B reast density is an important risk factor for breast cancer (1-3). Additionally, areas of higher density can mask findings within mammograms, leading to lower sensitivity (4). Many states have passed breast density notification laws requiring clinics to inform women of their breast density (5). Radiologists typically assess breast density by using the Breast Imaging Reporting and Data System (BI-RADS) lexicon, which divides breast density into four categories: A, almost entirely fatty; B, scattered areas of fibroglandular density; C, heterogeneously dense; and D, extremely dense (examples are presented in Fig E1 [supplement]) (6). Unfortunately, radiologists exhibit intra-and interreader variability in the assessment of BI-RADS breast density, which can result in differences in clinical care and estimated risk (7-9).Deep learning (DL) has previously been used to assess BI-RADS breast density for film (10) and full-field digital mammographic (FFDM) images (11-16), with some models demonstrating closer agreement with consensus estimates than individual radiologists (14). To realize the promise of the use of these DL models in clinical practice, two key challenges must be met. First, because digital breast tomosynthesis (DBT) is increasingly used in breast cancer screening (17) due to improved reader performance (18-20), DL models should be compatible with DBT examinations. To aid in radiologist interpretation of breast cancer and breast density, DBT examinations contain twodimensional images in addition to three-dimensional images. These two-dimensional images may be either FFDM images or synthetic two-dimensional mammographic (SM) images derived from the three-dimensional images. Figure E2 (supplement) shows the differences in image characteristics between FFDM and SM images. The relatively recent adoption of DBT at many institutions means that the datasets available for training DL models are often fairly limited for DBT examinations compared with FFDM examinations. Second, DL models must offer consistent performance across sites, where differences in imaging technology, patient demographics, or assessment practices could impact model performance. To be practical, this

Background: Major prevention trials for Alzheimer's disease (AD) are now focusing on multidomain lifestyle interventions. However, the exact combination of behavioral factors related to AD pathology remains unclear. In two cohorts of cognitively unimpaired individuals at risk of AD, we examined which combinations of personality traits, neuropsychiatric symptoms, and cognitive lifestyle (years of education or lifetime cognitive activity) related to the pathological hallmarks of AD, amyloid-beta and tau deposits.Methods: Some 115 older adults with a parental or multiple-sibling family history of sporadic AD (PREVENT-AD cohort) underwent amyloid and tau positron emission tomography (PET) and answered several questionnaires related to behavioral attributes. Separately, we studied 117 mutation carriers from the Dominantly Inherited AD (DIAN) cohort with amyloid PET and behavioral data. Using partial least squares analysis, we identified latent variables relating amyloid or tau pathology with combinations of personality traits, neuropsychiatric symptoms, and cognitive lifestyle. Results:In PREVENT-AD, lower neuroticism, neuropsychiatric burden and higher education were associated with less amyloid deposition (p=0.014). Lower neuroticism and neuropsychiatric features, along with higher measures of openness and extraversion, were related to less tau deposition (p=0.006). In DIAN, lower neuropsychiatric burden and higher education were also associated with less amyloid (p=0.005). The combination of these factors accounted for up to 14% of AD pathology. Conclusions:In the preclinical phase of both sporadic and autosomal dominant AD, multiple behavioral features were associated with AD pathology. These results may suggest potential pathways by which multi-domain interventions might help delay AD onset or progression.

Since the early 2000’s, much of the neuroimaging work at Washington University (WU) has been facilitated by the Central Neuroimaging Data Archive (CNDA), an XNAT-based imaging informatics system. The CNDA is uniquely related to XNAT, as it served as the original codebase for the XNAT open source platform. The CNDA hosts data acquired in over 1000 research studies, encompassing 36,000 subjects and more than 60,000 imaging sessions. Most imaging modalities used in modern human research are represented in the CNDA, including magnetic resonance (MR), positron emission tomography (PET), computed tomography (CT), nuclear medicine (NM), computed radiography (CR), digital radiography (DX), and ultrasound (US). However, the majority of the imaging data in the CNDA are MR and PET of the human brain. Currently, about 20% of the total imaging data in the CNDA is available by request to external researchers. CNDA’s available data includes large sets of imaging sessions and in some cases clinical, psychometric, tissue, or genetic data acquired in the study of Alzheimer’s disease, brain metabolism, cancer, HIV, sickle cell anemia, and Tourette syndrome.

