Label-free two-photon autofluorescence images of different immune cell types

These original images were obtained in a previous work by Lemire et al. ( DOI ) from immune cells that were isolated from the spleen (CD4+, CD8+ T cells, B cells) or bone marrow (macrophages, dendritic cells, neutrophils) of wildtype C57BL/6 mice, seeded on glass slides and imaged with a multiphoton microscope (TriMScope II, LaVision BioTec, Bielefeld, Germany) using filters that target autofluorescence from NADH (BP 450/70) and FAD (BP 560/40). In addition to these AF channels, the forward scattered Dodt channel was recorded (displayed in gray in all figures). Similar to DIC, Dodt contrast is a gradient-based technique, and it provides optical sectioning and improved visualization of thick tissue slices. Although it offers enhanced structural detail, its application for DL-based immune cell classification is less established, and, as with DIC, it primarily encodes morphological rather than biochemical or metabolic differences. Each full raw image had a size of 1,024x1,024 pixels across a field of view (FOV) of 405x405µm², containing dozens to hundreds of cells. The data was used to train deep neutral networks on the automated classification of these cell types, as described in our paper here: https://doi.org/10.1002/jbio.70260 Set A: Cell mixtureFirst, we investigated the potential to differentiate two different cell types (neutrophils and T cells) that were present in the same sample. In that case, T cells were stained with the allophycocyanin (APC)-labeled lymphocyte marker a-CD3 to obtain ground truth annotations. This APC signal had no significant spectral overlap with natural AF emissions (BP 675/67 for APC) and was subsequently recorded at a different excitation wavelength (810nm for AF and 1,040nm for APC) which prevented channel leakage entirely. In total, this data set consisted of 31 full field-of-view image pairs of label-free AF images. Four images only contained T cells, seven images only contained neutrophils and 20 images were from samples that contained roughly a 50:50 mixture of both cell types. An image processing procedure was developed in the open-source image processing software Fiji to crop single cell image patches from these full-FOV images. The image processing macro loaded the raw data and registered AF and APC images via Scale Invariant Feature Transform (SIFT). Cell detection was performed via semi-automated, user-validated Otsu-thresholding of the NADH channel (`setAutoThreshold("Otsu no-reset")'), auto adjusted to include 10% of bright pixels, and a human observer verified or adjusted the threshold manually, if needed. Thresholding was followed by Watershed and `Analyze Particles' (minimal size of 25pixels area and 0.3-1 circularity). The center of the detected regions of interest (ROI) was then used to crop a patch of 64x64 pixels (25.6x25.6µm² FOV) around it. For each image patch, the two AF channels and the Dodt channel were saved together as multi-channel TIF file. Cells at the edges of the original image were ignored to ensure a consistent size of 64x64 for all patches. The respective APC channel of the patch was used for thresholding to determine it as APC-positive or APC-negative. This procedure resulted in a data set with a total of 5,078 annotated image patches, each with a unique cell in the center. Set B: Multi-class data setIn the second case, we investigated the potential of two-photon induced AF for multi-class classification of several different cell types. For that purpose, we used a different experimental design in the available data base, where cell types were not mixed, and each isolated cell type was imaged separately without antibody reference. Therefore, annotations for each cell type were available from the experimental protocol instead of a fluorescence antibody. Purity of these isolated cell suspensions reached values of >95% in each case. In total, we pooled 85 unique full FOV images from six different cell types. These images were processed into 64x64 pixel patches following the same procedure as explained above, resulting in a total of 3,424 cell patches.