no code implementations • 24 Apr 2018 • Matthew Sinclair, Christian F. Baumgartner, Jacqueline Matthew, Wenjia Bai, Juan Cerrolaza Martinez, Yuanwei Li, Sandra Smith, Caroline L. Knight, Bernhard Kainz, Jo Hajnal, Andrew P. King, Daniel Rueckert
Measurement of head biometrics from fetal ultrasonography images is of key importance in monitoring the healthy development of fetuses.
no code implementations • 27 Jul 2018 • Esther Puyol-Anton, Bram Ruijsink, Helene Langet, Mathieu De Craene, Paolo Piro, Julia A. Schnabel, Andrew P. King
The availability of large scale databases containing imaging and non-imaging data, such as the UK Biobank, represents an opportunity to improve our understanding of healthy and diseased bodily function.
no code implementations • 30 Jul 2018 • Katarína Tóthová, Sarah Parisot, Matthew C. H. Lee, Esther Puyol-Antón, Lisa M. Koch, Andrew P. King, Ender Konukoglu, Marc Pollefeys
Surface reconstruction is a vital tool in a wide range of areas of medical image analysis and clinical research.
no code implementations • 15 Aug 2018 • Ilkay Oksuz, Bram Ruijsink, Esther Puyol-Anton, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Daniel Rueckert, Julia A. Schnabel, Andrew P. King
As this is a highly imbalanced classification problem (due to the high number of good quality images compared to the low number of images with motion artefacts), we propose a novel k-space based training data augmentation approach in order to address this problem.
no code implementations • 29 Oct 2018 • Ilkay Oksuz, Bram Ruijsink, Esther Puyol-Anton, James Clough, Gastao Cruz, Aurelien Bustin, Claudia Prieto, Rene Botnar, Daniel Rueckert, Julia A. Schnabel, Andrew P. King
Due to the high number of good quality images compared to the relatively low number of images with motion artefacts, we propose a novel data augmentation scheme based on synthetic artefact creation in k-space.
no code implementations • 19 Dec 2018 • Ilkay Oksuz, Gastao Cruz, James Clough, Aurelien Bustin, Nicolo Fuin, Rene M. Botnar, Claudia Prieto, Andrew P. King, Julia A. Schnabel
Magnetic Resonance Fingerprinting (MRF) is a new approach to quantitative magnetic resonance imaging that allows simultaneous measurement of multiple tissue properties in a single, time-efficient acquisition.
no code implementations • 29 Jan 2019 • James R. Clough, Ilkay Oksuz, Nicholas Byrne, Julia A. Schnabel, Andrew P. King
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.
no code implementations • 17 May 2019 • Alberto Gomez, Cornelia Schmitz, Markus Henningsson, James Housden, Yohan Noh, Veronika A. Zimmer, James R. Clough, Ilkay Oksuz, Nicolas Toussaint, Andrew P. King, Julia A. Schnabel
Motion imaging phantoms are expensive, bulky and difficult to transport and set-up.
no code implementations • 12 Jun 2019 • lkay Oksuz, James Clough, Bram Ruijsink, Esther Puyol-Anton, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Daniel Rueckert, Andrew P. King, Julia A. Schnabel
In this paper, we propose a method to automatically detect and correct motion-related artefacts in CMR acquisitions during reconstruction from k-space data.
no code implementations • 14 Jun 2019 • James R. Clough, Ilkay Oksuz, Esther Puyol-Anton, Bram Ruijsink, Andrew P. King, Julia A. Schnabel
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 applicability in clinical practice.
no code implementations • 13 Aug 2019 • Esther Puyol-Antón, Bram Ruijsink, James R. Clough, Ilkay Oksuz, Daniel Rueckert, Reza Razavi, Andrew P. King
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 different risk factors on cardiac health.
no code implementations • 23 Aug 2019 • Nick Byrne, James R. Clough, Isra Valverde, Giovanni Montana, Andrew P. King
In a series of five-fold cross-validations, we demonstrate the performance gain produced by this pipeline and the relevance of topological considerations to the segmentation of congenital heart defects.
