Machine learning‐based in‐line holographic sensing of unstained malaria‐infected red blood cells

Accurate and immediate diagnosis of malaria is important for medication of the infectious disease. Conventional methods for diagnosing malaria are time consuming and rely on the skill of experts. Therefore, an automatic and simple diagnostic modality is essential for healthcare in developing countries that lack the expertise of trained microscopists. In the present study, a new automatic sensing method using digital in-line holographic microscopy (DIHM) combined with machine learning algorithms was proposed to sensitively detect unstained malaria-infected red blood cells (iRBCs). To identify the RBC characteristics, 13 descriptors were extracted from segmented holograms of individual RBCs. Among the 13 descriptors, 10 features were highly statistically different between healthy RBCs (hRBCs) and iRBCs. Six machine learning algorithms were applied to effectively combine the dominant features and to greatly improve the diagnostic capacity of the present method. Among the classification models trained by the 6 tested algorithms, the model trained by the support vector machine (SVM) showed the best accuracy in separating hRBCs and iRBCs for training (n = 280, 96.78%) and testing sets (n = 120, 97.50%). This DIHM-based artificial intelligence methodology is simple and does not require blood staining. Thus, it will be beneficial and valuable in the diagnosis of malaria.

[1]  A. Craig,et al.  The Role of Animal Models for Research on Severe Malaria , 2012, PLoS pathogens.

[2]  Charles Awasom,et al.  Malaria over-diagnosis in Cameroon: diagnostic accuracy of Fluorescence and Staining Technologies (FAST) Malaria Stain and LED microscopy versus Giemsa and bright field microscopy validated by polymerase chain reaction , 2017, Infectious Diseases of Poverty.

[3]  Sang Joon Lee,et al.  Precise measurement of orientations of transparent ellipsoidal particles through digital holographic microscopy. , 2016, Optics express.

[4]  J. Rosenblatt,et al.  Diagnostic performance of rapid diagnostic tests versus blood smears for malaria in US clinical practice. , 2009, Clinical Infectious Diseases.

[5]  Bahram Javidi,et al.  Cell morphology-based classification of red blood cells using holographic imaging informatics. , 2016, Biomedical optics express.

[6]  Leann Tilley,et al.  Illuminating Plasmodium falciparum-infected red blood cells. , 2007, Trends in parasitology.

[7]  S. Vanapalli,et al.  Label-free, high-throughput holographic screening and enumeration of tumor cells in blood. , 2017, Lab on a chip.

[8]  Chandan Chakraborty,et al.  Machine learning approach for automated screening of malaria parasite using light microscopic images. , 2013, Micron.

[9]  Fei Li,et al.  Advances in paper-based point-of-care diagnostics. , 2014, Biosensors & bioelectronics.

[10]  H. Greenspan,et al.  Quantitative phase microscopy spatial signatures of cancer cells , 2017, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[11]  Bahram Javidi,et al.  Automatic cell identification and visualization using digital holographic microscopy with head mounted augmented reality devices: An Overview , 2018, 2018 17th Workshop on Information Optics (WIO).

[12]  YongKeun Park,et al.  High-resolution three-dimensional imaging of red blood cells parasitized by Plasmodium falciparum and in situ hemozoin crystals using optical diffraction tomography , 2013, Journal of biomedical optics.

[13]  Hayit Greenspan,et al.  Automated analysis of individual sperm cells using stain‐free interferometric phase microscopy and machine learning , 2017, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[14]  Z. Premji,et al.  Acridine Orange for malaria diagnosis: its diagnostic performance, its promotion and implementation in Tanzania, and the implications for malaria control , 2002, Annals of tropical medicine and parasitology.

[15]  Yong-Seok Choi,et al.  Advances in digital holographic micro-PTV for analyzing microscale flows , 2012 .

[16]  Young-Ran Ha,et al.  In vivo study on splenomegaly inhibition by genistein in Plasmodium berghei-infected mice. , 2015, Parasitology international.

[17]  Yongkeun Park,et al.  Refractive index maps and membrane dynamics of human red blood cells parasitized by Plasmodium falciparum , 2008, Proceedings of the National Academy of Sciences.

