Show simple item record

dc.contributor.authorSundaresan, Vaanathi
dc.contributor.authorArthofer, Christoph
dc.contributor.authorZamboni, Giovanna
dc.contributor.authorDineen, Robert A
dc.contributor.authorRothwell, Peter M
dc.contributor.authorSotiropoulos, Stamatios N
dc.contributor.authorAuer, Dorothee P
dc.contributor.authorTozer, Daniel J
dc.contributor.authorMarkus, Hugh S
dc.contributor.authorMiller, Karla L
dc.contributor.authorDragonu, Iulius
dc.contributor.authorSprigg, Nikola
dc.contributor.authorAlfaro-Almagro, Fidel
dc.contributor.authorJenkinson, Mark
dc.contributor.authorGriffanti, Ludovica
dc.description.abstractCerebral microbleeds (CMBs) appear as small, circular, well defined hypointense lesions of a few mm in size on T2*-weighted gradient recalled echo (T2*-GRE) images and appear enhanced on susceptibility weighted images (SWI). Due to their small size, contrast variations and other mimics (e.g., blood vessels), CMBs are highly challenging to detect automatically. In large datasets (e.g., the UK Biobank dataset), exhaustively labelling CMBs manually is difficult and time consuming. Hence it would be useful to preselect candidate CMB subjects in order to focus on those for manual labelling, which is essential for training and testing automated CMB detection tools on these datasets. In this work, we aim to detect CMB candidate subjects from a larger dataset, UK Biobank, using a machine learning-based, computationally light pipeline. For our evaluation, we used 3 different datasets, with different intensity characteristics, acquired with different scanners. They include the UK Biobank dataset and two clinical datasets with different pathological conditions. We developed and evaluated our pipelines on different types of images, consisting of SWI or GRE images. We also used the UK Biobank dataset to compare our approach with alternative CMB preselection methods using non-imaging factors and/or imaging data. Finally, we evaluated the pipeline's generalisability across datasets. Our method provided subject-level detection accuracy > 80% on all the datasets (within-dataset results), and showed good generalisability across datasets, providing a consistent accuracy of over 80%, even when evaluated across different modalities.
dc.publisherFrontiers Media SA
dc.rightsAttribution 4.0 International
dc.sourcenlmid: 101477957
dc.sourceessn: 1662-5196
dc.subjectT2*-weighted MRI
dc.subjectUK Biobank
dc.subjectcerebral microbleeds
dc.subjectmachine learning
dc.subjectstructural MRI
dc.subjectsubject-level detection
dc.subjectsusceptibility weighted image (SWI)
dc.titleAutomated Detection of Candidate Subjects With Cerebral Microbleeds Using Machine Learning.
prism.publicationNameFront Neuroinform
dc.contributor.orcidMarkus, Hugh [0000-0002-9794-5996]
pubs.funder-project-idMedical Research Council (MR/L023784/2)

Files in this item


This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International