, and D. PsaltisCalibration-free imaging through a multicore fiber using speckle scanning microscopyOpt. Lett.20164130783081
  9. N. Stasio, D. B. Conkey, C. Moser, and D. PsaltisLight control in a multicore fiber using the memory effectOpt. Express2015233053230544
  10. P. Fan, T. Zhao, and L. SuDeep learning the high variability and randomness inside multimode fibersOpt. Express2019272024120258
  11. P. Caramazza, O. Moran, R. Murray-Smith, and D. FaccioTransmission of natural scene images through a multimode fibreNat. Commun.2019102029
  12. N. Borhani, E. Kakkava, C. Moser, and D. PsaltisLearning to see through multimode fibersOptica20185960966
  13. R. Horisaki, R. Takagi, and J. TanidaLearning-based imaging through scattering mediaOpt. Express2016241373813743
  14. K. Wang, J. Dou, Q. Kemao, J. Di, and J. ZhaoY-Net: a one-to-two deep learning framework for digital holographic reconstructionOpt. Lett.20194447654768
  15. H. Wang, M. Lyu, and G. SitueHoloNet: a learning-based end-to-end approach for in-line digital holographic reconstructionOpt. Express2018262260322614
  16. T. Nguyen, V. Bui, V. Lam, C. B. Raub, L.-C. Chang, and G. NehmetallahAutomatic phase aberration compensation for digital holographic microscopy based on deep learning background detectionOpt. Express2017251504315057
  17. Y. Wu, Y. Rivenson, Y. Zhang, Z. Wei, H. Günaydin, X. Lin, and A. OzcanExtended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recoveryOptica20185704710
  18. Y. L. Cun, Y. Bengio, and G. HintonDeep learningNature2015521436444
  19. S. Aisawa, K. Noguchi, and T. MatsumotoRemote image classification through multimode optical fiber using a neural networkOpt. Lett.199116645647
  20. S. Li, M. Deng, J. Lee, A. Sinha, and G. BarbastathisImaging through glass diffusers using densely connected convolutional networksOptica20185803813
  21. X. Yuan and Y. PuParallel lensless compressive imaging via deep convolutional neural networksOpt. Express20182619621977
  22. C. Park, C. C. Took, and J.-K. SeongMachine learning in biomedical engineeringBiomed. Eng. Lett.2018813
  23. C. M. Sandino, J. Y. Cheng, F. Chen, M. Mardani, J. M. Pauly, and S. S. VasanawalaCompressed sensing: from research to clinical practice with deep neural networks: Shortening Scan Times for Magnetic Resonance ImagingIEEE Signal Process. Mag.202037117127
  24. K. Hammernik, T. Klatzer, E. Kobler, M. P. Recht, D. K. Sodickson, T. Pock, and F. KnollLearning a variational network for reconstruction of accelerated MRI dataMagn. Reson. Med.20187930553071
  25. O. Ronneberger, P. Fischer, and T. BroxU-net: convolutional networks for biomedical image segmentationProc. Medical Image Computing and Computer-Assisted InterventionMunich, Germany2015Oct.234241
  26. G. Huang, Z. Liu, L. V. D. Maaten, and K. Q. WeinbergerDensely connected convolutional networksProc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Honolulu, USA2017Jul.47004708
  27. P. D. Kingma and J. BaAdam: a method for stochastic optimizationProc. the 3rd International Conference for Learning RepresentationsSan Diego, USA2015May
  28. A. Kendall and Y. GalWhat uncertainties do we need in Bayesian deep learning for computer vision?Proc. Neural Information Processing SystemsCA, USA2017Dec.55745584
  29. B. Li, Y. Liu, and X. WangGradient harmonized single-stage detectorProc. AAAI Conference on Artificial IntelligenceHonolulu, USA2019Jan.85778584
  30. L. Wu, W. Fan, Z. Chen, and J. PuFocusing and polarized modulation of a laser passing through multi-core fiberOpt. Rev.201926531536
  31. Y. L. Cun, C. Cortes, and C. J. C. BurgesTHE MNIST DATABASE of handwritten digits (Y. L. Cun, C. Cortes, and C. J. C. Burges)http://yann.lecun.com/exdb/mnist/Accessed date: 2019.06.13
  32. Y. Li, Y. Xue, and L. TianDeep speckle correlation: a deep learning approach toward scalable imaging through scattering mediaOptica2018511811190

Other (32)

I. N. Papadopoulos, S. Farahi, C. Moser, and D. PsaltisHigh-resolution, lensless endoscope based on digital scanning through a multimode optical fiberBiomed. Opt. Express20134260270

T. Čižmár and K. DholakiaExploiting multimode waveguides for pure fibre-based imagingNat. Commun.201231027

Y. Choi, C. Yoon, M. Kim, T. D. Yang, C. Fang-Yen, R. R. Dasari, K. J. Lee, and W. ChoiScanner-free and wide-field endoscopic imaging by using a single multimode optical fiberPhys. Rev. Lett.2012109203901