1 code implementation • 24 Sep 2019 • Jo Schlemper, Ilkay Oksuz, James R. Clough, Jinming Duan, Andrew P. King, Julia A. Schnabel, Joseph V. Hajnal, Daniel Rueckert
AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited.
1 code implementation • 4 Oct 2019 • James R. Clough, Nicholas Byrne, Ilkay Oksuz, Veronika A. Zimmer, Julia A. Schnabel, Andrew P. King
We show that the incorporation of the prior knowledge of the topology of this anatomy improves the resulting segmentations in terms of both the topological accuracy and the Dice coefficient.
no code implementations • 11 Oct 2019 • Ilkay Oksuz, James R. Clough, Bram Ruijsink, Esther Puyol Anton, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Andrew P. King, Julia A. Schnabel
In this paper, we discuss the implications of image motion artefacts on cardiac MR segmentation and compare a variety of approaches for jointly correcting for artefacts and segmenting the cardiac cavity.
no code implementations • 31 Jan 2020 • Esther Puyol Anton, Bram Ruijsink, Christian F. Baumgartner, Matthew Sinclair, Ender Konukoglu, Reza Razavi, Andrew P. King
The PHiSeg network and QC were validated against manual analysis on a cohort of the UK Biobank containing healthy subjects and chronic cardiomyopathy patients.
no code implementations • 2 May 2020 • Christopher J Arthurs, Andrew P. King
The contributions of this work are threefold: 1) To demonstrate that neural networks can be efficient aggregators of whole families of parameteric solutions to physical problems, trained using data created with traditional, trusted numerical methods such as finite elements.
no code implementations • 24 Jun 2020 • Esther Puyol-Antón, Chen Chen, James R. Clough, Bram Ruijsink, Baldeep S. Sidhu, Justin Gould, Bradley Porter, Mark Elliott, Vishal Mehta, Daniel Rueckert, Christopher A. Rinaldi, Andrew P. King
Our key contribution is that the VAE disentangles the latent space based on `explanations' drawn from existing clinical knowledge.
no code implementations • 21 Aug 2020 • Nick Byrne, James R. Clough, Giovanni Montana, Andrew P. King
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 observer variation.
no code implementations • 1 Sep 2020 • Bram Ruijsink, Esther Puyol-Anton, Ye Li, Wenja Bai, Eric Kerfoot, Reza Razavi, Andrew P. King
SemiQCSeg can be an efficient approach for training segmentation networks for medical image data when labelled datasets are scarce.
no code implementations • 6 Sep 2020 • Zhen Yuan, Esther Puyol-Anton, Haran Jogeesvaran, Catriona Reid, Baba Inusa, Andrew P. King
To the best of our knowledge, this is the first attempt to measure spleen size in a fully automated way from ultrasound images.
no code implementations • 2 Dec 2020 • Refik Soyak, Ebru Navruz, Eda Ozgu Ersoy, Gastao Cruz, Claudia Prieto, Andrew P. King, Devrim Unay, Ilkay Oksuz
Magnetic Resonance Fingerprinting (MRF) enables simultaneous mapping of multiple tissue parameters such as T1 and T2 relaxation times.
no code implementations • 23 Jun 2021 • Esther Puyol-Anton, Bram Ruijsink, Stefan K. Piechnik, Stefan Neubauer, Steffen E. Petersen, Reza Razavi, Andrew P. King
The subject of "fairness" in artificial intelligence (AI) refers to assessing AI algorithms for potential bias based on demographic characteristics such as race and gender, and the development of algorithms to address this bias.
