Artificial‐Intelligence‐Enabled Reagent‐Free Imaging Hematology Analyzer

Leukocyte differential test is a widely performed clinical procedure for screening infectious diseases. Existing hematology analyzers require labor-intensive work and a panel of expensive reagents. Here we report an artificial-intelligence enabled reagent-free imaging hematology analyzer (AIRFIHA) modality that can accurately classify subpopulations of leukocytes with minimal sample preparation. AIRFIHA is realized through training a two-step residual neural network using label-free images of separated leukocytes acquired from a custom-built quantitative phase microscope. We validated the performance of AIRFIHA in randomly selected test set and cross-validated it across all blood donors. AIRFIHA outperforms current methods in classification accuracy, especially in B and T lymphocytes, while preserving the natural state of cells. It also shows a promising potential in differentiating CD4 and CD8 cells. Owing to its easy operation, low cost, and strong discerning capability of complex leukocyte subpopulations, we envision AIRFIHA is clinically translatable and can also be deployed in resource-limited settings, e.g., during pandemic situations for the rapid screening of infectious diseases.

[1]  Peter Schelkens,et al.  Accurate label-free 3-part leukocyte recognition with single cell lens-free imaging flow cytometry , 2018, Comput. Biol. Medicine.

[2]  David S Boyle,et al.  Emerging technologies for point-of-care CD4 T-lymphocyte counting. , 2012, Trends in biotechnology.

[3]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[4]  Pramod Kumar Srivastava,et al.  Reagent-Free and Rapid Assessment of T Cell Activation State Using Diffraction Phase Microscopy and Deep Learning. , 2019, Analytical chemistry.

[5]  Ata Mahjoubfar,et al.  Deep Learning in Label-free Cell Classification , 2016, Scientific Reports.

[6]  D. Corda,et al.  A reliable Raman-spectroscopy-based approach for diagnosis, classification and follow-up of B-cell acute lymphoblastic leukemia , 2016, Scientific Reports.

[7]  Zahid Yaqoob,et al.  Large population cell characterization using quantitative phase cytometer , 2017, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[8]  A. Ozcan,et al.  Deep learning enables cross-modality super-resolution in fluorescence microscopy , 2018, Nature Methods.

[9]  Gabriel Popescu,et al.  Optical imaging of cell mass and growth dynamics. , 2008, American journal of physiology. Cell physiology.

[10]  Stefan W Krause,et al.  Comparison of automated differential blood cell counts from Abbott Sapphire, Siemens Advia 120, Beckman Coulter DxH 800, and Sysmex XE-2100 in normal and pathologic samples. , 2013, American journal of clinical pathology.

[11]  Hyun-seok Min,et al.  Quantitative Phase Imaging and Artificial Intelligence: A Review , 2018, IEEE Journal of Selected Topics in Quantum Electronics.

[12]  Gabriel Popescu,et al.  Erythrocyte structure and dynamics quantified by Hilbert phase microscopy. , 2005, Journal of biomedical optics.

[13]  T. Valdez,et al.  Integration of diffraction phase microscopy and Raman imaging for label‐free morpho‐molecular assessment of live cells , 2018, Journal of biophotonics.

[14]  J. Popp,et al.  Toward a spectroscopic hemogram: Raman spectroscopic differentiation of the two most abundant leukocytes from peripheral blood. , 2012, Analytical chemistry.

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

[16]  Yibo Zhang,et al.  PhaseStain: the digital staining of label-free quantitative phase microscopy images using deep learning , 2018, Light: Science & Applications.

[17]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[18]  David E. Goldberg,et al.  Genetic algorithms and Machine Learning , 1988, Machine Learning.

[19]  Nahil Sobh,et al.  Label-free colorectal cancer screening using deep learning and spatial light interference microscopy (SLIM). , 2020, APL photonics.

[20]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[21]  Barry R. Masters,et al.  Quantitative Phase Imaging of Cells and Tissues , 2012 .

[22]  Jianlin Zhao,et al.  Quantitative investigation on morphology and intracellular transport dynamics of migrating cells. , 2019, Applied optics.

[23]  R. Dasari,et al.  Diffraction phase microscopy for quantifying cell structure and dynamics. , 2006, Optics letters.

