An Artificial Intelligent System for Prostate Cancer Diagnosis in Whole Slide Images.

In recent years a significant demand to develop computer-assisted diagnostic tools to assess prostate cancer using whole slide images has been observed. In this study we develop and validate a machine learning system for cancer assessment, inclusive of detection of perineural invasion and measurement of cancer portion to meet clinical reporting needs. The system analyses the whole slide image in three consecutive stages: tissue detection, classification, and slide level analysis. The whole slide image is divided into smaller regions (patches). The tissue detection stage relies upon traditional machine learning to identify WSI patches containing tissue, which are then further assessed at the classification stage where deep learning algorithms are employed to detect and classify cancer tissue. At the slide level analysis stage, entire slide level information is generated by aggregating all the patch level information of the slide. A total of 2340 haematoxylin and eosin stained slides were used to train and validate the system. A medical team consisting of 11 board certified pathologists with prostatic pathology subspeciality competences working independently in 4 different medical centres performed the annotations. Pixel-level annotation based on an agreed set of 10 annotation terms, determined based on medical relevance and prevalence, was created by the team. The system achieved an accuracy of 99.53% in tissue detection, with sensitivity and specificity respectively of 99.78% and 99.12%. The system achieved an accuracy of 92.80% in classifying tissue terms, with sensitivity and specificity respectively 92.61% and 99.25%, when 5x magnification level was used. For 10x magnification, these values were respectively 91.04%, 90.49%, and 99.07%. For 20x magnification they were 84.71%, 83.95%, 90.13%.

Spatiotemporal characterization of cellular tau pathology in the human locus coeruleus-pericoerulear complex by three-dimensional imaging.

Tau pathology of the noradrenergic locus coeruleus (LC) is a hallmark of several age-related neurodegenerative disorders, including Alzheimer's disease. However, a comprehensive neuropathological examination of the LC is difficult due to its small size and rod-like shape. To investigate the LC cytoarchitecture and tau cytoskeletal pathology in relation to possible propagation patterns of disease-associated tau in an unprecedented large-scale three-dimensional view, we utilized volume immunostaining and optical clearing technology combined with light sheet fluorescence microscopy. We examined AT8+ pathological tau in the LC/pericoerulear region of 20 brains from Braak neurofibrillary tangle (NFT) stage 0-6. We demonstrate an intriguing morphological complexity and heterogeneity of AT8+ cellular structures in the LC, representing various intracellular stages of NFT maturation and their diverse transition forms. We describe novel morphologies of neuronal tau pathology such as AT8+ cells with fine filamentous somatic protrusions or with disintegrating soma. We show that gradual dendritic atrophy is the first morphological sign of the degeneration of tangle-bearing neurons, even preceding axonal lesions. Interestingly, irrespective of the Braak NFT stage, tau pathology is more advanced in the dorsal LC that preferentially projects to vulnerable forebrain regions in Alzheimer's disease, like the hippocampus or neocortical areas, compared to the ventral LC projecting to the cerebellum and medulla. Moreover, already in the precortical Braak 0 stage, 3D analysis reveals clustering tendency and dendro-dendritic close appositions of AT8+ LC neurons, AT8+ long axons of NFT-bearing cells that join the ascending dorsal noradrenergic bundle after leaving the LC, as well as AT8+ processes of NFT-bearing LC neurons that target the 4th ventricle wall. Our study suggests that the unique cytoarchitecture, comprised of a densely packed and dendritically extensively interconnected neuronal network with long projections, makes the human LC to be an ideal anatomical template for early accumulation and trans-neuronal spreading of hyperphosphorylated tau.