Search

Acute myeloid leukemia (AML) is a heterogenous blood cancer with a dismal prognosis. It emanates from leukemic stem cells (LSCs) arising from the genetic transformation of hematopoietic stem cells (HSCs). LSCs hold prognostic value, but their molecular and immunophenotypic heterogeneity poses challenges: there is no single marker for identifying all LSCs across AML samples. We hypothesized that imaging flow cytometry (IFC) paired with artificial intelligence-driven image analysis could visually distinguish LSCs from HSCs based solely on morphology. Initially, a seven-color IFC panel was employed to immunophenotypically identify LSCs and HSCs in bone marrow samples from five AML patients and ten healthy donors, respectively. Next, we developed convolutional neural network (CNN) models for HSC-LSC discrimination using brightfield (BF), side scatter (SSC), and DNA images. Classification using only BF images achieved 86.96% accuracy, indicating significant morphological differences. Accuracy increased to 93.42% when combining BF with DNA images, highlighting differences in nuclear morphology, although DNA images alone were inadequate for accurate HSC-LSC discrimination. Model development using SSC images revealed minor granularity differences. Performance metrics varied substantially between AML patients, indicating considerable morphologic variations among LSCs. Overall, we demonstrate proof-of-concept results for accurate CNN-based HSC-LSC differentiation, instigating the development of a novel technique within AML monitoring. [ABSTRACT FROM AUTHOR]

This panel was designed to identify, quantify and phenotypically characterize putative leukemic stem cells (LSCs) in bone marrow (BM) samples from individual pediatric patients diagnosed with acute myeloid leukemia (AML). Based on an aberrant expression on immunophenotypically defined hematopoietic stem cells (HSCs), several antigens have been proposed as LSC markers in AML research, using healthy adult BM samples as reference material. Generally, these antigens have been evaluated individually in smaller panels (e.g. 8‐color panels). This necessitates several tubes to characterize the LSC phenotype and compromises the ability to evaluate LSC heterogeneity. The present 15‐color OMIP incorporates nine suggested LSC markers to comprehensively capture LSC immunophenotypes and to explore heterogenic marker‐patterns within LSC populations in a single tube. Importantly, this single tube approach requires less input material, which is essential when sampling BM aspirates from pediatric patients where sample volumes often are sparse. As knowledge on normal expression levels of the included LSC markers in HSCs from hematologically healthy children are a prerequisite for labelling a phenotype as abnormal, we have evaluated the applicability of the panel on cryopreserved mononuclear cells (MNCs) isolated from BM samples from pediatric patients without hematological disorders as well as pediatric AML patients. The panel is optimized for cryopreserved BM MNCs, but could in principle, be utilized for LSC detection in any biological material containing human hematopoietic cells. For the comparison of two widely‐used blood preservation buffers, whole blood samples are processed as shown in the workflow and acquired by flow cytometry or mass cytometry. An example of high dimensional analysis using UMAP is shown. The similarity between FRESH and preserved blood can be appreciated along different preservation buffers and time of storage. [ABSTRACT FROM AUTHOR]