ABSTRACT
The amyloid aggregation of alpha-synuclein within the brain is associated with the pathogenesis of Parkinson's disease (PD) and other related synucleinopathies, including multiple system atrophy (MSA). Alpha-synuclein aggregates are a major therapeutic target for treatment of these diseases. We identify two small molecules capable of disassembling preformed alpha-synuclein fibrils. The compounds, termed CNS-11 and CNS-11g, disaggregate recombinant alpha-synuclein fibrils in vitro, prevent the intracellular seeded aggregation of alpha-synuclein fibrils, and mitigate alpha-synuclein fibril cytotoxicity in neuronal cells. Furthermore, we demonstrate that both compounds disassemble fibrils extracted from MSA patient brains and prevent their intracellular seeding. They also reduce in vivo alpha-synuclein aggregates in C. elegans. Both compounds also penetrate brain tissue in mice. A molecular dynamics-based computational model suggests the compounds may exert their disaggregating effects on the N terminus of the fibril core. These compounds appear to be promising therapeutic leads for targeting alpha-synuclein for the treatment of synucleinopathies.
Subject(s)
Multiple System Atrophy , Parkinson Disease , Synucleinopathies , Mice , Animals , alpha-Synuclein/metabolism , Synucleinopathies/pathology , Caenorhabditis elegans/metabolism , Parkinson Disease/pathology , Multiple System Atrophy/pathology , Brain/metabolism , Amyloid/metabolismABSTRACT
Despite much effort, antibody therapies for Alzheimer's disease (AD) have shown limited efficacy. Challenges to the rational design of effective antibodies include the difficulty of achieving specific affinity to critical targets, poor expression, and antibody aggregation caused by buried charges and unstructured loops. To overcome these challenges, we grafted previously determined sequences of fibril-capping amyloid inhibitors onto a camel heavy chain antibody scaffold. These sequences were designed to cap fibrils of tau, known to form the neurofibrillary tangles of AD, thereby preventing fibril elongation. The nanobodies grafted with capping inhibitors blocked tau aggregation in biosensor cells seeded with postmortem brain extracts from AD and progressive supranuclear palsy (PSP) patients. The tau capping nanobody inhibitors also blocked seeding by recombinant tau oligomers. Another challenge to the design of effective antibodies is their poor blood-brain barrier (BBB) penetration. In this study, we also designed a bispecific nanobody composed of a nanobody that targets a receptor on the BBB and a tau capping nanobody inhibitor, conjoined by a flexible linker. We provide evidence that the bispecific nanobody improved BBB penetration over the tau capping inhibitor alone after intravenous administration in mice. Our results suggest that the design of synthetic antibodies that target sequences that drive protein aggregation may be a promising approach to inhibit the prion-like seeding of tau and other proteins involved in AD and related proteinopathies.
Subject(s)
Alzheimer Disease , Single-Domain Antibodies , Supranuclear Palsy, Progressive , Humans , Animals , Mice , Alzheimer Disease/drug therapy , Alzheimer Disease/metabolism , tau Proteins/metabolism , Single-Domain Antibodies/pharmacology , Single-Domain Antibodies/metabolism , Neurofibrillary Tangles/metabolism , Supranuclear Palsy, Progressive/metabolism , Antibodies/metabolism , Brain/metabolismABSTRACT
Capsule networks (see Hinton et al., 2018) aim to encode knowledge of and reason about the relationship between an object and its parts. In this letter, we specify a generative model for such data and derive a variational algorithm for inferring the transformation of each model object in a scene and the assignments of observed parts to the objects. We derive a learning algorithm for the object models, based on variational expectation maximization (Jordan et al., 1999). We also study an alternative inference algorithm based on the RANSAC method of Fischler and Bolles (1981). We apply these inference methods to data generated from multiple geometric objects like squares and triangles ("constellations") and data from a parts-based model of faces. Recent work by Kosiorek et al. (2019) has used amortized inference via stacked capsule autoencoders to tackle this problem; our results show that we significantly outperform them where we can make comparisons (on the constellations data).
