7 papers
Metadata Supervised MRI Representations for Modelling and Controlling Acquisition Variability
Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez +5
Magnetic resonance imaging exhibits substantial acquisition variability, where identical anatomy can appear markedly different across scanners and imaging protocols. Consequently,…
Deep generative computed perfusion-deficit mapping of ischaemic stroke
Chayanin Tangwiriyasakul, Pedro Borges, Guilherme Pombo +8
Focal deficits in ischaemic stroke result from impaired perfusion downstream of a critical vascular occlusion. While parenchymal lesions are traditionally used to predict clinical…
DIST-CLIP: Arbitrary Metadata and Image Guided MRI Harmonization via Disentangled Anatomy-Contrast Representations
Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez +4
Deep learning holds immense promise for transforming medical image analysis, yet its clinical generalization remains profoundly limited. A major barrier is data heterogeneity. This…
Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control
Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez +4
Magnetic Resonance Imaging suffers from substantial data heterogeneity and the absence of standardized contrast labels across scanners, protocols, and institutions, which severely…
MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations
Mehmet Yigit Avci, Pedro Borges, Paul Wright +3
Accurate interpretation of Magnetic Resonance Imaging scans in clinical systems is based on a precise understanding of image contrast. This contrast is primarily governed by acquis…
Generalizable automated ischaemic stroke lesion segmentation with vision transformers
Chris Foulon, Robert Gray, James K. Ruffle +13
Ischaemic stroke, a leading cause of death and disability, critically relies on neuroimaging for characterising the anatomical pattern of injury. Diffusion-weighted imaging (DWI) p…