K. Krupa, A. Tonello, B. M. Shalaby, M. Fabert, A. Barthélémy, G. Millot, S. Wabnitz, and V. CoudercSpatial beam self-cleaning in multimode fibresNat. Photonics201711237241

M. Hughes, T. P. Chang, and G.-Z. YangFiber bundle endocytoscopyBiomed. Opt. Express2013427812794

V. Tsvirkun, S. Sivankutty, G. Bouwmans, O. Katz, E. R. Andresen, and H. RigneaultWidefield lensless endoscopy with a multicore fiberOpt. Lett.20164147714774

A. Porat, E. R. Andresen, H. Rigneault, D. Oron, S. Gigan, and O. KatzWidefield lensless imaging through a fiber bundle via speckle correlationsOpt. Express2016241683516855

N. Stasio, C. Moser, and D. PsaltisCalibration-free imaging through a multicore fiber using speckle scanning microscopyOpt. Lett.20164130783081

N. Stasio, D. B. Conkey, C. Moser, and D. PsaltisLight control in a multicore fiber using the memory effectOpt. Express2015233053230544

P. Fan, T. Zhao, and L. SuDeep learning the high variability and randomness inside multimode fibersOpt. Express2019272024120258

P. Caramazza, O. Moran, R. Murray-Smith, and D. FaccioTransmission of natural scene images through a multimode fibreNat. Commun.2019102029

N. Borhani, E. Kakkava, C. Moser, and D. PsaltisLearning to see through multimode fibersOptica20185960966

R. Horisaki, R. Takagi, and J. TanidaLearning-based imaging through scattering mediaOpt. Express2016241373813743

K. Wang, J. Dou, Q. Kemao, J. Di, and J. ZhaoY-Net: a one-to-two deep learning framework for digital holographic reconstructionOpt. Lett.20194447654768

H. Wang, M. Lyu, and G. SitueHoloNet: a learning-based end-to-end approach for in-line digital holographic reconstructionOpt. Express2018262260322614

T. Nguyen, V. Bui, V. Lam, C. B. Raub, L.-C. Chang, and G. NehmetallahAutomatic phase aberration compensation for digital holographic microscopy based on deep learning background detectionOpt. Express2017251504315057

Y. Wu, Y. Rivenson, Y. Zhang, Z. Wei, H. Günaydin, X. Lin, and A. OzcanExtended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recoveryOptica20185704710

Y. L. Cun, Y. Bengio, and G. HintonDeep learningNature2015521436444

S. Aisawa, K. Noguchi, and T. MatsumotoRemote image classification through multimode optical fiber using a neural networkOpt. Lett.199116645647

S. Li, M. Deng, J. Lee, A. Sinha, and G. BarbastathisImaging through glass diffusers using densely connected convolutional networksOptica20185803813

X. Yuan and Y. PuParallel lensless compressive imaging via deep convolutional neural networksOpt. Express20182619621977

C. Park, C. C. Took, and J.-K. SeongMachine learning in biomedical engineeringBiomed. Eng. Lett.2018813

C. M. Sandino, J. Y. Cheng, F. Chen, M. Mardani, J. M. Pauly, and S. S. VasanawalaCompressed sensing: from research to clinical practice with deep neural networks: Shortening Scan Times for Magnetic Resonance ImagingIEEE Signal Process. Mag.202037117127

K. Hammernik, T. Klatzer, E. Kobler, M. P. Recht, D. K. Sodickson, T. Pock, and F. KnollLearning a variational network for reconstruction of accelerated MRI dataMagn. Reson. Med.20187930553071

O. Ronneberger, P. Fischer, and T. BroxU-net: convolutional networks for biomedical image segmentationProc. Medical Image Computing and Computer-Assisted InterventionMunich, Germany2015Oct.234241

G. Huang, Z. Liu, L. V. D. Maaten, and K. Q. WeinbergerDensely connected convolutional networksProc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Honolulu, USA2017Jul.47004708

P. D. Kingma and J. BaAdam: a method for stochastic optimizationProc. the 3rd International Conference for Learning RepresentationsSan Diego, USA2015May

A. Kendall and Y. GalWhat uncertainties do we need in Bayesian deep learning for computer vision?Proc. Neural Information Processing SystemsCA, USA2017Dec.55745584

B. Li, Y. Liu, and X. WangGradient harmonized single-stage detectorProc. AAAI Conference on Artificial IntelligenceHonolulu, USA2019Jan.85778584

L. Wu, W. Fan, Z. Chen, and J. PuFocusing and polarized modulation of a laser passing through multi-core fiberOpt. Rev.201926531536

Y. L. Cun, C. Cortes, and C. J. C. BurgesTHE MNIST DATABASE of handwritten digits (Y. L. Cun, C. Cortes, and C. J. C. Burges)http://yann.lecun.com/exdb/mnist/Accessed date: 2019.06.13

Y. Li, Y. Xue, and L. TianDeep speckle correlation: a deep learning approach toward scalable imaging through scattering mediaOptica2018511811190

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.