Explore the vast range of titles available.

We developed a machine learning methodology for automatic sleep stage scoring. Our time-frequency analysis-based feature extraction is fine-tuned to capture sleep stage-specific signal features as described in the American Academy of Sleep Medicine manual that the human experts follow. We used ensemble learning with an ensemble of stacked sparse autoencoders for classifying the sleep stages. We used class-balanced random sampling across sleep stages for each model in the ensemble to avoid skewed performance in favor of the most represented sleep stages, and addressed the problem of misclassification errors due to class imbalance while significantly improving worst-stage classification. We used an openly available dataset from 20 healthy young adults for evaluation. We used a single channel of EEG from this dataset, which makes our method a suitable candidate for longitudinal monitoring using wearable EEG in real-world settings. Our method has both high overall accuracy (78%, range 75–80%), and high mean F 1 -score (84%, range 82–86%) and mean accuracy across individual sleep stages (86%, range 84–88%) over all subjects. The performance of our method appears to be uncorrelated with the sleep efficiency and percentage of transitional epochs in each recording.

UK Biobank is a population-based cohort of half a million participants aged 40–69 years recruited between 2006 and 2010. In 2014, UK Biobank started the world’s largest multi-modal imaging study, with the aim of re-inviting 100,000 participants to undergo brain, cardiac and abdominal magnetic resonance imaging, dual-energy X-ray absorptiometry and carotid ultrasound. The combination of large-scale multi-modal imaging with extensive phenotypic and genetic data offers an unprecedented resource for scientists to conduct health-related research. This article provides an in-depth overview of the imaging enhancement, including the data collected, how it is managed and processed, and future directions. Between 2014 and 2023, 100,000 UK Biobank participants are undergoing brain, heart and abdominal MRI, as well as DXA and carotid ultrasound scans. In this review, authors provide a detailed overview of the rationale for the collection of these imaging data, the procedures of data collection and management, and the future directions of the UK biobank imaging enhancement.

UK Biobank is a large-scale prospective epidemiological study with all data accessible to researchers worldwide. It is currently in the process of bringing back 100,000 of the original participants for brain, heart and body MRI, carotid ultrasound and low-dose bone/fat x-ray. The brain imaging component covers 6 modalities (T1, T2 FLAIR, susceptibility weighted MRI, Resting fMRI, Task fMRI and Diffusion MRI). Raw and processed data from the first 10,000 imaged subjects has recently been released for general research access. To help convert this data into useful summary information we have developed an automated processing and QC (Quality Control) pipeline that is available for use by other researchers. In this paper we describe the pipeline in detail, following a brief overview of UK Biobank brain imaging and the acquisition protocol. We also describe several quantitative investigations carried out as part of the development of both the imaging protocol and the processing pipeline.

Key Points There is growing concern about the reproducibility of scientific research, and neuroimaging research suffers from many features that are thought to lead to high levels of false results. Statistical power of neuroimaging studies has increased over time but remains relatively low, especially for group comparison studies. An analysis of effect sizes in the Human Connectome Project demonstrates that most functional MRI studies are not sufficiently powered to find reasonable effect sizes. Neuroimaging analysis has a high degree of flexibility in analysis methods, which can lead to inflated false-positive rates unless controlled for. Pre-registration of analysis plans and clear delineation of hypothesis-driven and exploratory research are potential solutions to this problem. The use of appropriate corrections for multiple tests has increased, but some common methods can have highly inflated false-positive rates. The use of non-parametric methods is encouraged to provide accurate correction for multiple tests. Software errors have the potential to lead to incorrect or irreproducible results. The adoption of improved software engineering methods and software testing strategies can help to reduce such problems. Reproducibility will be improved through greater transparency in methods reporting and through increased sharing of data and code. Neuroimaging techniques are increasingly applied by the wider neuroscience community. However, problems such as low statistical power, flexibility in data analysis and software issues pose challenges to interpreting neuroimaging data in a meaningful and reliable way. Here, Poldrack et al . discuss these and other problems, and suggest solutions. Functional neuroimaging techniques have transformed our ability to probe the neurobiological basis of behaviour and are increasingly being applied by the wider neuroscience community. However, concerns have recently been raised that the conclusions that are drawn from some human neuroimaging studies are either spurious or not generalizable. Problems such as low statistical power, flexibility in data analysis, software errors and a lack of direct replication apply to many fields, but perhaps particularly to functional MRI. Here, we discuss these problems, outline current and suggested best practices, and describe how we think the field should evolve to produce the most meaningful and reliable answers to neuroscientific questions.

