Image processing and Quality Control for the first 10,000 brain imaging datasets from UK Biobank

Abstract

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.

VERDICT‐AMICO: Ultrafast fitting algorithm for non‐invasive prostate microstructure characterization

“…Rapid‐fitting algorithms are important to analyse the large volume of data arising from studies and clinical trials and, potentially, to improve patient workflow during the clinical process. For example, the UK Biobank imaging project requires fitting up to 100 000 imaging datasets; only through the use of ultrafast‐fitting algorithms NODDI parameters have been included as imaging phenotypes in the project . Cohorts in PCa studies are also increasingly large and thus necessitate similar techniques.…”

Automated image quality evaluation of structural brain MRI using an ensemble of deep learning networks

“…However, only 7.2% of the cases were of unacceptable image quality. Alfaro‐Almagro et al reported high sensitivity (0.91) and specificity (0.84) in the multicenter UK BioBank study using the QAP pipeline . They developed a set of 190 IQMs to train three different classifiers: Bayes Network, Naïve Bayes, and MetaCost.…”

“…Automated quality assessment procedures compute specific image quality metrics (IQMs) and train a machine‐learning algorithm to rate image quality based on the extracted IQMs. The number of IQMs used can be as small as one or two, but can be as large as a few hundreds . Similar approaches have been proposed for diffusion MRI, functional MRI, and multimodal integration .…”

“…The accuracy of these methods depends on the performance of the hand‐crafted IQMs. However, crafting and selecting a suitable set of IQMs are highly subjective, and the extent to which the selected IQMs capture the majority of artifacts in multicenter datasets is yet to be proven . A plausible approach would be to allow the data to define their own IQMs.…”

Simulation and Synthesis in Medical Imaging

“…Image-based simulation and image synthesis will only gain relevance in the years to come: consider the tsunami of healthcare data 14 , emerging large-scale population imaging and its analytics 15,16 , and the growing role of machine learning 17,18,19 and computational medicine 20,21 , just to name a few trends. As perhaps never before, intensive industrial innovation in this area fuels translation of these technologies into clinical applications and commercial products.…”