Tauopathies are a category of neurodegenerative diseases characterized by the presence of abnormal tau protein-containing neurofibrillary tangles (NFTs). NFTs are universally observed in aging, occurring with or without the concomitant accumulation of amyloid-beta peptide (Aβ) in plaques that typifies Alzheimer disease (AD), the most common tauopathy. Primary age-related tauopathy (PART) is an Aβ-independent process that affects the medial temporal lobe in both cognitively normal and impaired subjects. Determinants of symptomology in subjects with PART are poorly understood and require clinicopathologic correlation; however, classical approaches to staging tau pathology have limited quantitative reproducibility. As such, there is a critical need for unbiased methods to quantitatively analyze tau pathology on the histological level. Artificial intelligence (AI)-based convolutional neural networks (CNNs) generate highly accurate and precise computer vision assessments of digitized pathology slides, yielding novel histology metrics at scale. Here, we performed a retrospective autopsy study of a large cohort (n = 706) of human post-mortem brain tissues from normal and cognitively impaired elderly individuals with mild or no Aβ plaques (average age of death of 83.1 yr, range 55–110). We utilized a CNN trained to segment NFTs on hippocampus sections immunohistochemically stained with antisera recognizing abnormal hyperphosphorylated tau (p-tau), which yielded metrics of regional NFT counts, NFT positive pixel density, as well as a novel graph-theory based metric measuring the spatial distribution of NFTs. We found that several AI-derived NFT metrics significantly predicted the presence of cognitive impairment in both the hippocampus proper and entorhinal cortex (p < 0.0001). When controlling for age, AI-derived NFT counts still significantly predicted the presence of cognitive impairment (p = 0.04 in the entorhinal cortex; p = 0.04 overall). In contrast, Braak stage did not predict cognitive impairment in either age-adjusted or unadjusted models. These findings support the hypothesis that NFT burden correlates with cognitive impairment in PART. Furthermore, our analysis strongly suggests that AI-derived metrics of tau pathology provide a powerful tool that can deepen our understanding of the role of neurofibrillary degeneration in cognitive impairment.

The diagnosis of Parkinson’s disease (PD) is challenging at all stages due to variable symptomatology, comorbidities, and mimicking conditions. Postmortem assessment remains the gold standard for a definitive diagnosis. While it is well recognized that PD manifests pathologically in the central nervous system with aggregation of α-synuclein as Lewy bodies and neurites, similar Lewy-type synucleinopathy (LTS) is additionally found in the peripheral nervous system that may be useful as an antemortem biomarker. We have previously found that detection of LTS in submandibular gland (SMG) biopsies is sensitive and specific for advanced PD; however, the sensitivity is suboptimal especially for early-stage disease. Further, visual microscopic assessment of biopsies by a neuropathologist to identify LTS is impractical for large-scale adoption. Here, we trained and validated a convolutional neural network (CNN) for detection of LTS on 283 digital whole slide images (WSI) from 95 unique SMG biopsies. A total of 8,450 LTS and 35,066 background objects were annotated following an inter-rater reliability study with Fleiss Kappa = 0.72. We used transfer learning to train a CNN model to classify image patches (151 × 151 pixels at 20× magnification) with and without the presence of LTS objects. The trained CNN model showed the following performance on image patches: sensitivity: 0.99, specificity: 0.99, precision: 0.81, accuracy: 0.99, and F-1 score: 0.89. We further tested the trained network on 1230 naïve WSI from the same cohort of research subjects comprising 42 PD patients and 14 controls. Logistic regression models trained on features engineered from the CNN predictions on the WSI resulted in sensitivity: 0.71, specificity: 0.65, precision: 0.86, accuracy: 0.69, and F-1 score: 0.76 in predicting clinical PD status, and 0.64 accuracy in predicting PD stage, outperforming expert neuropathologist LTS density scoring in terms of sensitivity but not specificity. These findings demonstrate the practical utility of a CNN detector in screening for LTS, which can translate into a computational tool to facilitate the antemortem tissue-based diagnosis of PD in clinical settings.

