Feasibility study of stain-free classification of cell apoptosis based on diffraction imaging flow cytometry and supervised machine learning techniques
- 136 Downloads
This study was to explore the feasibility of prediction and classification of cells in different stages of apoptosis with a stain-free method based on diffraction images and supervised machine learning. Apoptosis was induced in human chronic myelogenous leukemia K562 cells by cis-platinum (DDP). A newly developed technique of polarization diffraction imaging flow cytometry (p-DIFC) was performed to acquire diffraction images of the cells in three different statuses (viable, early apoptotic and late apoptotic/necrotic) after cell separation through fluorescence activated cell sorting with Annexin V-PE and SYTOX® Green double staining. The texture features of the diffraction images were extracted with in-house software based on the Gray-level co-occurrence matrix algorithm to generate datasets for cell classification with supervised machine learning method. Therefore, this new method has been verified in hydrogen peroxide induced apoptosis model of HL-60. Results show that accuracy of higher than 90% was achieved respectively in independent test datasets from each cell type based on logistic regression with ridge estimators, which indicated that p-DIFC system has a great potential in predicting and classifying cells in different stages of apoptosis.
KeywordsApoptosis Stain-free Machine learning Classification Diffraction image
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
- 4.Islam M, Brink H, Blanche S, DiPrete C, Bongiorno T, Stone N, Liu A, Philip A, Wang G, Lam W, Alexeev A, Waller EK, Sulchek T (2017) Microfluidic sorting of cells by viability based on differences in cell stiffness. Sci Rep 7(1):1997. https://doi.org/10.1038/s41598-017-01807-z CrossRefPubMedPubMedCentralGoogle Scholar
- 5.Nadalini M, Tarozzi N, Di Santo M, Borini A (2014) Annexin V magnetic-activated cell sorting versus swim-up for the selection of human sperm in ART: is the new approach better then the traditional one? J Assist Reprod Genet 31(8):1045–1051. https://doi.org/10.1007/s10815-014-0267-3 CrossRefPubMedPubMedCentralGoogle Scholar
- 10.Huh S, Kanade T (2013) Apoptosis detection for non-adherent cells in time-lapse phase contrast microscopy. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 16(Pt 2):59–66Google Scholar
- 11.Huh S, Ker DF, Su H, Kanade T (2012) Apoptosis detection for adherent cell populations in time-lapse phase-contrast microscopy images. In:International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 15(Pt 1):331–339Google Scholar
- 14.Mukhopadhyay P, Rajesh M, Hasko G, Hawkins BJ, Madesh M, Pacher P (2007) Simultaneous detection of apoptosis and mitochondrial superoxide production in live cells by flow cytometry and confocal microscopy. Nat Protoc 2(9):2295–2301. https://doi.org/10.1038/nprot.2007.327 CrossRefPubMedPubMedCentralGoogle Scholar
- 16.Wilkins RC, Kutzner BC, Truong M, Sanchez-Dardon J, McLean JR (2002) Analysis of radiation-induced apoptosis in human lymphocytes: flow cytometry using Annexin V and propidium iodide versus the neutral comet assay. Cytometry 48(1):14–19. https://doi.org/10.1002/cyto.10098 CrossRefPubMedGoogle Scholar
- 17.Peng L, Jiang H, Bradley C (2001) Annexin V for flow cytometric detection of phosphatidylserine expression on lymphoma cells undergoing apoptosis. Hua xi yi ke da xue xue bao = J West China Univ Med Sci = Huaxi yike daxue xuebao 32(4):602–620Google Scholar