Purpose Flourine-18-flortaucipir tau positron emission tomography (PET) was developed for the detection for Alzheimer’s disease. Human imaging studies have begun to investigate its use in chronic traumatic encephalopathy (CTE). Flortaucipir-PET to autopsy correlation studies in CTE are needed for diagnostic validation. We examined the association between end-of-life flortaucipir PET and postmortem neuropathological measurements of CTE-related tau in six former American football players. Methods Three former National Football League players and three former college football players who were part of the DIAGNOSE CTE Research Project died and agreed to have their brains donated. The six players had flortaucipir (tau) and florbetapir (amyloid) PET prior to death. All brains from the deceased participants were neuropathologically evaluated for the presence of CTE. On average, the participants were 59.0 (SD = 9.32) years of age at time of PET. PET scans were acquired 20.33 (SD = 13.08) months before their death. Using Spearman correlation analyses, we compared flortaucipir standard uptake value ratios (SUVRs) to digital slide-based AT8 phosphorylated tau (p-tau) density in a priori selected composite cortical, composite limbic, and thalamic regions-of-interest (ROIs). Results Four brain donors had autopsy-confirmed CTE, all with high stage disease (n = 3 stage III, n = 1 stage IV). Three of these four met criteria for the clinical syndrome of CTE, known as traumatic encephalopathy syndrome (TES). Two did not have CTE at autopsy and one of these met criteria for TES. Concomitant pathology was only present in one of the non-CTE cases (Lewy body) and one of the CTE cases (motor neuron disease). There was a strong association between flortaucipir SUVRs and p-tau density in the composite cortical (ρ = 0.71) and limbic (ρ = 0.77) ROIs. Although there was a strong association in the thalamic ROI (ρ = 0.83), this is a region with known off-target binding. SUVRs were modest and CTE and non-CTE cases had overlapping SUVRs and discordant p-tau density for some regions. Conclusions Flortaucipir-PET could be useful for detecting high stage CTE neuropathology, but specificity to CTE p-tau is uncertain. Off-target flortaucipir binding in the hippocampus and thalamus complicates interpretation of these associations. In vivo biomarkers that can detect the specific p-tau of CTE across the disease continuum are needed.

Stroke is one of the leading causes of death and disability worldwide. Reducing this disease burden through drug discovery and evaluation of stroke patient outcomes requires broader characterization of stroke pathophysiology, yet the underlying biologic and genetic factors contributing to outcomes are largely unknown. Remedying this critical knowledge gap requires deeper phenotyping, including large-scale integration of demographic, clinical, genomic, and imaging features. Such big data approaches will be facilitated by developing and running processing pipelines to extract stroke-related phenotypes at large scale. Millions of stroke patients undergo routine brain imaging each year, capturing a rich set of data on stroke-related injury and outcomes. The Stroke Neuroimaging Phenotype Repository (SNIPR) was developed as a multi-center centralized imaging repository of clinical computed tomography (CT) and magnetic resonance imaging (MRI) scans from stroke patients worldwide, based on the open source XNAT imaging informatics platform. The aims of this repository are to: (i) store, manage, process, and facilitate sharing of high-value stroke imaging data sets, (ii) implement containerized automated computational methods to extract image characteristics and disease-specific features from contributed images, (iii) facilitate integration of imaging, genomic, and clinical data to perform large-scale analysis of complications after stroke; and (iv) develop SNIPR as a collaborative platform aimed at both data scientists and clinical investigators. Currently, SNIPR hosts research projects encompassing ischemic and hemorrhagic stroke, with data from 2,246 subjects, and 6,149 imaging sessions from Washington University’s clinical image archive as well as contributions from collaborators in different countries, including Finland, Poland, and Spain. Moreover, we have extended the XNAT data model to include relevant clinical features, including subject demographics, stroke severity (NIH Stroke Scale), stroke subtype (using TOAST classification), and outcome [modified Rankin Scale (mRS)]. Image processing pipelines are deployed on SNIPR using containerized modules, which facilitate replicability at a large scale. The first such pipeline identifies axial brain CT scans from DICOM header data and image data using a meta deep learning scan classifier, registers serial scans to an atlas, segments tissue compartments, and calculates CSF volume. The resulting volume can be used to quantify the progression of cerebral edema after ischemic stroke. SNIPR thus enables the development and validation of pipelines to automatically extract imaging phenotypes and couple them with clinical data with the overarching aim of enabling a broad understanding of stroke progression and outcomes.