Artificial intelligence in neuropathology: deep learning-based assessment of tauopathy.

Accumulation of abnormal tau in neurofibrillary tangles (NFT) occurs in Alzheimer disease (AD) and a spectrum of tauopathies. These tauopathies have diverse and overlapping morphological phenotypes that obscure classification and quantitative assessments. Recently, powerful machine learning-based approaches have emerged, allowing the recognition and quantification of pathological changes from digital images. Here, we applied deep learning to the neuropathological assessment of NFT in postmortem human brain tissue to develop a classifier capable of recognizing and quantifying tau burden. The histopathological material was derived from 22 autopsy brains from patients with tauopathies. We used a custom web-based informatics platform integrated with an in-house information management system to manage whole slide images (WSI) and human expert annotations as ground truth. We utilized fully annotated regions to train a deep learning fully convolutional neural network (FCN) implemented in PyTorch against the human expert annotations. We found that the deep learning framework is capable of identifying and quantifying NFT with a range of staining intensities and diverse morphologies. With our FCN model, we achieved high precision and recall in naive WSI semantic segmentation, correctly identifying tangle objects using a SegNet model trained for 200 epochs. Our FCN is efficient and well suited for the practical application of WSIs with average processing times of 45 min per WSI per GPU, enabling reliable and reproducible large-scale detection of tangles. We measured performance on test data of 50 pre-annotated regions on eight naive WSI across various tauopathies, resulting in the recall, precision, and an F1 score of 0.92, 0.72, and 0.81, respectively. Machine learning is a useful tool for complex pathological assessment of AD and other tauopathies. Using deep learning classifiers, we have the potential to integrate cell- and region-specific annotations with clinical, genetic, and molecular data, providing unbiased data for clinicopathological correlations that will enhance our knowledge of the neurodegeneration.

Ice hockey summit II: zero tolerance for head hits and fighting.

OBJECTIVE: To present currently known basic science and on-ice influences of sport related concussion (SRC) in hockey, building upon the Ice Hockey Summit I action plan (2011) to reduce SRC. METHODS: The prior summit proceedings included an action plan intended to reduce SRC. As such, the proceedings from Summit I served as a point of departure, for the science and discussion held during Summit II (Mayo Clinic, Rochester MN, October, 2013). Summit II focused on Basic Science of Concussions in Ice Hockey: Taking Science Forward; (2) Acute and Chronic Concussion Care: Making a Difference; (3) Preventing Concussions via Behavior, Rules, Education and Measuring Effectiveness; (4) Updates in Equipment: their Relationship to Industry Standards and (5) Policies and Plans at State, National and Federal Levels to reduce SRC. Action strategies derived from the presentations and discussion described in these sectors were subsequently voted on for purposes of prioritization. The following proceedings include the knowledge and research shared by invited faculty, many of whom are health care providers and clinical investigators. RESULTS: The Summit II evidence based action plan emphasizes the rapidly evolving scientific content of hockey SRC. It includes the most highly prioritized strategies voted on for implementation to decrease concussion. CONCLUSIONS: The highest priority action items identified from the Summit include: 1) eliminate head hits from all levels of ice hockey, 2) change body checking policies, and 3) eliminate fighting in all amateur and professional hockey.