ABSTRACT
Hyaline protoplasmic astrocytopathy (HPA) describes a rare histologic finding of eosinophilic, hyaline cytoplasmic inclusions in astrocytes, predominantly in the cerebral cortex. It has mainly been observed in children and adults with a history of developmental delay and epilepsy, frequently with focal cortical dysplasia (FCD), but the nature and significance of these inclusions are unclear. In this study, we review the clinical and pathologic features of HPA and characterize the inclusions and brain tissue in which they are seen in surgical resection specimens from five patients with intractable epilepsy and HPA compared to five patients with intractable epilepsy without HPA using immunohistochemistry for filamin A, previously shown to label these inclusions, and a variety of astrocytic markers including aldehyde dehydrogenase 1 family member L1 (ALDH1L1), SRY-Box Transcription Factor 9 (SOX9), and glutamate transporter 1/excitatory amino acid transporter 2 (GLT-1/EAAT2) proteins. The inclusions were positive for ALDH1L1 with increased ALDH1L1 expression in areas of gliosis. SOX9 was also positive in the inclusions, although to a lesser intensity than the astrocyte nuclei. Filamin A labeled the inclusions but also labeled reactive astrocytes in a subset of patients. The immunoreactivity of the inclusions for various astrocytic markers and filamin A as well as the positivity of filamin A in reactive astrocytes raise the possibility that these astrocytic inclusions may be the result of an uncommon reactive or degenerative phenomenon.
Subject(s)
Drug Resistant Epilepsy , Epilepsy , Child , Adult , Humans , Filamins/metabolism , Hyalin , Brain/pathology , Astrocytes/pathologyABSTRACT
Barlow (1985) hypothesized that the co-occurrence of two events A and B is "suspicious" if P(A,B)â«P(A)P(B). We first review classical measures of association for 2 × 2 contingency tables, including Yule's Y (Yule, 1912), which depends only on the odds ratio λ and is independent of the marginal probabilities of the table. We then discuss the mutual information (MI) and pointwise mutual information (PMI), which depend on the ratio P(A,B)/P(A)P(B), as measures of association. We show that once the effect of the marginals is removed, MI and PMI behave similarly to Y as functions of λ. The pointwise mutual information is used extensively in some research communities for flagging suspicious coincidences. We discuss the pros and cons of using it in this way, bearing in mind the sensitivity of the PMI to the marginals, with increased scores for sparser events.
Subject(s)
ProbabilityABSTRACT
As diving foragers, sea ducks are vulnerable to underwater anthropogenic activity, including ships, underwater construction, seismic surveys and gillnet fisheries. Bycatch in gillnets is a contributing source of mortality for sea ducks, killing hundreds of thousands of individuals annually. We researched underwater hearing in sea duck species to increase knowledge of underwater avian acoustic sensitivity and to assist with possible development of gillnet bycatch mitigation strategies that include auditory deterrent devices. We used both psychoacoustic and electrophysiological techniques to investigate underwater duck hearing in several species including the long-tailed duck (Clangula hyemalis), surf scoter (Melanitta perspicillata) and common eider (Somateria mollissima). Psychoacoustic results demonstrated that all species tested share a common range of maximum auditory sensitivity of 1.0-3.0â kHz, with the long-tailed ducks and common eiders at the high end of that range (2.96â kHz), and surf scoters at the low end (1.0â kHz). In addition, our electrophysiological results from 4 surf scoters and 2 long-tailed ducks, while only tested at 0.5, 1 and 2â kHz, generally agree with the audiogram shape from our psychoacoustic testing. The results from this study are applicable to the development of effective acoustic deterrent devices or pingers in the 2-3â kHz range to deter sea ducks from anthropogenic threats.
Subject(s)
Ducks , Fisheries , Humans , Animals , Ducks/physiology , Acoustics , HearingABSTRACT
Intracerebral hemorrhage (ICH) is a significant cause of morbidity and mortality worldwide. Hypertension and cerebral amyloid angiopathy (CAA) are the most common causes of primary ICH, but the mechanism of hemorrhage in both conditions is unclear. Although fibrinoid necrosis and Charcot-Bouchard aneurysms (CBAs) have been postulated to underlie vessel rupture in ICH, the role and significance of CBAs in ICH has been controversial. First described as the source of bleeding in hypertensive hemorrhage, they are also one of the CAA-associated microangiopathies along with fibrinoid necrosis, fibrosis and "lumen within a lumen appearance." We describe clinicopathologic findings of CBAs found in 12 patients out of over 2700 routine autopsies at a tertiary academic medical center. CBAs were rare and predominantly seen in elderly individuals, many of whom had multiple systemic and cerebrovascular comorbidities including hypertension, myocardial and cerebral infarcts, and CAA. Only one of the 12 subjects with CBAs had a large ICH, and the etiology underlying the hemorrhage was likely multifactorial. Two CBAs in the basal ganglia demonstrated associated microhemorrhages, while three demonstrated infarcts in the vicinity. CBAs may not be a significant cause of ICH but are a manifestation of severe cerebral small vessel disease including both hypertensive arteriopathy and CAA.
