A novel automatic quantification protocol for biomarkers of tauopathies in the hippocampus and entorhinal cortex of post-mortem samples using an extended semi-Siamese U-Net

Abstract Through various imaging techniques, efforts have been made to diagnose and predict the course of different neurodegenerative diseases, which significantly increase their morbidity and mortality in the human population over the years, especially proteinopathies where the Tau polypeptide is a key participant in molecular pathogenesis. However, this standard approach to explore the phenomenon of neurodegener-ation has not been directed at understanding the molecular mechanism that causes the aberrant polymeric and fibrillar behavior of Tau protein in the neurofibrillary tangles that replace neuronal populations comprising the hippocampal formation and cortical regions of clinical cases with various proteinopathies. Our main objective was to implement a novel approach based on computational seg-mentation protocols in triple-labeled immunofluorescence imaging with different biomarkers based on pathological post-translational modifications undergone by Tau in brains of patients with tauopathies, implementing an adaptation of the U-Net neural network architecture. Importantly, we used the resulting segmentation masks and significantly quantified the individual and combined fluorescent signals of the different molecular changes Tau underwent in neurofibrillary tangles as individual study structures. Then, we separated them from the rest of the quadrant, detecting unconventional interaction signals between the different biomarkers. Our algorithm provides information that will be fundamental to understand the pathogenesis of dementias with another computational analysis approach in subsequent studies.