Strategies of T-Cells Identification in AI-Powered Quantitative Phase Imaging Flow Cytometry
The precise identification and counting of T lymphocytes (T-cells) in solid cancers represents a challenging topic since their number is directly correlated to disease severity and therapy response. Recently, this goal has been made effective thanks to the help of Artificial Intelligence, that has boosted the performance of a microscopy imaging system in detecting target cells. However, to date, the T-cells evaluation is based on immunohistochemistry, that is time-consuming, marker-dependent and requires highly qualified personnel to evaluate the samples. Here we report a fully label-free method, based on holographic microscopy imaging in flow cytometry combined with machine learning, to identify T-lymphocytes with respect to a background of multiple cell lines.
Authors
- Giuseppe Gasparre (ORCID: https://orcid.org/0000-0003-1229-9006)
- Daniele Pirone (ORCID: https://orcid.org/0000-0003-1317-7545)
- Anna Myriam Perrone (ORCID: https://orcid.org/0000-0003-3140-4772)
- Anna Maria Porcelli (ORCID: https://orcid.org/0000-0002-6209-0692)
- Martina Mugnano (ORCID: https://orcid.org/0000-0003-2734-8448)
- Lisa Miccio (ORCID: https://orcid.org/0000-0001-9427-881X)
- Ivana Kurelac (ORCID: https://orcid.org/0000-0002-8364-9985)
- Pasquale Memmolo (ORCID: https://orcid.org/0000-0002-9607-7728)
- Vittorio Bianco (ORCID: https://orcid.org/0000-0003-1956-4976)
- Beatrice Cavina (ORCID: https://orcid.org/0000-0001-5485-5360)
Institutions
- Institute of Applied Science and Intelligent Systems (IT)
- National Research Council (IT)
- University of Bologna (IT)
Publication Details
- Published
- 2024-09-18
- DOI
- https://doi.org/10.1109/rtsi61910.2024.10761908
- Primary Topic
- Single-cell and spatial transcriptomics
- Type
- article
- Field-Weighted Citation Impact
- 0.00