Medical imaging has enormous potential for early disease prediction, but is impeded by the difficulty and expense of acquiring datasets prior to symptom onset. UK Biobank aims to address this problem directly by acquiring high quality, consistently acquired imaging data from 100,000 predominantly healthy participants, with health outcomes tracked over coming decades. The brain imaging includes structural, diffusion and functional modalities. Along with body and cardiac imaging, genetics, lifestyle measures, biological phenotyping and health records, this is expected to enable discovery of imaging markers of a broad range of diseases at their earliest stages, as well Users may view, print, copy, and download text and data-mine the content in such documents, for the purposes of academic research, subject always to the full Conditions of use

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.

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 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 lack of direct replication apply to many fields, but perhaps particularly to fMRI. 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 answers to neuroscientific questions. Main textNeuroimaging, particularly using functional magnetic resonance imaging (fMRI), has become the primary tool of human neuroscience 1 , and recent advances in the acquisition and analysis of fMRI data have provided increasingly powerful means to dissect brain function. The most common form of fMRI (known as "blood oxygen level dependent" or BOLD fMRI) measures brain activity indirectly through localized changes in blood oxygenation that occur in relation to 2 synaptic signaling 2 . These signal changes provide the ability to map activation in relation to specific mental processes, identify functionally connected networks from resting fMRI 3 , characterize neural representational spaces 4 , and decode or predict mental function from brain activity 5,6 . These advances promise to offer important insights into the workings of the human brain, but also generate the potential for a "perfect storm" of irreproducible results. In particular, the high dimensionality of fMRI data, relatively low power of most fMRI studies, and the great amount of flexibility in data analysis all potentially contribute to a high degree of false positive findings.Recent years have seen intense interest in the reproducibility of scientific results and the degree to which some problematic yet common research practices may be responsible for high rates of false findings in the scientific literature, particularly within psychology but also more generally [7][8][9] . There is growing interest in "meta-research" 10 , and a corresponding growth in studies investigating factors that contribute to poor reproducibility. These factors include study design characteristics which may introduce bias, low statistical power, and flexibility in data collection, analysis, and reporting -termed "researcher degrees of freedom" by Simmons and colleagues 8 . There is clearly concern that these issues may be undermining the value of science -in the UK, the Academy of Medical Sciences recently convened a joint meeting with a number of other funders to explore these issues, while in the US the National Institutes of Health has an ongoing initiative to improve research reproducibility 11 .In this article we outline a number of potentially problematic research practices in neuroimaging that can lead to increased risk of false or exaggerated results. For each prob...

BackgroundCardiovascular 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.MethodsDeep 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).ResultsBy 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.ConclusionsWe show that an automated method achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.Electronic supplementary materialThe online version of this article (10.1186/s12968-018-0471-x) contains supplementary material, which is available to authorized users.