7 papers
CLoPA: Continual Low Parameter Adaptation of Interactive Segmentation for Medical Image Annotation
Parhom Esmaeili, Chayanin Tangwiriyasakul, Eli Gibson +2
Interactive segmentation enables clinicians to guide annotation, but existing zero-shot models like nnInteractive fail to consistently reach expert-level performance across diverse…
Dynamic causal discovery in Alzheimer's disease through latent pseudotime modelling
Natalia Glazman, Jyoti Mangal, Pedro Borges +2
The application of causal discovery to diseases like Alzheimer's (AD) is limited by the static graph assumptions of most methods; such models cannot account for an evolving pathoph…
A methodology for clinically driven interactive segmentation evaluation
Parhom Esmaeili, Virginia Fernandez, Pedro Borges +3
Interactive segmentation is a promising strategy for building robust, generalisable algorithms for volumetric medical image segmentation. However, inconsistent and clinically unrea…
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…
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…
Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models
Guilherme Pombo, Robert Gray, Jorge Cardoso +4
We describe Countersynth, a conditional generative model of diffeomorphic deformations that induce label-driven, biologically plausible changes in volumetric brain images. The mode…