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.
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 • 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 • 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 • 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 • 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 • 15 Jun 2022 • Jorge Mariscal-Harana, Clint Asher, Vittoria Vergani, Maleeha Rizvi, Louise Keehn, Raymond J. Kim, Robert M. Judd, Steffen E. Petersen, Reza Razavi, Andrew King, Bram Ruijsink, Esther Puyol-Antón
We show that our proposed tool, which combines image pre-processing steps, a domain-generalisable AI algorithm trained on a large-scale multi-domain CMR dataset and quality control steps, allows robust analysis of (clinical or research) databases from multiple centres, vendors, and cardiac diseases.
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.
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 • 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.
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 • 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 • 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 • 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 • 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 • 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 • 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 • 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 • 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 • 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 • 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 • 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 • 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.