Cell-MICS: Detecting Immune Cells With Label-Free Two-Photon Autofluorescence and Deep Learning

Kreiss L, Chaware A, Roohian M, Lemire S, Thoma OM, Carlé BE, Waldner M, Schürmann S, Friedrich O, Horstmeyer R (2026)

Publication Type: Journal article

Publication year: 2026

Journal

Journal of Biophotonics Wiley-VCH Verlag

Book Volume: 19

Article Number: e70260

Journal Issue: 4

DOI: 10.1002/jbio.70260

Abstract

Multiphoton imaging has been widely used for deep-tissue imaging. Although its label-free, metabolic contrast is ideal for investigating inflammation, the label-free two-photon induced autofluorescence is often regarded as less specific compared to conventional antibody markers. In this work, we investigate the potential for multiphoton imaging with computational specificity (MICS) by training a convolutional neural network on images of different immune cells. A low-complexity squeezeNet architecture was able to achieve reliable immune cell classification results (0.89 ROC-AUC, 0.95 PR-AUC for binary classification between T cells and neutrophils; 0.689 F1 score, 0.697 precision, 0.748 recall for multi-class classification between six isolated cell types). Perturbation tests confirmed that the model was not confused by the extracellular environment and that 2P-AF from NADH and FAD is equally important for the classification. In the future, deep learning could provide computational specificity for specific immune cells in unstained tissues, with great potential for label-free in vivo endomicroscopy.

Authors with CRIS profile

Sarah Lemire Department of Medicine 1 – Gastroenterology, Pneumology and Endocrinology Oana-Maria Thoma Department of Medicine 1 – Gastroenterology, Pneumology and Endocrinology Birgitta-Elisabeth Carlé Lehrstuhl für Medizinische Biotechnologie (MBT) Maximilian Waldner Department of Medicine 1 – Gastroenterology, Pneumology and Endocrinology Sebastian Schürmann Lehrstuhl für Medizinische Biotechnologie (MBT) Oliver Friedrich Lehrstuhl für Medizinische Biotechnologie (MBT)

Involved external institutions

Duke University US United States (USA) (US)

How to cite

APA:

Kreiss, L., Chaware, A., Roohian, M., Lemire, S., Thoma, O.-M., Carlé, B.-E.,... Horstmeyer, R. (2026). Cell-MICS: Detecting Immune Cells With Label-Free Two-Photon Autofluorescence and Deep Learning. Journal of Biophotonics, 19(4). https://doi.org/10.1002/jbio.70260

MLA:

Kreiss, Lucas, et al. "Cell-MICS: Detecting Immune Cells With Label-Free Two-Photon Autofluorescence and Deep Learning." Journal of Biophotonics 19.4 (2026).

BibTeX: Download