Subject(s)
Brain Diseases/diagnosis , Microaneurysm/diagnosis , Aged , Aged, 80 and over , Arteriosclerosis/diagnosis , Atherosclerosis/diagnosis , Cerebral Amyloid Angiopathy/complications , Cerebral Hemorrhage/complications , Cerebrovascular Circulation , Female , Humans , Hypertension/complications , Male , Middle Aged , Risk FactorsABSTRACT
In this note, I study how the precision of a binary classifier depends on the ratio r of positive to negative cases in the test set, as well as the classifier's true and false-positive rates. This relationship allows prediction of how the precision-recall curve will change with r, which seems not to be well known. It also allows prediction of how Fß and the precision gain and recall gain measures of Flach and Kull (2015) vary with r.
ABSTRACT
Huntington's disease (HD), an inherited neurodegenerative disorder that principally affects striatum and cerebral cortex, is generally thought to have an adult onset. However, a small percentage of cases develop symptoms before 20 years of age. This juvenile variant suggests that brain development may be altered in HD. Indeed, recent evidence supports an important role of normal huntingtin during embryonic brain development and mutations in this protein cause cortical abnormalities. Functional studies also demonstrated that the cerebral cortex becomes hyperexcitable with disease progression. In this review, we examine clinical and experimental evidence that cortical development is altered in HD. We also provide preliminary evidence that cortical pyramidal neurons from R6/2 mice, a model of juvenile HD, are hyperexcitable and display dysmorphic processes as early as postnatal day 7. Further, some symptomatic mice present with anatomical abnormalities reminiscent of human focal cortical dysplasia, which could explain the occurrence of epileptic seizures in this genetic mouse model and in children with juvenile HD. Finally, we discuss recent treatments aimed at correcting abnormal brain development.
Subject(s)
Cerebral Cortex/growth & development , Cerebral Cortex/physiopathology , Cortical Excitability , Huntington Disease/physiopathology , Neurons/physiology , Animals , Cerebral Cortex/pathology , Disease Models, Animal , Humans , Huntingtin Protein/genetics , Huntington Disease/pathology , Mice, Transgenic , Neurons/pathologyABSTRACT
The objectives of the African Organization for Research and Training in Cancer (AORTIC), includes bringing products of decades of advances in cancer research to African populations through local and international collaboration. The consistent and huge growth in participation in the conferences and the diversity of the nations is a witness to the success of the organization thus far. The theme for the Tenth AORTIC International Conference on Cancer in Africa in Morocco in 2015 was "Road map to Cancer Control in Africa" and topics of discussion of paramount importance for low- and middle-income African countries included childhood cancers such as BL, cancers of the cervix, breast, and prostate; cancers associated with HIV-infection such as cervical, vulvar, and anal; as well as cancer care challenges associated with palliative care. The role of environmental factors that underlie some epigenetic changes in some of the cancers was emphasized. Oral and poster presentations from various parts of the continent indicate the growth of basic and translational science of cancer in the region, with studies revealing regional diversity in the frequencies of the triple-negative breast cancer, cervical cancer, prostate cancer, HCC, and Burkitt's lymphoma. There was a sign that Africa is trying to keep pace with the paradigm shift and focusing on translational medicine. This was shown by suggestions for application of genome-wide association studies, new generation sequencing, as well as the evaluation of single nucleotide polymorphisms that may be responsible for variable susceptibility in some of the prevalent cancers in people of African descent. J. Cell. Physiol. 232: 2287-2295, 2017. © 2016 Wiley Periodicals, Inc.
