Automated Detection of Candidate Subjects with Cerebral Microbleeds using Machine Learning
Automated Detection of Candidate Subjects with Cerebral Microbleeds using Machine Learning
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 (withindataset results), and showed good generalisability across datasets, providing a consistent accuracy of over 80%, even when evaluated across different modalities.
Sundaresan Vaanathi、Rothwell Peter M.、Arthofer Christoph、Dineen Robert A.、Sotiropoulos Stamatios N.、Markus Hugh S.、Dragonu Iulius、Alfaro-Almagro Fidel、Zamboni Giovanna、Sprigg Nikola、Auer Dorothee P.、Griffanti Ludovica、Miller Karla L.、Tozer Daniel、Jenkinson Mark
Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford||Oxford-Nottingham Centre for Doctoral Training in Biomedical Imaging, University of OxfordWolfson Centre for Prevention of Stroke and Dementia, Nuffield Department of Clinical Neurosciences, University of OxfordNIHR Nottingham Biomedical Research Centre, Queens Medical Centre, University of Nottingham||Sir Peter Mansfield Imaging Centre, University of Nottingham||Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of OxfordNIHR Nottingham Biomedical Research Centre, Queens Medical Centre, University of Nottingham||Sir Peter Mansfield Imaging Centre, University of Nottingham||Radiological Sciences, Mental Health & Clinical Neurosciences, School of Medicine, University of NottinghamNIHR Nottingham Biomedical Research Centre, Queens Medical Centre, University of Nottingham||Sir Peter Mansfield Imaging Centre, University of Nottingham||Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of OxfordDepartment of Clinical Neurosciences, University of CambridgeSiemens Healthcare Ltd, Research and Collaborations GB & IWellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of OxfordWellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford||Wolfson Centre for Prevention of Stroke and Dementia, Nuffield Department of Clinical Neurosciences, University of Oxford||Dipartimento di Scienze Biomediche, Metaboliche e Neuroscienze, Universit¨¤ di Modena e Reggio EmiliaStroke Trials Unit, Mental Health & Clinical Neuroscience, University of NottinghamNIHR Nottingham Biomedical Research Centre, Queens Medical Centre, University of Nottingham||Sir Peter Mansfield Imaging Centre, University of Nottingham||Radiological Sciences, Mental Health & Clinical Neurosciences, School of Medicine, University of NottinghamWellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford||Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Human Brain Activity, Department of Psychiatry, University of OxfordWellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of OxfordDepartment of Clinical Neurosciences, University of CambridgeWellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford||South Australian Health and Medical Research Institute (SAHMRI)||Australian Institute for Machine Learning (AIML), School of Computer Science, The University of Adelaide
医学研究方法神经病学、精神病学计算技术、计算机技术
cerebral microbleedsstructural MRIUK biobankmachine learningsusceptibility weighted imagingsubject-level detectionT2*-weighted MRI
Sundaresan Vaanathi,Rothwell Peter M.,Arthofer Christoph,Dineen Robert A.,Sotiropoulos Stamatios N.,Markus Hugh S.,Dragonu Iulius,Alfaro-Almagro Fidel,Zamboni Giovanna,Sprigg Nikola,Auer Dorothee P.,Griffanti Ludovica,Miller Karla L.,Tozer Daniel,Jenkinson Mark.Automated Detection of Candidate Subjects with Cerebral Microbleeds using Machine Learning[EB/OL].(2025-03-28)[2025-04-26].https://www.medrxiv.org/content/10.1101/2021.09.21.21263298.点此复制
评论