Abstract:
Due to the extensive use of flow cytometry in immunophenotyping, cell sorting, cell
cycle analysis, apoptosis, cell proliferation assays, intracellular calcium flux, and numerous
other techniques in digital pathology, scientific research is convergent towards more robust
and interpretable end-to-end solutions. Flow cytometry is a well-established method for the
identification of cells in solution. It is most frequently employed to evaluate peripheral blood,
bone marrow, and other body fluids. Whenever the source equipment for flow cytometry data
collection is replaced, the features of the flow cytometry data change, offering a considerable
challenge for existing learning-based algorithms. Automated gating utilising learning-based
algorithms and automated logical parsing to manage significant challenges such signal
overlap, poor signal detection, population segregation without overlaps, and other significant
issues.