Subject(s)
Delivery of Health Care, Integrated/organization & administration , Developing Countries , Neoplasms/therapy , Translational Research, Biomedical/organization & administration , Africa/epidemiology , Attitude of Health Personnel , Diffusion of Innovation , Epigenesis, Genetic , Genetic Predisposition to Disease , HIV Infections/epidemiology , Health Knowledge, Attitudes, Practice , Humans , Interdisciplinary Communication , Life Style , Neoplasms/diagnosis , Neoplasms/epidemiology , Neoplasms/genetics , Phenotype , Prevalence , Prognosis , Risk FactorsABSTRACT
INTRODUCTION: High-resolution, artefact-free and accurately annotated physiological data are desirable in patients with brain injury both to inform clinical decision-making and for intelligent analysis of the data in applications such as predictive modelling. We have quantified the quality of annotation surrounding artefactual events and propose a factorial switching linear dynamical systems (FSLDS) approach to automatically detect artefact in physiological data collected in the neurological intensive care unit (NICU). METHODS: Retrospective analysis of the BrainIT data set to discover potential hypotensive events corrupted by artefact and identify the annotation of associated clinical interventions. Training of an FSLDS model on clinician-annotated artefactual events in five patients with severe traumatic brain injury. RESULTS: In a subset of 187 patients in the BrainIT database, 26.5 % of potential hypotensive events were abandoned because of artefactual data. Only 30 % of these episodes could be attributed to an annotated clinical intervention. As assessed by the area under the receiver operating characteristic curve metric, FSLDS model performance in automatically identifying the events of blood sampling, arterial line damping and patient handling was 0.978, 0.987 and 0.765, respectively. DISCUSSION: The influence of artefact on physiological data collected in the NICU is a significant problem. This pilot study using an FSLDS approach shows real promise and is under further development.
Subject(s)
Artifacts , Hypotension/physiopathology , Intracranial Hypertension/physiopathology , Monitoring, Physiologic , Arterial Pressure , Databases, Factual , Humans , Intracranial Pressure , Linear Models , Machine Learning , Medical Informatics , Pilot Projects , Retrospective Studies , Signal Processing, Computer-AssistedABSTRACT
We propose non-negative matrix factorisation with iterative restarts (iNMF) to model a noisy dataset of highly overlapping fluorophores with intermittent intensities. We can recover high-resolution images of individual sources from the optimised model, despite their high mutual overlap in the original data. Each source can have an arbitrary, unknown shape of the PSF and blinking behaviour. This allows us to use quantum dots as bright and stable fluorophores for localisation microscopy. We compare the iNMF results to CSSTORM, 3B and bSOFI. iNMF shows superior performance in the challenging task of super-resolution imaging using quantum dots. We can also retrieve axial localisation of the sources from the shape of the recovered PSF.
Subject(s)
Algorithms , Diagnostic Imaging , Fluorescent Dyes , Microscopy, Fluorescence/methods , Models, Theoretical , Quantum Dots , HumansABSTRACT
Fire suppression has negatively impacted thousands of acres of private and public lands in the United States. As a case study, the New Jersey Pine Barrens (NJPB) are a disturbance driven ecosystem that is experiencing serious ecological implications due to a loss of traditional forest thinning activities such as harvesting for forest products or thinning for wildfire fuel-load reduction measures coupled with a long-standing philosophy of fire suppression and dormant-season prescribed burning. Dense closed-canopy forest conditions, dissimilar to historic open-canopy forests of the NJPB, have reduced abundance and diversity of certain flora and fauna, including regionally imperiled breeding birds. In recent years, active forest stewardship (e.g., thinning, clear-cutting, and burning) has occurred on private and some public lands within the NJPB; however, the impact of such management on breeding birds is unclear due to a paucity of research on this subject within the NJPB. During 2012, 2013, 2016, and 2017, we conducted repeat-visit point counts (n = 1,800) for breeding songbirds across 75 control and 75 treatment sites within the NJPB to assess the influence of forest structure at three strata levels (groundcover, midstory profile, and canopy) on breeding bird communities. Specifically, we constructed a hierarchical community abundance model within a Bayesian framework for Bird Conservation Region (BCR) 30 priority upland birds (n = 12) within three species suites: Forested Upland, Scrub-Shrub (or Young Forest), and Grassland. At the community level, we found a negative relationship between bird abundance and live tree basal area. At the BCR 30 suite level, we found no relationship between Forested Upland suite-level abundance and any of the measured covariates; however, we found a negative relationship between percentage of woody groundcover and Scrub-Shrub suite-level abundance, and negative relationship between horizontal visual obstruction at 2 m above ground level and Grassland suite-level abundance. Furthermore, the two latter species suites exhibited a strong negative relationship with basal area. We recommend active forest stewardship that specifically targets opening the canopy to achieve basal areas between ~0-15 m2/ha via selective thinning, shelter cutting, and small-scale clear cutting. Mechanical treatment and prescribed burning would produce such conditions and have the added benefit of reducing fuel loads across this ~4,500 km2 landscape as well as assisting in carbon defense strategies for the region.
