Virtual Staining, Segmentation, and Classification of Blood Smears for Label-Free Hematology Analysis

• Type of Material: Article
• Authors: Nischita Kaza, Georgia Institute of Technology; Ashkan Ojaghi, Emory University; Francisco E. Robles, Emory University
• Language: English
• Date: 2022-07-01
• Publisher: American Association for the Advancement of Science
• Publication Version: Final Published Version
• Copyright Statement: © 2022 Nischita Kaza et al.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): https://doi.org/10.34133/2022/9853606
• Title of Journal or Parent Work: BME Frontiers
• Volume: 2022
• Start Page: 9853606
• Grant/Funding Information: We greatly acknowledge support for this work by the Massner Lane Family Foundation; Burroughs Wellcome Fund (CASI BWF 1014540); National Science Foundation (NSF CBET CAREER 1752011); and the Donaldson Charitable Trust Research Synergy Fund Award, a philanthropic award provided by the Winship Cancer Institute of Emory University, the Aflac Cancer & Blood Disorders Center at Children’s Healthcare of Atlanta, and the Wallace H. Coulter Department of Biomedical Engineering at Emory University and the Georgia Institute of Technology.
• Keywords: white blood cells; hematology; deep-UV microscopy; independent deep networks; molecular imaging technique
• Research Categories: Health Sciences, Public Health; Artificial Intelligence

Abstract

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.