Abstract
We present a rapid and label-free method for hematologic screening for diseases and syndromes, utilizing quantitative phase imaging (QPI) and machine learning. We aim to establish an efficient blood examination framework that does not suffer from the drawbacks of conventional blood assays, which are incapable of profiling single cells or require labeling procedures. Our method involves the synergistic employment of QPI and machine learning. The high-dimensional refractive index information arising from the QPI-based profiling of single red blood cells is processed to screen for diseases and syndromes using machine learning, which can utilize high-dimensional data beyond the human level. Accurate screening for iron-deficiency anemia, reticulocytosis, hereditary spherocytosis, and diabetes mellitus is demonstrated (>98% accuracy) using the proposed method. Furthermore, we highlight the synergy between QPI and machine learning in the proposed method by analyzing the performance of the method.
Highlights
We present a rapid and label-free method for hematologic screening for diseases and syndromes, utilizing quantitative phase imaging (QPI) and machine learning
We show that single-cell profiling provides invaluable information in the context of high-accuracy screening for iron-deficiency anemia (IDA), reticulocytosis (RET), hereditary spherocytosis (HS), and diabetes mellitus (DM)
The surface areas of the red blood cells (RBCs) were 143.1 17.9, 117.8 21.2, 202.6 38.2, 97.8 16.7, and 148.2 14.4 m2; the sphericities of the RBCs were 0.67 0.06, 0.60 0.11, 0.50 0.08, and 0.66 0.05; the Hb contents were 27.3 6.4, 11.7 5.9, 19.4 7.3, 17.1 6.3, and 31.2 4.8 pg; the Hb concentrations were 30.9 4.6, 19.9 5.3, 20.1 5.0, 27.2 7.5, and 34.6 2.7 g/dL; and the membrane fluctuations were 51.0 8.6, 68.9 20.6, 61.6 16.5, 53.5 14.4, and 46.6 4.5 nm. It was evident from the distributions of the RBC properties extracted from the QPI images that a tool for highdimensional analysis is essential for the classification of RBCs
Summary
The use of disease-induced alterations of individual red blood cells (RBCs) as diagnostic markers that may facilitate efficient screening for various diseases and syndromes has been widely reported (Baskurt et al 1998; Bateman et al 2017; Jung et al 2016; Kim et al 2014a; Koepke and Koepke 1986; Lee et al 2017; Watanabe et al 1994). Despite the well-established diagnostic protocols and usefulness of this approach in hematological studies (Higgins 2015; Higgins and Mahadevan 2010; Urrechaga et al 2013; Weatherall 2011b), the massive population-based nature of CBC measurements and analyses suggest the clear limitation that this method is incapable of characterizing individual RBCs. Considering the increasing awareness of cellular heterogeneity at the single-cell level (Altschuler and Wu 2010; Wang and Bodovitz 2010), a new technique for profiling individual RBCs would play a major role in extending the potential of RBC-based disease screening (Weatherall 2011a)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