no code implementations • 20 Jul 2021 • Esther Puyol-Antón, Baldeep S. Sidhu, Justin Gould, Bradley Porter, Mark K. Elliott, Vishal Mehta, Christopher A. Rinaldi, Andrew P. King
Next, a multimodal deep learning classifier is used for CRT response prediction, which combines the latent spaces of the segmentation models of the two modalities.
no code implementations • 16 Sep 2021 • Ines Machado, Esther Puyol-Anton, Kerstin Hammernik, Gastao Cruz, Devran Ugurlu, Bram Ruijsink, Miguel Castelo-Branco, Alistair Young, Claudia Prieto, Julia A. Schnabel, Andrew P. King
The framework consists of a deep learning model for the reconstruction of 2D+t cardiac cine MRI images from undersampled data, an image quality-control step to detect good quality reconstructions, followed by a deep learning model for bi-ventricular segmentation, a quality-control step to detect good quality segmentations and automated calculation of cardiac functional parameters.
no code implementations • 20 Sep 2021 • Jorge Mariscal-Harana, Naomi Kifle, Reza Razavi, Andrew P. King, Bram Ruijsink, Esther Puyol-Antón
Using manual segmentations as a reference, CMR slices were assigned to one of four regions: non-cardiac, base, middle, and apex.
no code implementations • 22 Sep 2021 • Tareen Dawood, Chen Chen, Robin Andlauer, Baldeep S. Sidhu, Bram Ruijsink, Justin Gould, Bradley Porter, Mark Elliott, Vishal Mehta, C. Aldo Rinaldi, Esther Puyol-Antón, Reza Razavi, Andrew P. King
Evaluation of predictive deep learning (DL) models beyond conventional performance metrics has become increasingly important for applications in sensitive environments like healthcare.
no code implementations • 22 Sep 2021 • Devran Ugurlu, Esther Puyol-Anton, Bram Ruijsink, Alistair Young, Ines Machado, Kerstin Hammernik, Andrew P. King, Julia A. Schnabel
Our dataset contains short axis images from 4 different MR scanners and 3 different pathology groups.
1 code implementation • 21 Mar 2022 • Esther Puyol-Antón, Bram Ruijsink, Baldeep S. Sidhu, Justin Gould, Bradley Porter, Mark K. Elliott, Vishal Mehta, Haotian Gu, Miguel Xochicale, Alberto Gomez, Christopher A. Rinaldi, Martin Cowie, Phil Chowienczyk, Reza Razavi, Andrew P. King
In this work we propose for the first time an AI approach for deriving advanced biomarkers of systolic and diastolic LV function from 2-D echocardiography based on segmentations of the full cardiac cycle.
no code implementations • 2 May 2022 • Inês P. Machado, Esther Puyol-Antón, Kerstin Hammernik, Gastão Cruz, Devran Ugurlu, Ihsane Olakorede, Ilkay Oksuz, Bram Ruijsink, Miguel Castelo-Branco, Alistair A. Young, Claudia Prieto, Julia A. Schnabel, Andrew P. King
Cine cardiac magnetic resonance (CMR) imaging is considered the gold standard for cardiac function evaluation.
no code implementations • 5 Aug 2022 • Germain Morilhat, Naomi Kifle, Sandra FinesilverSmith, Bram Ruijsink, Vittoria Vergani, Habtamu Tegegne Desita, Zerubabel Tegegne Desita, Esther Puyol-Anton, Aaron Carass, Andrew P. King
This work showcases, for the first time, the potential of DL in automating the process of effusion assessment from ultrasound in LMIC settings where there is often a lack of experienced radiologists to perform such tasks.
no code implementations • 13 Aug 2022 • Stefanos Ioannou, Hana Chockler, Alexander Hammers, Andrew P. King
We find significant sex and race bias effects in segmentation model performance.
no code implementations • 4 Sep 2022 • Tiarna Lee, Esther Puyol-Anton, Bram Ruijsink, Miaojing Shi, Andrew P. King
We present the first systematic study of the impact of training set imbalance on race and sex bias in CNN-based segmentation.
