AI-aided holographic flow cytometry for label-free identification of ovarian cancer cells in the presence of unbalanced datasets
Liquid biopsy is a valuable emerging alternative to tissue biopsy with great potential in the noninvasive early diagnostics of cancer. Liquid biopsy based on single cell analysis can be a powerful approach to identify circulating tumor cells (CTCs) in the bloodstream and could provide new opportunit...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2023-06-01
|
Series: | APL Bioengineering |
Online Access: | http://dx.doi.org/10.1063/5.0153413 |
_version_ | 1797771782792413184 |
---|---|
author | F. Borrelli J. Behal A. Cohen L. Miccio P. Memmolo I. Kurelac A. Capozzoli C. Curcio A. Liseno V. Bianco N. T. Shaked P. Ferraro |
author_facet | F. Borrelli J. Behal A. Cohen L. Miccio P. Memmolo I. Kurelac A. Capozzoli C. Curcio A. Liseno V. Bianco N. T. Shaked P. Ferraro |
author_sort | F. Borrelli |
collection | DOAJ |
description | Liquid biopsy is a valuable emerging alternative to tissue biopsy with great potential in the noninvasive early diagnostics of cancer. Liquid biopsy based on single cell analysis can be a powerful approach to identify circulating tumor cells (CTCs) in the bloodstream and could provide new opportunities to be implemented in routine screening programs. Since CTCs are very rare, the accurate classification based on high-throughput and highly informative microscopy methods should minimize the false negative rates. Here, we show that holographic flow cytometry is a valuable instrument to obtain quantitative phase-contrast maps as input data for artificial intelligence (AI)-based classifiers. We tackle the problem of discriminating between A2780 ovarian cancer cells and THP1 monocyte cells based on the phase-contrast images obtained in flow cytometry mode. We compare conventional machine learning analysis and deep learning architectures in the non-ideal case of having a dataset with unbalanced populations for the AI training step. The results show the capacity of AI-aided holographic flow cytometry to discriminate between the two cell lines and highlight the important role played by the phase-contrast signature of the cells to guarantee accurate classification. |
first_indexed | 2024-03-12T21:42:38Z |
format | Article |
id | doaj.art-ae1b268386f14748a51d3e691ee97ca1 |
institution | Directory Open Access Journal |
issn | 2473-2877 |
language | English |
last_indexed | 2024-03-12T21:42:38Z |
publishDate | 2023-06-01 |
publisher | AIP Publishing LLC |
record_format | Article |
series | APL Bioengineering |
spelling | doaj.art-ae1b268386f14748a51d3e691ee97ca12023-07-26T15:56:53ZengAIP Publishing LLCAPL Bioengineering2473-28772023-06-0172026110026110-1010.1063/5.0153413AI-aided holographic flow cytometry for label-free identification of ovarian cancer cells in the presence of unbalanced datasetsF. Borrelli0J. Behal1A. Cohen2L. Miccio3P. Memmolo4I. Kurelac5A. Capozzoli6C. Curcio7A. Liseno8V. Bianco9N. T. Shaked10P. Ferraro11 Dipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione (DIETI), Università di Napoli Federico II, 80125 Napoli, Italy Institute of Applied Sciences and Intelligent Systems “E. Caianiello,” CNR-ISASI, Via Campi Flegrei 34, 80078 Pozzuoli, Napoli, Italy Tel Aviv University, Ramat Aviv, 6997801 Tel Aviv, Israel Institute of Applied Sciences and Intelligent Systems “E. Caianiello,” CNR-ISASI, Via Campi Flegrei 34, 80078 Pozzuoli, Napoli, Italy Institute of Applied Sciences and Intelligent Systems “E. Caianiello,” CNR-ISASI, Via Campi Flegrei 34, 80078 Pozzuoli, Napoli, Italy Unit of Medical Genetics, Department of Medical and Surgical Sciences (DIMEC), University of Bologna, Via Massarenti 9, Bologna 40138, Italy Dipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione (DIETI), Università di Napoli Federico II, 80125 Napoli, Italy Dipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione (DIETI), Università di Napoli Federico II, 80125 Napoli, Italy Dipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione (DIETI), Università di Napoli Federico II, 80125 Napoli, Italy Institute of Applied Sciences and Intelligent Systems “E. Caianiello,” CNR-ISASI, Via Campi Flegrei 34, 80078 Pozzuoli, Napoli, Italy Tel Aviv University, Ramat Aviv, 6997801 Tel Aviv, Israel Institute of Applied Sciences and Intelligent Systems “E. Caianiello,” CNR-ISASI, Via Campi Flegrei 34, 80078 Pozzuoli, Napoli, ItalyLiquid biopsy is a valuable emerging alternative to tissue biopsy with great potential in the noninvasive early diagnostics of cancer. Liquid biopsy based on single cell analysis can be a powerful approach to identify circulating tumor cells (CTCs) in the bloodstream and could provide new opportunities to be implemented in routine screening programs. Since CTCs are very rare, the accurate classification based on high-throughput and highly informative microscopy methods should minimize the false negative rates. Here, we show that holographic flow cytometry is a valuable instrument to obtain quantitative phase-contrast maps as input data for artificial intelligence (AI)-based classifiers. We tackle the problem of discriminating between A2780 ovarian cancer cells and THP1 monocyte cells based on the phase-contrast images obtained in flow cytometry mode. We compare conventional machine learning analysis and deep learning architectures in the non-ideal case of having a dataset with unbalanced populations for the AI training step. The results show the capacity of AI-aided holographic flow cytometry to discriminate between the two cell lines and highlight the important role played by the phase-contrast signature of the cells to guarantee accurate classification.http://dx.doi.org/10.1063/5.0153413 |
spellingShingle | F. Borrelli J. Behal A. Cohen L. Miccio P. Memmolo I. Kurelac A. Capozzoli C. Curcio A. Liseno V. Bianco N. T. Shaked P. Ferraro AI-aided holographic flow cytometry for label-free identification of ovarian cancer cells in the presence of unbalanced datasets APL Bioengineering |
title | AI-aided holographic flow cytometry for label-free identification of ovarian cancer cells in the presence of unbalanced datasets |
title_full | AI-aided holographic flow cytometry for label-free identification of ovarian cancer cells in the presence of unbalanced datasets |
title_fullStr | AI-aided holographic flow cytometry for label-free identification of ovarian cancer cells in the presence of unbalanced datasets |
title_full_unstemmed | AI-aided holographic flow cytometry for label-free identification of ovarian cancer cells in the presence of unbalanced datasets |
title_short | AI-aided holographic flow cytometry for label-free identification of ovarian cancer cells in the presence of unbalanced datasets |
title_sort | ai aided holographic flow cytometry for label free identification of ovarian cancer cells in the presence of unbalanced datasets |
url | http://dx.doi.org/10.1063/5.0153413 |
work_keys_str_mv | AT fborrelli aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT jbehal aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT acohen aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT lmiccio aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT pmemmolo aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT ikurelac aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT acapozzoli aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT ccurcio aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT aliseno aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT vbianco aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT ntshaked aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets AT pferraro aiaidedholographicflowcytometryforlabelfreeidentificationofovariancancercellsinthepresenceofunbalanceddatasets |