176 citations
- Imperial College LondonGB100 papers
- King's College LondonGB6 papers
- University of OxfordGB6 papers
- University College LondonGB5 papers
- University of CambridgeGB5 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- Technical University of MunichDE4 papers
- Institute for High Energy PhysicsES3 papers
- Institute of Group AnalysisGB3 papers
- Lancaster UniversityGB3 papers
- MRC London Institute of Medical SciencesGB3 papers
- Nanjing University of Science and TechnologyCN3 papers
8 papers · 2 filters
A Comprehensive Approach for Learning-based Fully-Automated Inter-slice Motion Correction for Short-Axis Cine Cardiac MR Image Stacks
Giacomo Tarroni, Ozan Oktay, Matthew Sinclair +7
In the clinical routine, short axis (SA) cine cardiac MR (CMR) image stacks are acquired during multiple subsequent breath-holds. If the patient cannot consistently hold the breath…
Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images
Jo Schlemper, Ozan Oktay, Michiel Schaap +4
We propose a novel attention gate (AG) model for medical image analysis that automatically learns to focus on target structures of varying shapes and sizes. Models trained with AGs…
Learning Interpretable Anatomical Features Through Deep Generative Models: Application to Cardiac Remodeling
Carlo Biffi, Ozan Oktay, Giacomo Tarroni +9
Alterations in the geometry and function of the heart define well-established causes of cardiovascular disease. However, current approaches to the diagnosis of cardiovascular disea…
CascadeCNN: Pushing the Performance Limits of Quantisation in Convolutional Neural Networks
Alexandros Kouris, Stylianos I. Venieris, Christos-Savvas Bouganis
This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, aiming to perform high-throughput inference. A two-stage architectu…
Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstruction
Maximilian Seitzer, Guang Yang, Jo Schlemper +9
Deep learning approaches have shown promising performance for compressed sensing-based Magnetic Resonance Imaging. While deep neural networks trained with mean squared error (MSE)…
NeuroNet: Fast and Robust Reproduction of Multiple Brain Image Segmentation Pipelines
Martin Rajchl, Nick Pawlowski, Daniel Rueckert +2
NeuroNet is a deep convolutional neural network mimicking multiple popular and state-of-the-art brain segmentation tools including FSL, SPM, and MALPEM. The network is trained on 5…