In vivo identification of apoptotic and extracellular vesicle-bound live cells using image-based deep learning

ABSTRACT

The in vivo detection of dead cells remains a major challenge due to technical hurdles. Here, we present a novel method, where injection of fluorescent milk fat globule-EGF factor 8 protein (MFG-E8) in vivo combined with imaging flow cytometry and deep learning allows the identification of dead cells based on their surface exposure of phosphatidylserine (PS) and other image parameters. A convolutional autoencoder (CAE) was trained on defined pictures and successfully used to identify apoptotic cells in vivo. However, unexpectedly, these analyses also revealed that the great majority of PS⁺ cells were not apoptotic, but rather live cells associated with PS⁺ extracellular vesicles (EVs). During acute viral infection apoptotic cells increased slightly, while up to 30% of lymphocytes were decorated with PS⁺ EVs of antigen-presenting cell (APC) exosomal origin. The combination of recombinant fluorescent MFG-E8 and the CAE-method will greatly facilitate analyses of cell death and EVs in vivo.

KEYWORDS:

• Extracellular Vesicles
• exosomes
• dendritic cells
• viral Infection
• irradiation
• apoptosis

Acknowledgments

We acknowledge the Core Facility Flow Cytometry at the Biomedical Center, Ludwig-Maxmilians-Universität München, for providing the ImageStream^X MKII imaging flow cytometer. N.K.C., A.L., T.K. were supported by a Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) fellowship through the Graduate School of Quantitative Biosciences Munich (QBM) and N.K.C. is supported additionally through the School of Life Sciences Weihenstephan, Technical University of Munich, Germany. F.J.T. acknowledges financial support by the Graduate School QBM, the DFG within the Collaborative Research Centre (CRC) 1243 (Subproject A17), by the Helmholtz Association (Incubator grant sparse2big, grant # ZT-I-0007), by the BMBF (grant# 01IS18036A and grant# 01IS18053A) and by the Chan Zuckerberg Initiative DAF (advised fund of Silicon Valley Community Foundation, 182835). T.B. is supported by the DFG CRC 1054 (TP B03) and Graduate School QBM. This work was funded by the DFG under Germany’s Excellence Strategy within the framework of the Munich Cluster for Systems Neurology (EXC 2145 SyNergy – ID 390857198) to M.K.

Author contributions

N.K.C. and F.J.T. developed the deep learning model and the data analysis pipeline. T.B. and J.K. planned experiments and wrote the paper. L.R., A.L., A.F.-A.K. and T.K. performed experiments. M.SCH. and M.S. provided electron microscopy expertise.

Declaration of interests

The authors declare no competing financial interests. T.B. and J.K. consult Bioconduct (France).

Supplemental Material

Supplemental data for this article can be accessed here.

Correction Statement

This article has been republished with minor changes. These changes do not impact the academic content of the article.

Additional information

Funding

This work was supported by the Helmholtz-Association [ZT-I-0007]; Deutsche Forschungsgemeinschaft [QBM]; Deutsche Forschungsgemeinschaft [QBM]; Deutsche Forschungsgemeinschaft [CRC1243]; Exzellenzcluster 2145 Munich Cluster for Systems Neurology (SyNergy) [ID 390857198]; Bundesministerium für Bildung und Forschung [01IS18036A, 01IS18053A]; Chan Zuckerberg Initiative DAF [182835]; DFG [CRC 1054]; DFG [QBM].