Differences in cardiac and aortic structure and function are associated with cardiovascular diseases and a wide range of other types of disease. Here we analyzed cardiovascular magnetic resonance images from a population-based study, the UK Biobank, using an automated machine-learning-based analysis pipeline. We report a comprehensive range of structural and functional phenotypes for the heart and aorta across 26,893 participants, and explore how these phenotypes vary according to sex, age and major cardiovascular risk factors. We extended this analysis with a phenome-wide association study, in which we tested for correlations of a wide range of non-imaging phenotypes of the participants with imaging phenotypes. We further explored the associations of imaging phenotypes with early-life factors, mental health and cognitive function using both observational analysis and Mendelian randomization. Our study illustrates how population-based cardiac and aortic imaging phenotypes can be used to better define cardiovascular disease risks as well as heart–brain health interactions, highlighting new opportunities for studying disease mechanisms and developing image-based biomarkers. Using magnetic resonance images of the heart and aorta from 26,893 individuals in the UK Biobank, a phenome-wide association study associates cardiovascular imaging phenotypes with a wide range of demographic, lifestyle and clinical features.

Key Points CNS remyelination serves to limit and repair the damage in demyelinating diseases such as multiple sclerosis (MS) Several intrinsic molecular pathways that execute endogenous remyelination have been identified and are potential therapeutic targets The first clinical proof-of-concept trials to enhance remyelination in MS have been conducted in the past few years The optimal clinical and paraclinical outcome measures for the assessment of remyelination are not known, but neurophysiological measures, MRI, myelin-targeted PET radiotracers, and optical coherence tomography all are possible adjuncts to clinical outcomes in proof-of-concept studies The timing of remyelination therapy is a crucial issue Future MS therapy is likely to involve a combination of immunomodulatory and regenerative treatments Inadequate remyelination is central to degeneration and disability in patients with multiple sclerosis (MS); however, all currently approved therapies for MS are primarily immunomodulatory. Here, Martin Stangel and colleagues review our current knowledge of remyelination in MS, discuss results from clinical trials of remyelination-enhancing therapies, and evaluate the opportunities for future regenerative treatments. Remyelination in the CNS is the natural process of damage repair in demyelinating diseases such as multiple sclerosis (MS). However, remyelination becomes inadequate in many people with MS, which results in axonal degeneration and clinical disability. Enhancement of remyelination is a logical therapeutic goal; nevertheless, all currently licensed therapies for MS are immunomodulatory and do not support remyelination directly. Several molecular pathways have been identified as potential therapeutic targets to induce remyelination, and some of these have now been assessed in proof-of-concept clinical trials. However, trial design faces several obstacles: optimal clinical or paraclinical outcome measures to assess remyelination remain ill-defined, and identification of the ideal timing of therapy is also a crucial issue. In addition, realistic expectations are needed concerning the probable benefits of such therapies. Nevertheless, approaches that enhance remyelination are likely to be protective for axons and so could prevent long-term neurodegeneration. Future MS treatment paradigms, therefore, are likely to comprise a combinatorial approach that involves both immunomodulatory and regenerative treatments.