Subject(s)
Conservation of Natural Resources , Ecosystem , Forests , Animals , New Jersey , Conservation of Natural Resources/methods , Birds/physiology , Forestry/methods , Biodiversity , Songbirds/physiologyABSTRACT
Vascular dementia (VaD) is a white matter ischemic disease and the second-leading cause of dementia, with no direct therapy. Within the lesion site, cell-cell interactions dictate the trajectory towards disease progression or repair. To elucidate the underlying intercellular signaling pathways, a VaD mouse model was developed for transcriptomic and functional studies. The mouse VaD transcriptome was integrated with a human VaD snRNA-Seq dataset. A custom-made database encompassing 4053 human and 2032 mouse ligand-receptor (L-R) interactions identified significantly altered pathways shared between human and mouse VaD. Two intercellular L-R systems, Serpine2-Lrp1 and CD39-A3AR, were selected for mechanistic study as both the ligand and receptor were dysregulated in VaD. Decreased Seprine2 expression enhances OPC differentiation in VaD repair. A clinically relevant drug that reverses the loss of CD39-A3AR function promotes tissue and behavioral recovery in the VaD model. This study presents novel intercellular signaling targets and may open new avenues for VaD therapies.
ABSTRACT
Human immunodeficiency virus (HIV) and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) cause significant neurologic disease. Central nervous system (CNS) involvement of HIV has been extensively studied, with well-documented invasion of HIV into the brain in the initial stage of infection, while the acute effects of SARS-CoV-2 in the brain are unclear. Neuropathologic features of active HIV infection in the brain are well characterized whereas neuropathologic findings in acute COVID-19 are largely non-specific. On the other hand, neuropathologic substrates of chronic dysfunction in both infections, as HIV-associated neurocognitive disorders (HAND) and post-COVID conditions (PCC)/long COVID are unknown. Thus far, neuropathologic studies on patients with HAND in the era of combined antiretroviral therapy have been inconclusive, and autopsy studies on patients diagnosed with PCC have yet to be published. Further longitudinal, multidisciplinary studies on patients with HAND and PCC and neuropathologic studies in comparison to controls are warranted to help elucidate the mechanisms of CNS dysfunction in both conditions.
ABSTRACT
Although most birds are considered to be at least partially monogamous, molecular evidence continues to uncover that many species can have multiple sexual mates. Many species of Waterfowl (Order Anseriformes) consistently deploy alternative breeding strategies, and although cavity nesting species have been well studied, few attempts to understand rates of alternative breeding strategies exist in the Anatini tribe. Here, we assay mitochondrial DNA and thousands of nuclear markers across 20 broods of American black ducks (Anas rubripes; "black duck") that included 19 females and 172 offspring to study population structure as well as types and rates of secondary breeding strategies in coastal North Carolina. First, we report high levels of relatedness among nesting black ducks and offspring and while 17 (of 19) females were of pure black duck descent, three were found to be black duck x mallard (A. platyrhynchos) hybrids. Next, we evaluated for mismatched mitochondrial DNA and paternity identities across each female's clutch to determine types and frequency of alternative or secondary breeding strategies. Although we report that nest parasitism occurred in two nests, 37% (7 of 19) of the sampled nests were multi-paternal as a result of extra-pair copulation. In addition to being part of a mix of strategies used to increase fecundity by successfully breeding females, we posit nest densities providing easier alternative mate access for males also explains high rates of extra-pair copulation among our sampled black ducks. Ultimately, however, while some proportion of females of many species engage in forms of secondary breeding strategies, we conclude that the decision to do so appears to be seasonally flexible for each individual.
