Foreign body response to neuroimplantation: machine learning–assisted quantitative analysis of astrogliosis

Neuroimplants represent an emerging medical technology, offering new therapeutic approaches for severe neurological and psychiatric disorders. One of the key limitations to long-term neuroimplant performance is the foreign body response elicited by intracortical implantation. Among the contributing cell types, astrocytes play a central role in glial scar formation around the implant, which can compromise device functionality. Implantation-induced astrogliosis can be assessed by quantifying immunofluorescence of the astrogliosis marker glial fibrillary acidic protein (GFAP) in brain sections. Here, we used a pipeline-embedded random forest classifier implemented in the LabKit plugin for Fiji software to compare GFAP expression and astrocyte morphology in peri-implant scar versus distant cortical areas. We report an increase in GFAP expression, cell area and astrocytic process length as well as redistribution of GFAP signal along astrocytic processes within scar regions. We compare multiple classifiers producing different astrocyte segmentation outcomes and describe a procedure for generating a robust set of classifiers applicable to samples from repeated and independent experiments. Our results highlight the potential of artificial intelligence–assisted image analysis for automated and quantitative assessment of implantation-induced cellular and tissue responses.