Deep transfer learning-based hologram classification for molecular diagnostics

Lens-free digital in-line holography (LDIH) is a promising microscopic tool that overcomes several drawbacks (e.g., limited field of view) of traditional lens-based microcopy. However, extensive computation is required to reconstruct object images from the complex diffraction patterns produced by LDIH, which limits LDIH utility for point-of-care applications, particularly in resource limited settings. Here, we describe a deep transfer learning (DTL) based approach to process LDIH images in the context of cellular analyses. Specifically, we captured holograms of cells labeled with molecular-specific microbeads and trained neural networks to classify these holograms without reconstruction. Using raw holograms as input, the trained networks were able to classify individual cells according to the number of cell-bound microbeads. The DTL-based approach including a VGG19 pretrained network showed robust performance even with noisy experimental data. Combined with the developed DTL approach, LDIH could be realized as a low-cost, portable tool for point-of-care diagnostics.

[1]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[2]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Feng Xu,et al.  Miniaturized lensless imaging systems for cell and microorganism visualization in point‐of‐care testing , 2011, Biotechnology journal.

[4]  J R Fienup,et al.  Reconstruction of an object from the modulus of its Fourier transform. , 1978, Optics letters.

[5]  Aydogan Ozcan,et al.  Increased space-bandwidth product in pixel super-resolved lensfree on-chip microscopy , 2013, Scientific Reports.

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

[7]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[8]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[9]  Peter Klages,et al.  Digital in-line holographic microscopy. , 2006, Applied optics.

[10]  Andrew H. Beck,et al.  Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer , 2017, JAMA.

[11]  Lorien Y. Pratt,et al.  Discriminability-Based Transfer between Neural Networks , 1992, NIPS.

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

[13]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[14]  Christoph Meinel,et al.  Deep Learning for Medical Image Analysis , 2018, Journal of Pathology Informatics.

[15]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[16]  Vikas Sindhwani,et al.  Information Theoretic Feature Crediting in Multiclass Support Vector Machines , 2001, SDM.

[17]  Fujio Shimizu,et al.  Fresnel diffraction mirror for an atomic wave. , 2005, Physical review letters.

[18]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[19]  Hongying Zhu,et al.  Optical imaging techniques for point-of-care diagnostics. , 2013, Lab on a chip.

[20]  T. Latychevskaia,et al.  Solution to the twin image problem in holography. , 2006, Physical review letters.

[21]  Constantin F. Aliferis,et al.  A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification , 2008, BMC Bioinformatics.

[22]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[23]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[24]  Terry Taewoong Um,et al.  Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database , 2017, PloS one.

[25]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[26]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[27]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[28]  Cesar M. Castro,et al.  Holographic Assessment of Lymphoma Tissue (HALT) for Global Oncology Field Applications , 2016, Theranostics.

[29]  Bo Sun,et al.  Flow visualization and flow cytometry with holographic video microscopy. , 2009 .

[30]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[31]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[32]  Van Lam,et al.  Automatic phase aberration compensation for digital holographic microscopy based on deep learning background detection. , 2017, Optics express.

[33]  David M. Kaz,et al.  Measuring translational, rotational, and vibrational dynamics in colloids with digital holographic microscopy. , 2011, Optics express.

[34]  Derek K. Tseng,et al.  Detection of waterborne parasites using field-portable and cost-effective lensfree microscopy. , 2010, Lab on a chip.

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

[36]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[37]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[38]  W Xu,et al.  Digital in-line holography for biological applications , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[39]  Bernhard Schölkopf,et al.  A Primer on Kernel Methods , 2004 .

[40]  Hakho Lee,et al.  Digital diffraction analysis enables low-cost molecular diagnostics on a smartphone , 2015, Proceedings of the National Academy of Sciences.

[41]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[42]  Aydogan Ozcan,et al.  Imaging without lenses: achievements and remaining challenges of wide-field on-chip microscopy , 2012, Nature Methods.

[43]  Derek Tseng,et al.  Compact, light-weight and cost-effective microscope based on lensless incoherent holography for telemedicine applications. , 2010, Lab on a chip.

[44]  Juan Carlos Fernández,et al.  Multiobjective evolutionary algorithms to identify highly autocorrelated areas: the case of spatial distribution in financially compromised farms , 2014, Ann. Oper. Res..

[45]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.