Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Virtual Staining, Segmentation, and Classification of Blood Smears for Label-Free Hematology Analysis
Objective and Impact Statement . We present a fully automated hematological analysis framework based on single-channel (single-wavelength), label-free deep-ultraviolet (UV) microscopy that serves as a fast, cost-effective alternative to conventional hematology analyzers. Introduction . Hematological analysis is essential for the diagnosis and monitoring of several diseases but requires complex systems operated by trained personnel, costly chemical reagents, and lengthy protocols. Label-free techniques eliminate the need for staining or additional preprocessing and can lead to faster analysis and a simpler workflow. In this work, we leverage the unique capabilities of deep-UV microscopy as a label-free, molecular imaging technique to develop a deep learning-based pipeline that enables virtual staining, segmentation, classification, and counting of white blood cells (WBCs) in single-channel images of peripheral blood smears. Methods . We train independent deep networks to virtually stain and segment grayscale images of smears. The segmented images are then used to train a classifier to yield a quantitative five-part WBC differential. Results. Our virtual staining scheme accurately recapitulates the appearance of cells under conventional Giemsa staining, the gold standard in hematology. The trained cellular and nuclear segmentation networks achieve high accuracy, and the classifier can achieve a quantitative five-part differential on unseen test data. Conclusion . This proposed automated hematology analysis framework could greatly simplify and improve current complete blood count and blood smear analysis and lead to the development of a simple, fast, and low-cost, point-of-care hematology analyzer.  more » « less
Award ID(s):
1752011
PAR ID:
10412747
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
BME Frontiers
Volume:
2022
ISSN:
2765-8031
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, Biomedical Optics Express)
    Deep-ultraviolet (UV) microscopy enables label-free, high-resolution, quantitative molecular imaging and enables unique applications in biomedicine, including the potential for fast hematological analysis at the point-of-care. UV microscopy has been shown to quantify hemoglobin content and white blood cells (five-part differential), providing a simple alternative to the current gold standard, the hematological analyzer. Previously, however, the UV system comprised a bulky broadband laser-driven plasma light source along with a large and expensive camera and 3D translation stage. Here, we present a modified deep-UV microscope system with a compact footprint and low-cost components. We detail the novel design with simple, inexpensive optics and hardware to enable fast and accurate automated imaging. We characterize the system, including a modified low-cost web-camera and custom automated 3D translation stage, and demonstrate its ability to scan and capture large area images. We further demonstrate the capability of the system by imaging and analyzing blood smears, using previously trained networks for automatic segmentation, classification (including 5-part white blood cell differential), and colorization. The developed system is approximately 10 times less expensive than previous configurations and can serve as a point-of-care hematology analyzer, as well as be applied broadly in biomedicine as a simple compact, low-cost, quantitative molecular imaging system. 
    more » « less
  2. ; ; ; ; ; ; (, Proceedings of the National Academy of Sciences)
    null (Ed.)
    Hematological analysis, via a complete blood count (CBC) and microscopy, is critical for screening, diagnosing, and monitoring blood conditions and diseases but requires complex equipment, multiple chemical reagents, laborious system calibration and procedures, and highly trained personnel for operation. Here we introduce a hematological assay based on label-free molecular imaging with deep-ultraviolet microscopy that can provide fast quantitative information of key hematological parameters to facilitate and improve hematological analysis. We demonstrate that this label-free approach yields 1) a quantitative five-part white blood cell differential, 2) quantitative red blood cell and hemoglobin characterization, 3) clear identification of platelets, and 4) detailed subcellular morphology. Analysis of tens of thousands of live cells is achieved in minutes without any sample preparation. Finally, we introduce a pseudocolorization scheme that accurately recapitulates the appearance of cells under conventional staining protocols for microscopic analysis of blood smears and bone marrow aspirates. Diagnostic efficacy is evaluated by a panel of hematologists performing a blind analysis of blood smears from healthy donors and thrombocytopenic and sickle cell disease patients. This work has significant implications toward simplifying and improving CBC and blood smear analysis, which is currently performed manually via bright-field microscopy, and toward the development of a low-cost, easy-to-use, and fast hematological analyzer as a point-of-care device and for low-resource settings. 
    more » « less
  3. (, SPIE Optical Metrology)
    Ferraro, Pietro; Grilli, Simonetta; Psaltis, Demetri (Ed.)