Post‐mortem assessment remains the only option and a gold standard for a definitive diagnosis of Parkinson’s disease (PD). The antemortem diagnosis is challenging due to a variable clinical presentation and the abundance of mimicking conditions, obscuring the clinical picture and delaying the treatment. It is well established that while PD pathologically manifests in central nervous system with aggregation of α‐synuclein as Lewy bodies and Lewy neurites, this pathology is also found in the peripheral nervous system. Peripheral Lewy‐type synucleinopathy (LTS) is present in early PD, suggesting its utility as a diagnostic and prognostic biomarker. We have previously confirmed that detection of LTS in submandibular gland (SMG) biopsies is sensitive (.75) and specific (.90) for early PD. However, the assessment by a neuropathologist of multiple levels of such biopsy is laborious and time‐consuming.

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.

Background:Creutzfeldt-Jakob disease (CJD) is a rapidly progressive dementia with an illness duration averaging approximately 46 months. There are several challenges to conducting research and surveillance activities on CJD, including its rapid progression, difficulty to diagnosis, geographic dispersal, and rarity. Several studies have been conducted examining the utility of using teleneurology for research purposes of neurologic diseases. We conducted a feasibility study of using teleneurology for research and surveillance purposes inCJD.Methods:Subjectswere included in the study if theymet criteria for probable sporadic CJD (sCJD) or had a positive real-time quaking induced conversion (RT-QuIC) result. Subjects and a research partner were given a choice of in-person visit, teleneurology visit, or medical record review only. A standardized history and examination were collected as well as standardized instruments to measure cognition (Telephone Interview for Cognitive Status, TICS), functional status (MRC Prion Disease Rating Scale), and neuropsychiatric symptoms (Neuropsychiatric Inventory Questionnaire, NPI-Q). For teleneurology visits, subjects participated in the evaluation using secure software (Cisco Jabber) that could be installed on any internet connected device with a camera of their choice. Subjects were followed longitudinally on a monthly or bimonthly basis. Results:Over a 10-month period, the study received 81 referrals from 27 states. All but two enrolled subjects (95%) chose the teleneurology arm of the study and the majority participated from their homes (88%). Subjects and study partners expressed ease of use, convenience, and likelihood of recommending the teleneurology modality over other research modalities to potential participants. The quality of the examination depended on subject cooperation aswell as internet connectivity. All but one participant proceeded to autopsy (95% autopsy rate). Conclusions: This study demonstrates the feasibility of conducting research and surveillance activities of CJD subjects using teleneurology. Subjects preferred this modality, felt comfortable with its use, and may have been more likely to proceed to autopsy given involvement in the study. Further research should study the validity and reliability of instruments used to study this population remotely.

Accumulation of abnormal tau in neurofibrillary and glial tangles occurs in Alzheimer disease (AD) and a spectrum of amyloid-independent primary tauopathies. These tauopathies have diverse and overlapping morphological phenotypes that obscure diagnostic classification and quantitative assessments. There is a critical need to augment our ability to recognize and quantify tau pathology in post-mortem human brain tissues to facilitate clinical, genetic, and biomarker studies. Recently, powerful machine learning-based approaches have emerged that allow recognition and quantification of pathological changes from digital images. We are applying deep learning algorithms to augment the neuropathological assessment and create quantitative data for further clinicopathological correlations, as well as molecular and genomic studies of AD and neurodegenerative disease. Histopathological material was derived from brain samples from the Mount Sinai Alzheimer's Disease Research Center and the Mount Sinai/JJ Peters VA Medical Center Brain Bank (total n=1,700). We used a custom informatics platform to manage slide annotations and full slide images. Slides were imaged using the Philips Ultra Fast Scanner integrated with our in-house information management system. Human expert annotators labeled digital histology slides containing a range of pathological changes (e.g., tau tangles, diffuse plaques, neuritic plaques, and background elements). We utilized annotated whole slide regions to train a deep learning convolutional neural network (CNN) implemented in PyTorch against the human gold standard annotations. Our preliminary results show that the deep learning framework is capable of identifying and quantifying some pathological and diagnostic traits, which we further integrate with other metadata. We achieved >99% validation accuracy and <1% validation loss correctly distinguishing multiple degenerative features over 50 epochs in our framework consisting of 16,812,353 parameters of which 9,177,089 are trainable. Machine learning is a potentially useful tool for complex pathological assessment of AD and other tauopathies. Using our deep learning classifiers, we have the potential to integrate cell- and region-specific annotations with genetic, molecular and proteomic data. Such quantitative analysis provides unbiased data for clinicopathological correlations and enhances our knowledge of the disease.