no code implementations • 28 Sep 2022 • Emily Chan, Ciaran O'Hanlon, Carlota Asegurado Marquez, Marwenie Petalcorin, Jorge Mariscal-Harana, Haotian Gu, Raymond J. Kim, Robert M. Judd, Phil Chowienczyk, Julia A. Schnabel, Reza Razavi, Andrew P. King, Bram Ruijsink, Esther Puyol-Antón
Flow analysis carried out using phase contrast cardiac magnetic resonance imaging (PC-CMR) enables the quantification of important parameters that are used in the assessment of cardiovascular function.
no code implementations • 30 Jan 2023 • Tareen Dawood, Emily Chan, Reza Razavi, Andrew P. King, Esther Puyol-Anton
However, in our complex artefact detection task, we saw an improvement in calibration for both a low and higher-capacity model when implementing both the ENN and uncertainty-aware training together, indicating that this approach can offer a promising way to improve calibration in such settings.
1 code implementation • 7 Jun 2023 • Hamideh Kerdegari, Tran Huy Nhat Phung1, Van Hao Nguyen, Thi Phuong Thao Truong, Ngoc Minh Thu Le, Thanh Phuong Le, Thi Mai Thao Le, Luigi Pisani, Linda Denehy, VITAL Consortium, Reza Razavi, Louise Thwaites, Sophie Yacoub, Andrew P. King, Alberto Gomez
Skeletal muscle atrophy is a common occurrence in critically ill patients in the intensive care unit (ICU) who spend long periods in bed.
no code implementations • 15 Aug 2023 • Zhen Yuan, Esther Puyol-Anton, Haran Jogeesvaran, Baba Inusa, Andrew P. King
While spleen length measured from ultrasound images is a commonly used surrogate for spleen size, spleen volume remains the gold standard metric for assessing splenomegaly and the severity of related clinical conditions.
no code implementations • 25 Aug 2023 • Tiarna Lee, Esther Puyol-Antón, Bram Ruijsink, Keana Aitcheson, Miaojing Shi, Andrew P. King
However, the severity and nature of the bias varies between the models, highlighting the importance of model choice when attempting to train fair AI-based segmentation models for medical imaging tasks.
no code implementations • 26 Aug 2023 • Cosmin I. Bercea, Esther Puyol-Antón, Benedikt Wiestler, Daniel Rueckert, Julia A. Schnabel, Andrew P. King
This work presents a novel analysis of biases in unsupervised anomaly detection.
no code implementations • 29 Aug 2023 • Tareen Dawood, Chen Chen, Baldeep S. Sidhua, Bram Ruijsink, Justin Goulda, Bradley Porter, Mark K. Elliott, Vishal Mehta, Christopher A. Rinaldi, Esther Puyol-Anton, Reza Razavi, Andrew P. King
The best-performing model in terms of both classification accuracy and the most common calibration measure, expected calibration error (ECE) was the Confidence Weight method, a novel approach that weights the loss of samples to explicitly penalise confident incorrect predictions.
no code implementations • 29 Sep 2023 • Mohamed Huti, Tiarna Lee, Elinor Sawyer, Andrew P. King
Recent research has shown that artificial intelligence (AI) models can exhibit bias in performance when trained using data that are imbalanced by protected attribute(s).
1 code implementation • 13 Nov 2023 • Paula Ramirez, Alena Uus, Milou P. M. van Poppel, Irina Grigorescu, Johannes K. Steinweg, David F. A. Lloyd, Kuberan Pushparajah, Andrew P. King, Maria Deprez
Adding a classifier improves the anatomical and topological accuracy of all correctly classified double aortic arch subjects.
no code implementations • 12 Mar 2024 • Iman Islam, Esther Puyol-Antón, Bram Ruijsink, Andrew J. Reader, Andrew P. King
A significant challenge faced when training with multiple diverse datasets is the variation in label presence, i. e. the combined data are often partially-labelled.