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

[19]  Sang Joon Lee,et al.  Label-free sensor for automatic identification of erythrocytes using digital in-line holographic microscopy and machine learning. , 2018, Biosensors & bioelectronics.

[20]  Pasquale Memmolo,et al.  Investigation on dynamics of red blood cells through their behavior as biophotonic lenses , 2016, Journal of biomedical optics.

[21]  S. Schedin,et al.  Cell shape identification using digital holographic microscopy. , 2015, Applied optics.

[22]  Sang Joon Lee,et al.  Holographic analysis on deformation and restoration of malaria-infected red blood cells by antimalarial drug , 2015, Journal of biomedical optics.

[23]  J. Chi,et al.  Automated Detection of P. falciparum Using Machine Learning Algorithms with Quantitative Phase Images of Unstained Cells , 2016, PloS one.

[24]  J. Iqbal,et al.  Modified Giemsa Staining for Rapid Diagnosis of Malaria Infection , 2003, Medical Principles and Practice.

[25]  B. Javidi,et al.  Automatic Identification of Malaria-Infected RBC With Digital Holographic Microscopy Using Correlation Algorithms , 2012, IEEE Photonics Journal.

[26]  Pasquale Memmolo,et al.  Label‐free analysis of mononuclear human blood cells in microfluidic flow by coherent imaging tools , 2017, Journal of biophotonics.

[27]  Nicolas Pavillon,et al.  Noninvasive detection of macrophage activation with single-cell resolution through machine learning , 2018, Proceedings of the National Academy of Sciences.

[28]  Yong-Seok Choi,et al.  High-accuracy three-dimensional position measurement of tens of micrometers size transparent microspheres using digital in-line holographic microscopy. , 2011, Optics letters.

[29]  J. Katz,et al.  Applications of Holography in Fluid Mechanics and Particle Dynamics , 2010 .

[30]  Andrew G. Dempster,et al.  Parasite detection and identification for automated thin blood film malaria diagnosis , 2010, Comput. Vis. Image Underst..

[31]  Sang Joon Lee,et al.  Focusing and alignment of erythrocytes in a viscoelastic medium , 2017, Scientific Reports.

[32]  Myung K. Kim,et al.  Wavelength-scanning digital interference holography for tomographic three-dimensional imaging by use of the angular spectrum method. , 2005, Optics letters.

[33]  G. Grau,et al.  In vitro culture of Plasmodium berghei-ANKA maintains infectivity of mouse erythrocytes inducing cerebral malaria , 2011, Malaria Journal.

[34]  L. Bai,et al.  A portable image-based cytometer for rapid malaria detection and quantification , 2017, PloS one.

[35]  P Memmolo,et al.  Red blood cell as an adaptive optofluidic microlens , 2015, Nature Communications.

[36]  Myungjoo Kang,et al.  An Image Analysis Algorithm for Malaria Parasite Stage Classification and Viability Quantification , 2013, PloS one.

[37]  Hyunjoo Park,et al.  Label-free identification of individual bacteria using Fourier transform light scattering. , 2015, Optics express.

[38]  Bahram Javidi,et al.  Automatic multicell identification using a compact lensless single and double random phase encoding system. , 2018, Applied optics.

[39]  Faliu Yi,et al.  Three-dimensional counting of morphologically normal human red blood cells via digital holographic microscopy , 2015, Journal of biomedical optics.

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

[41]  Mahdieh Poostchi,et al.  Image analysis and machine learning for detecting malaria , 2018, Translational research : the journal of laboratory and clinical medicine.

[42]  A. Rajan,et al.  SEM studies on blood cells of Plasmodium berghei infected Balb/c mice treated with artesunate and homeopathic medicine China , 2011, Journal of parasitic diseases : official organ of the Indian Society for Parasitology.

[43]  Pasquale Memmolo,et al.  Recent advances in holographic 3D particle tracking , 2015 .

[44]  Chris J Janse,et al.  A Plasmodium berghei reference line that constitutively expresses GFP at a high level throughout the complete life cycle. , 2004, Molecular and biochemical parasitology.