271 citations · 549 across the 18 of their papers we have counts for
20 papers
A persistent homology-based topological loss for CNN-based multi-class segmentation of CMR
Nick Byrne, James R Clough, Isra Valverde +2
Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration. The most popular C…
A persistent homology-based topological loss function for multi-class CNN segmentation of cardiac MRI
Nick Byrne, James R. Clough, Giovanni Montana +1
With respect to spatial overlap, CNN-based segmentation of short axis cardiovascular magnetic resonance (CMR) images has achieved a level of performance consistent with inter obser…
Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Prediction
Esther Puyol-Antón, Chen Chen, James R. Clough +9
Advances in deep learning (DL) have resulted in impressive accuracy in some medical image classification tasks, but often deep models lack interpretability. The ability of these mo…
Deep Learning Based Detection and Correction of Cardiac MR Motion Artefacts During Reconstruction for High-Quality Segmentation
Ilkay Oksuz, James R. Clough, Bram Ruijsink +6
Segmenting anatomical structures in medical images has been successfully addressed with deep learning methods for a range of applications. However, this success is heavily dependen…
A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology
James R. Clough, Nicholas Byrne, Ilkay Oksuz +3
We introduce a method for training neural networks to perform image or volume segmentation in which prior knowledge about the topology of the segmented object can be explicitly pro…
dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance
Jo Schlemper, Ilkay Oksuz, James R. Clough +5
AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited. We present dAUTOMAP, a novel way for decomposing the…
Self-supervised Recurrent Neural Network for 4D Abdominal and In-utero MR Imaging
Tong Zhang, Laurence H. Jackson, Alena Uus +5
Accurately estimating and correcting the motion artifacts are crucial for 3D image reconstruction of the abdominal and in-utero magnetic resonance imaging (MRI). The state-of-art m…
Topology-preserving augmentation for CNN-based segmentation of congenital heart defects from 3D paediatric CMR
Nick Byrne, James R. Clough, Isra Valverde +2
Patient-specific 3D printing of congenital heart anatomy demands an accurate segmentation of the thin tissue interfaces which characterise these diagnoses. Even when a label set ha…
Assessing the Impact of Blood Pressure on Cardiac Function Using Interpretable Biomarkers and Variational Autoencoders
Esther Puyol-Antón, Bram Ruijsink, James R. Clough +4
Maintaining good cardiac function for as long as possible is a major concern for healthcare systems worldwide and there is much interest in learning more about the impact of differ…
Detection and Correction of Cardiac MR Motion Artefacts during Reconstruction from K-space
lkay Oksuz, James Clough, Bram Ruijsink +7
In fully sampled cardiac MR (CMR) acquisitions, motion can lead to corruption of k-space lines, which can result in artefacts in the reconstructed images. In this paper, we propose…
Global and Local Interpretability for Cardiac MRI Classification
James R. Clough, Ilkay Oksuz, Esther Puyol-Anton +3
Deep learning methods for classifying medical images have demonstrated impressive accuracy in a wide range of tasks but often these models are hard to interpret, limiting their app…
Mechanically Powered Motion Imaging Phantoms: Proof of Concept
Alberto Gomez, Cornelia Schmitz, Markus Henningsson +8
Motion imaging phantoms are expensive, bulky and difficult to transport and set-up. The purpose of this paper is to demonstrate a simple approach to the design of multi-modality mo…
Explicit topological priors for deep-learning based image segmentation using persistent homology
James R. Clough, Ilkay Oksuz, Nicholas Byrne +2
We present a novel method to explicitly incorporate topological prior knowledge into deep learning based segmentation, which is, to our knowledge, the first work to do so. Our meth…
Magnetic Resonance Fingerprinting using Recurrent Neural Networks
Ilkay Oksuz, Gastao Cruz, James Clough +6
Magnetic Resonance Fingerprinting (MRF) is a new approach to quantitative magnetic resonance imaging that allows simultaneous measurement of multiple tissue properties in a single,…
Automatic CNN-based detection of cardiac MR motion artefacts using k-space data augmentation and curriculum learning
Ilkay Oksuz, Bram Ruijsink, Esther Puyol-Anton +8
Good quality of medical images is a prerequisite for the success of subsequent image analysis pipelines. Quality assessment of medical images is therefore an essential activity and…
Neural Embeddings of Graphs in Hyperbolic Space
Benjamin Paul Chamberlain, James Clough, Marc Peter Deisenroth
Neural embeddings have been used with great success in Natural Language Processing (NLP). They provide compact representations that encapsulate word similarity and attain state-of-…
Embedding Graphs in Lorentzian Spacetime
James R. Clough, Tim S. Evans
Geometric approaches to network analysis combine simply defined models with great descriptive power. In this work we provide a method for embedding directed acyclic graphs into Min…
Time and Citation Networks
James R. Clough, Tim S. Evans
Citation networks emerge from a number of different social systems, such as academia (from published papers), business (through patents) and law (through legal judgements). A citat…
What is the dimension of citation space?
James R. Clough, Tim S. Evans
Citation networks represent the flow of information between agents. They are constrained in time and so form directed acyclic graphs which have a causal structure. Here we provide…
Transitive Reduction of Citation Networks
James R. Clough, Jamie Gollings, Tamar V. Loach +1
In many complex networks the vertices are ordered in time, and edges represent causal connections. We propose methods of analysing such directed acyclic graphs taking into account…