5 papers
HULFSynth : An INR based Super-Resolution and Ultra Low-Field MRI Synthesis via Contrast factor estimation
Pranav Indrakanti, Luca Trautmann, Ivor Simpson
We present an unsupervised single image bidirectional Magnetic Resonance Image (MRI) synthesizer that synthesizes an Ultra-Low Field (ULF) like image from a High-Field (HF) magnitu…
Learning Mechanistic Subtypes of Neurodegeneration with a Physics-Informed Variational Autoencoder Mixture Model
Sanduni Pinnawala, Annabelle Hartanto, Ivor J. A. Simpson +1
Modelling the underlying mechanisms of neurodegenerative diseases demands methods that capture heterogeneous and spatially varying dynamics from sparse, high-dimensional neuroimagi…
Evaluating structural uncertainty in accelerated MRI: are voxelwise measures useful surrogates?
Luca L. C. Trautmann, Peter A. Wijeratne, Itamar Ronen +1
Introducing accelerated reconstruction algorithms into clinical settings requires measures of uncertainty quantification that accurately assess the relevant uncertainty introduced…
Investigating the Role of Bilateral Symmetry for Inpainting Brain MRI
Sergey Kuznetsov, Sanduni Pinnawala, Peter A. Wijeratne +1
Inpainting has recently emerged as a valuable and interesting technology to employ in the analysis of medical imaging data, in particular brain MRI. A wide variety of methodologies…
Capturing Longitudinal Changes in Brain Morphology Using Temporally Parameterized Neural Displacement Fields
Aisha L. Shuaibu, Kieran A. Gibb, Peter A. Wijeratne +1
Longitudinal image registration enables studying temporal changes in brain morphology which is useful in applications where monitoring the growth or atrophy of specific structures…