Subject(s)
Breeding , Ducks , Humans , Animals , Male , Female , North Carolina , Birds , Reproduction , Nesting BehaviorABSTRACT
Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research. This is a very challenging problem due to (i) the lack of distinguishing visual features for each mouse, and (ii) the close confines of the scene with constant occlusion, making standard visual tracking approaches unusable. However, a coarse estimate of each mouse's location is available from a unique RFID implant, so there is the potential to optimally combine information from (weak) tracking with coarse information on identity. To achieve our objective, we make the following key contributions: (a) the formulation of the object identification problem as an assignment problem (solved using Integer Linear Programming), (b) a novel probabilistic model of the affinity between tracklets and RFID data, and (c) a curated dataset with per-frame BB and regularly spaced ground-truth annotations for evaluating the models. The latter is a crucial part of the model, as it provides a principled probabilistic treatment of object detections given coarse localisation. Our approach achieves 77% accuracy on this animal identification problem, and is able to reject spurious detections when the animals are hidden.
ABSTRACT
Precise, scalable, and quantitative evaluation of whole slide images is crucial in neuropathology. We release a deep learning model for rapid object detection and precise information on the identification, locality, and counts of cored plaques and cerebral amyloid angiopathies (CAAs). We trained this object detector using a repurposed image-tile dataset without any human-drawn bounding boxes. We evaluated the detector on a new manually-annotated dataset of whole slide images (WSIs) from three institutions, four staining procedures, and four human experts. The detector matched the cohort of neuropathology experts, achieving 0.64 (model) vs. 0.64 (cohort) average precision (AP) for cored plaques and 0.75 vs. 0.51 AP for CAAs at a 0.5 IOU threshold. It provided count and locality predictions that correlated with gold-standard CERAD-like WSI scoring (p=0.07± 0.10). The openly-available model can quickly score WSIs in minutes without a GPU on a standard workstation.
ABSTRACT
Cerebral microbleeds (CMBs) detected on magnetic resonance imaging are common in patients with cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL). The neuropathologic correlates of CMBs are unclear. In this study, we characterized findings relevant to CMBs in autopsy brain tissue of 8 patients with genetically confirmed CADASIL and 10 controls within the age range of the CADASIL patients by assessing the distribution and extent of hemosiderin/iron deposits including perivascular hemosiderin leakage (PVH), capillary hemosiderin deposits, and parenchymal iron deposits (PID) in the frontal cortex and white matter, basal ganglia and cerebellum. We also characterized infarcts, vessel wall thickening, and severity of vascular smooth muscle cell degeneration. CADASIL subjects had a significant increase in hemosiderin/iron deposits compared with controls. This increase was principally seen with PID. Hemosiderin/iron deposits were seen in the majority of CADASIL subjects in all brain areas. PVH was most pronounced in the frontal white matter and basal ganglia around small to medium sized arterioles, with no predilection for the vicinity of vessels with severe vascular changes or infarcts. CADASIL subjects have increased brain hemosiderin/iron deposits but these do not occur in a periarteriolar distribution. Pathogenesis of these lesions remains uncertain.
Subject(s)
CADASIL , Leukoencephalopathies , Humans , CADASIL/complications , CADASIL/diagnostic imaging , CADASIL/pathology , Hemosiderin , Cerebral Infarction/complications , Cerebral Infarction/diagnostic imaging , Cerebral Infarction/pathology , Leukoencephalopathies/pathology , Magnetic Resonance Imaging , Cerebral Hemorrhage/complications , Cerebral Hemorrhage/diagnostic imaging , Cerebral Hemorrhage/pathology , IronABSTRACT
Precise, scalable, and quantitative evaluation of whole slide images is crucial in neuropathology. We release a deep learning model for rapid object detection and precise information on the identification, locality, and counts of cored plaques and cerebral amyloid angiopathy (CAA). We trained this object detector using a repurposed image-tile dataset without any human-drawn bounding boxes. We evaluated the detector on a new manually-annotated dataset of whole slide images (WSIs) from three institutions, four staining procedures, and four human experts. The detector matched the cohort of neuropathology experts, achieving 0.64 (model) vs. 0.64 (cohort) average precision (AP) for cored plaques and 0.75 vs. 0.51 AP for CAAs at a 0.5 IOU threshold. It provided count and locality predictions that approximately correlated with gold-standard human CERAD-like WSI scoring (p = 0.07 ± 0.10). The openly-available model can quickly score WSIs in minutes without a GPU on a standard workstation.