Abstract
Hematopoietic stem cells (HSCs) and multipotent progenitors (MPPs) are crucial for maintaining lifelong hematopoiesis. Several decades of successful clinical HSC transplantation have demonstrated the therapeutic importance of HSCs and MPPs. For basic research, HSCs and MPPs are routinely analyzed and separated by fluorescence-activated cell sorting (FACS) based on cell surface marker staining, a procedure that requires incubation with various antibodies and expensive laser-equipped flow cytometers. Both antibody staining and laser impair cell viability and stem cell activity. To develop a new staining-free, laser-free method for predicting and separating subpopulations of HSCs and MPPs, we used a deep learning approach that can extract minutiae from large-scale datasets of long-term HSCs (LT-HSCs), short-term HSCs (ST-HSCs), and multipotent progenitors (MPPs) to distinguish subpopulations of hematopoietic precursor solely based on their morphology. Remarkably, our deep learning model can achieve predictable identification of subsets of HSCs with at least 85% accuracy; this demonstrates for the first time that HSC subpopulations can be differentiated solely based on their morphology exhibited in light microscopic images through deep learning. We anticipate that our robust and accurate deep-learning-based platform for hematopoietic precursors will provide a basis for the future development of a next-generation cell sorting system.
Disclosures
No relevant conflicts of interest to declare.
Author notes
Asterisk with author names denotes non-ASH members.
