Evolutionary design of explainable algorithms for biomedical image segmentation
Deep learning frameworks require large human-annotated datasets for training and the resulting ‘black box’ models are difficult to interpret. Here, the authors present Kartezio; a modular Cartesian Genetic Programming-based computational strategy that generates fully transparent and easily interpretable image processing pipelines.
Ultrarapid lytic granule release from CTLs activates Ca2+-dependent synaptic resistance pathways in melanoma cells
Using a preliminary version of Kartezio, we reveal a defensive configuration of melanoma nodules in vivo, in which melanoma cells facing Cytotoxic T Lymphocytes in the tumor periphery exhibited significant lysosomal enrichment.