Interpretable Classification of Tauopathies with a Convolutional Neural Network Pipeline Using Transfer Learning and Validation against Post-Mortem Clinical Cases of Alzheimer's Disease and Progressive Supranuclear Palsy.

Neurodegenerative diseases, tauopathies, constitute a serious global health problem. The etiology of these diseases is unclear and an increase in their incidence has been projected in the next 30 years. Therefore, the study of the molecular mechanisms that might stop these neurodegenerative processes is very relevant. Classification of neurodegenerative diseases using Machine and Deep Learning algorithms has been widely studied for medical imaging such as Magnetic Resonance Imaging. However, post-mortem immunofluorescence imaging studies of the brains of patients have not yet been used for this purpose. These studies may represent a valuable tool for monitoring aberrant chemical changes or pathological post-translational modifications of the Tau polypeptide. We propose a Convolutional Neural Network pipeline for the classification of Tau pathology of Alzheimer's disease and Progressive Supranuclear Palsy by analyzing post-mortem immunofluorescence images with different Tau biomarkers performed with models generated with the architecture ResNet-IFT using Transfer Learning. These models' outputs were interpreted with interpretability algorithms such as Guided Grad-CAM and Occlusion Analysis. To determine the best classifier, four different architectures were tested. We demonstrated that our design was able to classify diseases with an accuracy of 98.41% on average whilst providing an interpretation concerning the proper classification involving different structural patterns in the immunoreactivity of the Tau protein in NFTs present in the brains of patients with Progressive Supranuclear Palsy and Alzheimer's disease.

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.

Efforts have been made to diagnose and predict the course of different neurodegenerative diseases through various imaging techniques. Particularly tauopathies, where the tau polypeptide is a key participant in molecular pathogenesis, have significantly increased their morbidity and mortality in the human population over the years. However, the standard approach to exploring the phenomenon of neurodegeneration in tauopathies has not been directed at understanding the molecular mechanism that causes the aberrant polymeric and fibrillar behavior of the tau protein, which forms neurofibrillary tangles that replace neuronal populations in the hippocampal and cortical regions. The main objective of this work is to implement a novel quantification protocol for different biomarkers based on pathological post-translational modifications undergone by tau in the brains of patients with tauopathies. The quantification protocol consists of an adaptation of the U-Net neural network architecture. We used the resulting segmentation masks for the quantification of combined fluorescent signals of the different molecular changes tau underwent in neurofibrillary tangles. The quantification considers the neurofibrillary tangles as an individual study structure separated from the rest of the quadrant present in the images. This allows us to detect unconventional interaction signals between the different biomarkers. Our algorithm provides information that will be fundamental to understanding the pathogenesis of dementias with another computational analysis approach in subsequent studies.

Phospho-Tau Protein Expression in the Cell Cycle of SH-SY5Y Neuroblastoma Cells: A Morphological Study.

It has been reported that the main function of tau protein is to stabilize microtubules and promote the movement of organelles through the axon in neurons. In Alzheimer's disease, tau protein is the major constituent of the paired helical filament, and it undergoes post-translational modifications including hyperphosphorylation and truncation. Whether other functions of tau protein are involved in Alzheimer's disease is less clear. We used SH-SY5Y human neuroblastoma cells as an in vitro model to further study the functions of tau protein. We detected phosphorylated tau protein as small dense dots in the cell nucleus, which strongly colocalize with intranuclear speckle structures that were also labelled with an antibody to SC35, a protein involved in nuclear RNA splicing. We have shown further that tau protein, phosphorylated at the sites recognized by pT231, TG-3, and AD2 antibodies, is closely associated with cell division. Different functions may be characteristic of phosphorylation at specific sites. Our findings suggest that the presence of tau protein is involved in separation of sister chromatids in anaphase, and that tau protein also participates in maintaining the integrity of the DNA (pT231, prophase) and chromosomes during cell division (TG-3).

Pseudomonas aeruginosa: patogenicidad y resistencia antimicrobiana en la infección urinaria / Pseudomonas aeruginosa: pathogenicity and antimicrobial resistance in urinary tract infection

Resumen Dentro de las infecciones nosocomiales más frecuentes asociadas a bacterias multi-resistentes y de peor pronóstico, se encuentran las producidas por Pseudomonas aeruginosa. Esta bacteria posee una alta capacidad de adaptación a condiciones adversas como por ejemplo el pH y la osmolaridad de la orina. Pseudomonas aeruginosa es uno de los principales patógenos implicados en infecciones nosocomiales y de pacientes inmunosuprimidos. Esta bacteria se considera un agente infeccioso oportunista que posee diversos mecanismos de patogenicidad, así como de resistencia a antimicrobianos, lo que contribuye a la dificultad en el tratamiento de estas infecciones. En la presente revisión bibliográfica se analizan la taxonomía, los mecanismos de patogenicidad y genes de resistencia de P. aeruginosa. Así también, se abordan los factores microambientales de la infección urinaria producida por esta bacteria, haciendo un acercamiento al entendimiento de las bases fisiopatológicas de esta infección.

Among the most frequent nosocomial infections associated with polyresistant bacteria and with a worse prognosis, are those produced by Pseudomonas aeruginosa. This bacterium has a high capacity to adapt to adverse conditions such as pH and osmolarity of urine. Pseudomonas aeruginosa is one of the main pathogens involved in nosocomial infections and immunosuppressed patients. This bacterium is considered an opportunistic infectious agent that has diverse mechanisms of pathogenicity, as well as resistance to antimicrobials, which contributes to the difficulty in the treatment of these infections. In the present bibliographic review, the taxonomy, pathogenicity mechanisms and resistance genes of P. aeruginosa are analyzed. Likewise, the micro-environmental factors of the urinary infection produced by this bacterium are approached, making an approach to the understanding of the pathophysiological bases of this infection.