To better define roles that astrocytes and microglia play in Alzheimer’s disease (AD), we used single-nuclei RNA-sequencing to comprehensively characterise transcriptomes in astrocyte and microglia nuclei selectively enriched during isolation post-mortem from neuropathologically defined AD and control brains with a range of amyloid-beta and phospho-tau (pTau) pathology. Significant differences in glial gene expression (including AD risk genes expressed in both the astrocytes [CLU, MEF2C, IQCK] and microglia [APOE, MS4A6A, PILRA]) were correlated with tissue amyloid or pTau expression. The differentially expressed genes were distinct between with the two cell types and pathologies, although common (but cell-type specific) gene sets were enriched with both pathologies in each cell type. Astrocytes showed enrichment for proteostatic, inflammatory and metal ion homeostasis pathways. Pathways for phagocytosis, inflammation and proteostasis were enriched in microglia and perivascular macrophages with greater tissue amyloid, but IL1-related pathway enrichment was found specifically in association with pTau. We also found distinguishable sub-clusters in the astrocytes and microglia characterised by transcriptional signatures related to either homeostatic functions or disease pathology. Gene co-expression analyses revealed potential functional associations of soluble biomarkers of AD in astrocytes (CLU) and microglia (GPNMB). Our work highlights responses of both astrocytes and microglia for pathological protein clearance and inflammation, as well as glial transcriptional diversity in AD.

Background Cardiovascular resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocardial mass, providing information for diagnosis and monitoring of CVDs. However, for years, clinicians have been relying on manual approaches for CMR image analysis, which is time consuming and prone to subjective errors. It is a major clinical challenge to automatically derive quantitative and clinically relevant information from CMR images. Methods Deep neural networks have shown a great potential in image pattern recognition and segmentation for a variety of tasks. Here we demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network (FCN). The network is trained and evaluated on a large-scale dataset from the UK Biobank, consisting of 4,875 subjects with 93,500 pixelwise annotated images. The performance of the method has been evaluated using a number of technical metrics, including the Dice metric, mean contour distance and Hausdorff distance, as well as clinically relevant measures, including left ventricle (LV) end-diastolic volume (LVEDV) and end-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolic volume (RVEDV) and end-systolic volume (RVESV). Results By combining FCN with a large-scale annotated dataset, the proposed automated method achieves a high performance in segmenting the LV and RV on short-axis CMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR images. On a short-axis image test set of 600 subjects, it achieves an average Dice metric of 0.94 for the LV cavity, 0.88 for the LV myocardium and 0.90 for the RV cavity. The mean absolute difference between automated measurement and manual measurement is 6.1 mL for LVEDV, 5.3 mL for LVESV, 6.9 gram for LVM, 8.5 mL for RVEDV and 7.2 mL for RVESV. On long-axis image test sets, the average Dice metric is 0.93 for the LA cavity (2-chamber view), 0.95 for the LA cavity (4-chamber view) and 0.96 for the RA cavity (4-chamber view). The performance is comparable to human inter-observer variability. Conclusions We show that an automated method achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.

Alzheimer’s disease (AD) alters astrocytes, but the effect of Aß and Tau pathology is poorly understood. TRAP-seq translatome analysis of astrocytes in APP/PS1 ß-amyloidopathy and MAPT P301S tauopathy mice revealed that only Aß influenced expression of AD risk genes, but both pathologies precociously induced age-dependent changes, and had distinct but overlapping signatures found in human post-mortem AD astrocytes. Both Aß and Tau pathology induced an astrocyte signature involving repression of bioenergetic and translation machinery, and induction of inflammation pathways plus protein degradation/proteostasis genes, the latter enriched in targets of inflammatory mediator Spi1 and stress-activated cytoprotective Nrf2. Astrocyte-specific Nrf2 expression induced a reactive phenotype which recapitulated elements of this proteostasis signature, reduced Aß deposition and phospho-tau accumulation in their respective models, and rescued brain-wide transcriptional deregulation, cellular pathology, neurodegeneration and behavioural/cognitive deficits. Thus, Aß and Tau induce overlapping astrocyte profiles associated with both deleterious and adaptive-protective signals, the latter of which can slow patho-progression. Alzheimer’s disease is associated with changes in astrocytes. Here the authors investigated the astrocyte translatome associated with amyloid-ß and tau pathology.