    Deep learning techniques create new opportunities to revolutionize tissue staining methods by digitally generating histological stains using trained neural networks, providing rapid, cost-effective, accurate and environmentally friendly alternatives to standard chemical staining methods. These deep learning-based virtual staining techniques can successfully generate different types of histological stains, including immunohistochemical stains, from label-free microscopic images of unstained samples by using, e.g., autofluorescence microscopy, quantitative phase imaging (QPI) and reflectance confocal microscopy. Similar approaches were also demonstrated for transforming images of an already stained tissue sample into another type of stain, performing virtual stain-to-stain transformations. In this presentation, I will provide an overview of our recent work on the use of deep neural networks for label-free tissue staining, also covering their biomedical applications. 
    more » « less
  4. ; ; ; ; ; ; ; ; ; ; et al (, Optics Letters)
    Neutropenia is a condition comprising an abnormally low number of neutrophils, a type of white blood cell, which puts patients at an increased risk of severe infections. Neutropenia is especially common among cancer patients and can disrupt their treatment or even be life-threatening in severe cases. Therefore, routine monitoring of neutrophil counts is crucial. However, the current standard of care to assess neutropenia, the complete blood count (CBC), is resource-intensive, time-consuming, and expensive, thereby limiting easy or timely access to critical hematological information such as neutrophil counts. Here, we present a simple technique for fast, label-free neutropenia detection and grading via deep-ultraviolet (deep-UV) microscopy of blood cells in polydimethylsiloxane (PDMS)-based passive microfluidic devices. The devices can potentially be manufactured in large quantities at a low cost, requiring only 1 μL of whole blood for operation. We show that the absolute neutrophil counts (ANC) obtained from our proposed microfluidic device-enabled deep-UV microscopy system are highly correlated with those from CBCs using commercial hematology analyzers in patients with moderate and severe neutropenia, as well as healthy donors. This work lays the foundation for the development of a compact, easy-to-use UV microscope system to track neutrophil counts that is suitable for low-resource, at-home, or point-of-care settings. 
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al (, PLOS ONE)
    Becker, Daniel (Ed.)
    The black flying fox ( Pteropus alecto ) is a natural reservoir for Hendra virus, a paramyxovirus that causes fatal infections in humans and horses in Australia. Increased excretion of Hendra virus by flying foxes has been hypothesized to be associated with physiological or energetic stress in the reservoir hosts. The objective of this study was to explore the leukocyte profiles of wild-caught P . alecto , with a focus on describing the morphology of each cell type to facilitate identification for clinical purposes and future virus spillover research. To this end, we have created an atlas of images displaying the commonly observed morphological variations across each cell type. We provide quantitative and morphological information regarding the leukocyte profiles in bats captured at two roost sites located in Redcliffe and Toowoomba, Queensland, Australia, over the course of two years. We examined the morphology of leukocytes, platelets, and erythrocytes of P . alecto using cytochemical staining and characterization of blood films through light microscopy. Leukocyte profiles were broadly consistent with previous studies of P . alecto and other Pteropus species. A small proportion of individual samples presented evidence of hemoparasitic infection or leukocyte morphological traits that are relevant for future research on bat health, including unique large granular lymphocytes. Considering hematology is done by visual inspection of blood smears, examples of the varied cell morphologies are included as a visual guide. To the best of our knowledge, this study provides the first qualitative assessment of P . alecto leukocytes, as well as the first set of published hematology reference images for this species. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Text Encoded Conversion
  • XML
  • Save / Share this Record
  • Send to Email