Phase extraction neural network (PhENN) with coherent modulation imaging (CMI) for phase retrieval at low photon counts.

Imaging with low-dose light is of importance in various fields, especially when minimizing radiation-induced damage onto samples is desirable. The raw image captured at the detector plane is then predominantly a Poisson random process with Gaussian noise added due to the quantum nature of photo-electric conversion. Under such noisy conditions, highly ill-posed problems such as phase retrieval from raw intensity measurements become prone to strong artifacts in the reconstructions; a situation that deep neural networks (DNNs) have already been shown to be useful at improving. Here, we demonstrate that random phase modulation on the optical field, also known as coherent modulation imaging (CMI), in conjunction with the phase extraction neural network (PhENN) and a Gerchberg-Saxton-Fienup (GSF) approximant, further improves resilience to noise of the phase-from-intensity imaging problem. We offer design guidelines for implementing the CMI hardware with the proposed computational reconstruction scheme and quantify reconstruction improvement as function of photon count.

[1]  Laura Waller,et al.  Phase from chromatic aberrations. , 2010, Optics express.

[2]  George Barbastathis,et al.  Low Photon Count Phase Retrieval Using Deep Learning. , 2018, Physical review letters.

[3]  R. Gerchberg A practical algorithm for the determination of phase from image and diffraction plane pictures , 1972 .

[4]  Michael Unser,et al.  Three-Dimensional Optical Diffraction Tomography With Lippmann-Schwinger Model , 2020, IEEE Transactions on Computational Imaging.

[5]  Pavel Tomancak,et al.  Assessing phototoxicity in live fluorescence imaging , 2017, Nature Methods.

[6]  D. Gabor A New Microscopic Principle , 1948, Nature.

[7]  Robert W. Boyd,et al.  Imaging with a small number of photons , 2014, Nature Communications.

[8]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[9]  Pierre Ambs,et al.  Cross-talk compensation of a spatial light modulator for iterative phase retrieval applications. , 2016, Applied optics.

[10]  Joydeep Ghosh,et al.  Cluster Ensembles --- A Knowledge Reuse Framework for Combining Multiple Partitions , 2002, J. Mach. Learn. Res..

[11]  Shuai Li,et al.  Spectral pre-modulation of training examples enhances the spatial resolution of the phase extraction neural network (PhENN). , 2018, Optics express.

[12]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[13]  J R Fienup,et al.  Phase retrieval algorithms: a comparison. , 1982, Applied optics.

[14]  Paul S. Fisher,et al.  Image quality measures and their performance , 1995, IEEE Trans. Commun..

[15]  J. H. van Hateren,et al.  Modelling the Power Spectra of Natural Images: Statistics and Information , 1996, Vision Research.

[16]  J. Miao,et al.  Coherent X-Ray Diffraction Imaging , 2012, IEEE Journal of Selected Topics in Quantum Electronics.

[17]  M. D. de Jonge,et al.  Fresnel coherent diffractive imaging. , 2006, Physical review letters.

[18]  A. Matsko,et al.  Probing 10 μK stability and residual drifts in the cross-polarized dual-mode stabilization of single-crystal ultrahigh-Q optical resonators , 2019, Light, science & applications.

[19]  A. Ozcan,et al.  On the use of deep learning for computational imaging , 2019, Optica.

[20]  L. Tian,et al.  Transport of Intensity phase-amplitude imaging with higher order intensity derivatives. , 2010, Optics express.

[21]  Fucai Zhang,et al.  Phase retrieval by coherent modulation imaging , 2016, Nature Communications.

[22]  Yibo Zhang,et al.  Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery , 2018, Optica.

[23]  Keith A. Nugent,et al.  Fresnel coherent diffractive imaging: treatment and analysis of data , 2010 .

[24]  Jubo Zhu,et al.  Single-shot coherent power-spectrum imaging of objects hidden by opaque scattering media. , 2019, Applied optics.

[25]  Shuai Li,et al.  Lensless computational imaging through deep learning , 2017, ArXiv.

[26]  W. Osten,et al.  Characterization of a spatial light modulator and its application in phase retrieval. , 2009, Applied optics.

[27]  B. Chen,et al.  Validity of diffraction tomography based on the first born and the first rytov approximations. , 1998, Applied optics.

[28]  Yibo Zhang,et al.  Phase recovery and holographic image reconstruction using deep learning in neural networks , 2017, Light: Science & Applications.

[29]  Iksung Kang,et al.  Learning to synthesize: robust phase retrieval at low photon counts , 2019, Light, science & applications.

[30]  N. Streibl Phase imaging by the transport equation of intensity , 1984 .

[31]  Konstantina S. Nikita,et al.  Automatic retinal image registration scheme using global optimization techniques , 1999, IEEE Transactions on Information Technology in Biomedicine.

[32]  Guofan Jin,et al.  Single-shot lensless imaging with fresnel zone aperture and incoherent illumination , 2020, Light, science & applications.

[33]  Sameera S. Ponda,et al.  Phase and amplitude imaging from noisy images by Kalman filtering. , 2011, Optics express.

[34]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[35]  J. Rodenburg,et al.  Phase retrieval based on wave-front relay and modulation , 2010 .

[36]  Jianqiang Zhu,et al.  Single shot multi-wavelength phase retrieval with coherent modulation imaging. , 2018, Optics letters.

[37]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[38]  J. Fienup Invariant error metrics for image reconstruction. , 1997, Applied optics.

[39]  Garth J. Williams,et al.  Keyhole coherent diffractive imaging , 2008 .

[40]  George Barbastathis,et al.  High-resolution limited-angle phase tomography of dense layered objects using deep neural networks , 2018, Proceedings of the National Academy of Sciences.

[41]  G. Pedrini,et al.  Phase retrieval of arbitrary complex-valued fields through aperture-plane modulation , 2007 .

[42]  K. Nugent Coherent methods in the X-ray sciences , 2009, 0908.3064.

[43]  Aydogan Ozcan,et al.  Bright-field holography: cross-modality deep learning enables snapshot 3D imaging with bright-field contrast using a single hologram , 2018, Light: Science & Applications.

[44]  O. Bunk,et al.  X-ray ptychographic computed tomography at 16 nm isotropic 3D resolution , 2014, Scientific Reports.

[45]  George Barbastathis,et al.  Probing shallower: perceptual loss trained Phase Extraction Neural Network (PLT-PhENN) for artifact-free reconstruction at low photon budget. , 2020, Optics express.

[46]  Kannan Ramchandran,et al.  Multiplexed coded illumination for Fourier Ptychography with an LED array microscope. , 2014, Biomedical optics express.

[47]  Ichirou Yamaguchi,et al.  Algorithm for reconstruction of digital holograms with adjustable magnification. , 2004, Optics letters.

[48]  L. Tian,et al.  Low-noise phase imaging by hybrid uniform and structured illumination transport of intensity equation. , 2014, Optics express.

[49]  J. Tanida,et al.  Learning-based imaging through scattering media. , 2016, Optics express.

[50]  A. Devaney Inverse-scattering theory within the Rytov approximation. , 1981, Optics letters.

[51]  J. Rodenburg,et al.  An improved ptychographical phase retrieval algorithm for diffractive imaging. , 2009, Ultramicroscopy.

[52]  F. Stellari,et al.  High Energy BSE/SE/STEM Imaging of 8 um Thick Semiconductor Interconnects , 2014 .