Digital assessment of peripheral blood and bone marrow aspirate smears

Abstract

The diagnosis of benign and neoplastic hematologic disorders relies on analysis of peripheral blood and bone marrow aspirate smears. As demonstrated by the widespread laboratory adoption of hematology analyzers for automated assessment of peripheral blood, digital analysis of these samples provides many significant benefits compared to relying solely on manual review. Nonetheless, analogous instruments for digital bone marrow aspirate smear assessment have yet to be clinically implemented. In this review, we first provide a historical overview detailing the implementation of hematology analyzers for digital peripheral blood assessment in the clinical laboratory, including the improvements in accuracy, scope, and throughput of current instruments over prior generations. We also describe recent research in digital peripheral blood assessment, particularly in the development of advanced machine learning models that may soon be incorporated into commercial instruments. Next, we provide an overview of recent research in digital assessment of bone marrow aspirate smears and how these approaches could soon lead to development and clinical adoption of instrumentation for automated bone marrow aspirate smear analysis. Finally, we describe the relative advantages and provide our vision for the future of digital assessment of peripheral blood and bone marrow aspirate smears, including what improvements we can soon expect in the hematology laboratory.

Automated Deep Learning-Based Diagnosis and Molecular Characterization of Acute Myeloid Leukemia using Flow Cytometry

“…Current flow cytometric analysis relies heavily on manual intervention in both data processing, including compensation and gating, and data interpretation; this limits analysis of flow cytometry data to highly trained laboratory technologists and hematopathologists. Having an automated approach for analysis of flow cytometry data which does not rely on manual intervention would expand its use to a wider group of laboratorians and diagnosticians, similar to what automated pre-classification of white blood cell differentials has done for peripheral blood smears 4 . Additionally, manual data interpretation by hematopathologists introduces an element of subjectivity which could impact patient diagnosis and treatment; automated interpretation of data would eliminate such subjectivity.…”

“…Machine learning models have been extensively developed for applications in hematopathology, including for analysis of flow cytometry data [4][5][6] . Nonetheless, newer deep learning-based models, which have demonstrated improved predictive performance and interpretability compared to conventional machine learning techniques, have mainly been applied to morphologic assessment of blood and bone marrow aspirate samples rather than flow cytometric analysis 5 .…”