Skip to main content

Research Repository

Advanced Search

Automated Detection of Candidate Subjects With Cerebral Microbleeds Using Machine Learning

Sundaresan, Vaanathi; Arthofer, Christoph; Zamboni, Giovanna; Dineen, Robert A.; Rothwell, Peter M.; Sotiropoulos, Stamatios N.; Auer, Dorothee P.; Tozer, Daniel J.; Markus, Hugh S.; Miller, Karla L.; Dragonu, Iulius; Sprigg, Nikola; Alfaro-Almagro, Fidel; Jenkinson, Mark; Griffanti, Ludovica

Automated Detection of Candidate Subjects With Cerebral Microbleeds Using Machine Learning Thumbnail


Authors

Vaanathi Sundaresan

Christoph Arthofer

Giovanna Zamboni

ROBERT DINEEN rob.dineen@nottingham.ac.uk
Professor of Neuroradiology

Peter M. Rothwell

DOROTHEE AUER dorothee.auer@nottingham.ac.uk
Professor of Neuroimaging

Daniel J. Tozer

Hugh S. Markus

Karla L. Miller

Iulius Dragonu

NIKOLA SPRIGG nikola.sprigg@nottingham.ac.uk
Professor of Stroke Medicine

Fidel Alfaro-Almagro

Mark Jenkinson

Ludovica Griffanti



Abstract

Cerebral 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.

Journal Article Type Article
Acceptance Date Dec 23, 2021
Online Publication Date Jan 20, 2022
Publication Date Jan 20, 2022
Deposit Date Jan 21, 2022
Publicly Available Date Jan 21, 2022
Journal Frontiers in Neuroinformatics
Electronic ISSN 1662-5196
Publisher Frontiers Media SA
Peer Reviewed Peer Reviewed
Volume 15
Article Number 777828
DOI https://doi.org/10.3389/fninf.2021.777828
Keywords Computer Science Applications; Biomedical Engineering; Neuroscience (miscellaneous)
Public URL https://nottingham-repository.worktribe.com/output/7283694
Publisher URL https://www.frontiersin.org/articles/10.3389/fninf.2021.777828/full

Files





You might also like



Downloadable Citations