Use Case 3 Model Development - CTL Lytic Arsenal

From the original set of 19 images, 5 images were selected for the training dataset and 4 for the test dataset. Each 3D image was composed of 4 channels. Use Case 3 dataset preparation is summarized in Supplementary Table ³. To reduce the computational cost, we resized the images (halved the size). We chose a threshold t=0.7 for the fitness function (AP70) to be more stringent with the predicted mask. To process a 3D image, we provided the z-sections of ι=1 channel (CD45) to the model, which generates o=1 mask (as summarized in Supplementary Table ⁴). All the masks were averaged to produce one final mask of the whole 3D image. We then applied the Local-Max Watershed Endpoint to produce the final 2D IS. Cells were segmented from the 19 original images using the best model out of 35 runs. 161 cells were filtered from predicted cells using their pixel area (2000px <area <14000px). For each cell, we calculated intensity features (see below) based on the perforin, granzyme B and CD107a channels (shown in Supplementary Fig. ^2e). All the cell’s feature vectors were then used to generate the UMAPs³⁴ of Fig. 4. To this end, we used the following parameters to the UMAP function: dimensionality reduction down to 2 components, using following parameters: n_neighbors=15, min_dist=0.01.