Health AI Central
Share:
Peer-Reviewed Publication
Artif Intell Med2026;181103507.August 24, 2026Journal Article

Comparative evaluation of training strategies using partially labelled datasets for segmentation of white matter hyperintensities and stroke lesions in FLAIR MRI.

Jesse Phitidis1, Alison Q Smithard2, William N Whiteley3, Joanna M Wardlaw4, Miguel O Bernabeu5, Maria Valdés Hernández4
1Centre for Clinical Brain Sciences, University of Edinburgh, 49 Little France Crescent, Edinburgh, EH164SB, United Kingdom; Canon Medical Research Europe, Bonnington Bond, 2 Anderson Place, Edinburgh, EH65NP, United Kingdom. Electronic address: j.phitidis@ed.ac.uk.
2Canon Medical Research Europe, Bonnington Bond, 2 Anderson Place, Edinburgh, EH65NP, United Kingdom; School of Engineering, University of Edinburgh, Sanderson Building, Edinburgh, EH93FB, United Kingdom.
3Centre for Clinical Brain Sciences, University of Edinburgh, 49 Little France Crescent, Edinburgh, EH164SB, United Kingdom.
4Centre for Clinical Brain Sciences, University of Edinburgh, 49 Little France Crescent, Edinburgh, EH164SB, United Kingdom; UK Dementia Research Institute, Centre at The University of Edinburgh, 49 Little France Crescent, Edinburgh, EH164SB, United Kingdom.
5Usher Institute, University of Edinburgh, NINE, 9 Little France Road, Edinburgh, EH164UX, United Kingdom.
PubMed DOI

Abstract

White matter hyperintensities (WMH) and ischaemic stroke lesions (ISL) are key imaging biomarkers of cerebral small vessel disease (SVD) detectable on magnetic resonance imaging (MRI). The development of robust deep learning models to automatically segment and differentiate these pathologies remains challenging. Specifically, WMH and ISL frequently co-occur within the same subject and present as v…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.