Efficient and accurate inversion of multiple scattering with deep learning

Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography. The reconstruction problem is often formulated as a nonconvex optimization, where a nonlinear measurement model is used to account for multiple scattering and regularization is used to enforce prior constraints on the object. In this paper, we propose a powerful alternative to this optimization-based view of image reconstruction by designing and training a deep convolutional neural network that can invert multiple scattered measurements to produce a high-quality image of the refractive index. Our results on both simulated and experimental datasets show that the proposed approach is substantially faster and achieves higher imaging quality compared to the state-of-the-art methods based on optimization.

[1]  C. Eyraud,et al.  Free space experimental scattering database continuation: experimental set-up and measurement precision , 2005 .

[2]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[3]  E. Wolf,et al.  Principles of Optics (7th Ed) , 1999 .

[4]  Yongjin Sung,et al.  Deterministic regularization of three-dimensional optical diffraction tomography. , 2011, Journal of the Optical Society of America. A, Optics, image science, and vision.

[5]  P. Chaumet,et al.  Electromagnetic wave imaging of three-dimensional targets using a hybrid iterative inversion method , 2012 .

[6]  Stefan Roth,et al.  Shrinkage Fields for Effective Image Restoration , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Hassan Mansour,et al.  A Recursive Born Approach to Nonlinear Inverse Scattering , 2016, IEEE Signal Processing Letters.

[8]  Michael Unser,et al.  Efficient Inversion of Multiple-Scattering Model for Optical Diffraction Tomography , 2017, Optics express.

[9]  Marc Teboulle,et al.  Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems , 2009, IEEE Transactions on Image Processing.

[10]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[11]  Justin Lee,et al.  Lensless computational imaging through deep learning , 2017, ArXiv.

[12]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

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

[14]  C. Fang-Yen,et al.  Optical diffraction tomography for high resolution live cell imaging. , 2009, Optics express.

[15]  C. Fang-Yen,et al.  Tomographic phase microscopy , 2008, Nature Methods.

[16]  Hassan Mansour,et al.  Learning Optimal Nonlinearities for Iterative Thresholding Algorithms , 2015, IEEE Signal Processing Letters.

[17]  P. Chaumet,et al.  Superresolution in total internal reflection tomography. , 2005, Journal of the Optical Society of America. A, Optics, image science, and vision.

[18]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[19]  Hassan Mansour,et al.  Accelerated Image Reconstruction for Nonlinear Diffractive Imaging , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

[21]  Daniel L Marks,et al.  Compressive holography. , 2009, Optics express.

[22]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[23]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[24]  Jong Chul Ye,et al.  Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis , 2016, ArXiv.

[25]  Im,et al.  Versatile reconstruction framework for diffraction tomography with intensity measurements and multiple scattering , 2018 .

[26]  Jong Chul Ye,et al.  Comparative study of iterative reconstruction algorithms for missing cone problems in optical diffraction tomography. , 2015, Optics express.

[27]  F. Schmitt,et al.  Linear inverse problems in imaging , 2008, IEEE Signal Processing Magazine.

[28]  Philip Schniter,et al.  Onsager-Corrected Deep Networks for Sparse Linear Inverse Problems , 2016, ArXiv.

[29]  Hassan Mansour,et al.  SEAGLE: Sparsity-Driven Image Reconstruction Under Multiple Scattering , 2017, IEEE Transactions on Computational Imaging.

[30]  José M. Bioucas-Dias,et al.  Fast Image Recovery Using Variable Splitting and Constrained Optimization , 2009, IEEE Transactions on Image Processing.

[31]  Michael Unser,et al.  Learning approach to optical tomography , 2015, 1502.01914.

[32]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[33]  Anne Sentenac,et al.  High-resolution optical diffraction microscopy. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

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

[35]  Wei Yu,et al.  On learning optimized reaction diffusion processes for effective image restoration , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  L. Tian,et al.  3D intensity and phase imaging from light field measurements in an LED array microscope , 2015 .

[37]  Demetri Psaltis,et al.  Optical Tomographic Image Reconstruction Based on Beam Propagation and Sparse Regularization , 2016, IEEE Transactions on Computational Imaging.

[38]  Jong Chul Ye,et al.  DR AF T Deep Learning Can Reverse Photon Migration for Diffuse Optical Tomography , 2017 .

[39]  Richard G. Baraniuk,et al.  A deep learning approach to structured signal recovery , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[40]  Hugues Giovannini,et al.  Far-field diffraction microscopy at λ/10 resolution , 2016 .

[41]  Jong Chul Ye,et al.  Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems , 2017, SIAM J. Imaging Sci..

[42]  E. Wolf Three-dimensional structure determination of semi-transparent objects from holographic data , 1969 .

[43]  Sundeep Rangan,et al.  AMP-Inspired Deep Networks for Sparse Linear Inverse Problems , 2016, IEEE Transactions on Signal Processing.