[24]  C. Depeursinge,et al.  Quantitative phase imaging in biomedicine , 2012, 2012 Conference on Lasers and Electro-Optics (CLEO).

[25]  Zhuo Wang,et al.  Optical measurement of cycle-dependent cell growth , 2011, Proceedings of the National Academy of Sciences.

[26]  Jonghee Yoon,et al.  Holographic deep learning for rapid optical screening of anthrax spores , 2017, Science Advances.

[27]  Wan Kyun Chung,et al.  Real-time Image Processing for Microscopy-based Label-free Imaging Flow Cytometry in a Microfluidic Chip , 2017, Scientific Reports.

[28]  J. Thachil,et al.  Approach to the Diagnosis and Classification of Blood Cell Disorders , 2016, Dacie and Lewis Practical Haematology.

[29]  G. Erf,et al.  Ontogeny of T lymphocytes and intestinal morphological characteristics in neonatal pigs at different ages in the postnatal period. , 2006, Journal of animal science.

[30]  Makoto Yamada,et al.  High-throughput imaging flow cytometry by optofluidic time-stretch microscopy , 2018, Nature Protocols.

[31]  Hye-Jin Kim,et al.  Deep-learning-based label-free segmentation of cell nuclei in time-lapse refractive index tomograms , 2018, bioRxiv.

[32]  Natan T. Shaked,et al.  Rapid 3D Refractive‐Index Imaging of Live Cells in Suspension without Labeling Using Dielectrophoretic Cell Rotation , 2016, Advanced science.

[33]  Takaya Saito,et al.  The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets , 2015, PloS one.

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

[35]  F. Arai,et al.  Label-free chemical imaging flow cytometry by high-speed multicolor stimulated Raman scattering , 2019, Proceedings of the National Academy of Sciences.

[36]  B. Johansson,et al.  Age-related change in peripheral blood T-lymphocyte subpopulations and cytomegalovirus infection in the very old: the Swedish longitudinal OCTO immune study , 2001, Mechanisms of Ageing and Development.

[37]  Gabriel Popescu,et al.  Measurement of red blood cell mechanics during morphological changes , 2010, Proceedings of the National Academy of Sciences.

[38]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[39]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  R. Horstmeyer,et al.  Wide-field, high-resolution Fourier ptychographic microscopy , 2013, Nature Photonics.

[41]  YongKeun Park,et al.  Identification of non-activated lymphocytes using three-dimensional refractive index tomography and machine learning , 2017, Scientific Reports.

[42]  Anne E Carpenter,et al.  Label-free cell cycle analysis for high-throughput imaging flow cytometry , 2016, Nature Communications.

[43]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Ni Zhao,et al.  Portable quantitative phase microscope for material metrology and biological imaging , 2020 .

[45]  Hau-Tieng Wu,et al.  Imaging Cytometry of Human Leukocytes with Third Harmonic Generation Microscopy , 2016, Scientific Reports.

[46]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[47]  Francisco E. Robles,et al.  Label-free hematology analysis using deep-ultraviolet microscopy , 2020, Proceedings of the National Academy of Sciences.

[48]  Olaf Wolkenhauer,et al.  Label‐Free Identification of White Blood Cells Using Machine Learning , 2019, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[49]  Gabriel Popescu,et al.  Quantitative Phase Imaging , 2012 .

[50]  Barbara Sennino,et al.  Labeling Human Mesenchymal Stem Cells with Fluorescent Contrast Agents: the Biological Impact , 2010, Molecular Imaging and Biology.

[51]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[52]  Stefan W Krause,et al.  Label‐Free High‐Throughput Leukemia Detection by Holographic Microscopy , 2018, Advanced science.

[53]  Thierry Blu,et al.  PURE-LET Image Deconvolution , 2018, IEEE Transactions on Image Processing.

[54]  Tan H. Nguyen,et al.  Diffraction phase microscopy: principles and applications in materials and life sciences , 2014 .

[55]  John Scott Bridle,et al.  Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.

[56]  R. Barer.  Interference Microscopy and Mass Determination , 1952, Nature.

[57]  Trevor F Peter,et al.  Effect of point-of-care CD4 cell count tests on retention of patients and rates of antiretroviral therapy initiation in primary health clinics: an observational cohort study , 2011, The Lancet.