Publications
1021 results found
de Marvao A, McGurk KA, Zheng SL, et al., 2021, Outcomes and phenotypic expression of rare variants in hypertrophic cardiomyopathy genes amongst UK Biobank participants
<jats:title>Abstract</jats:title><jats:sec><jats:title>Background</jats:title><jats:p>Hypertrophic cardiomyopathy (HCM) is caused by rare variants in sarcomere-encoding genes, but little is known about the clinical significance of these variants in the general population.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>We compared outcomes and cardiovascular phenotypes in UK Biobank participants with whole exome sequencing stratified by sarcomere-encoding variant status.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>The prevalence of rare variants (allele frequency <0.00004) in HCM-associated sarcomere-encoding genes in 200,584 participants was 2.9% (n=5,727; 1 in 35), of which 0.24% (n=474, 1 in 423) were pathogenic or likely pathogenic variants (SARC-P/LP). SARC-P/LP variants were associated with increased risk of death or major adverse cardiac events compared to controls (HR 1.68, 95% CI 1.37-2.06, p<0.001), mainly due to heart failure (HR 4.40, 95% CI 3.22-6.02, p<0.001) and arrhythmia (HR 1.55, 95% CI 1.18-2.03, p=0.002). In 21,322 participants with cardiac magnetic resonance imaging, SARC-P/LP were associated with increased left ventricular maximum wall thickness (10.9±2.7 vs 9.4±1.6 mm, p<0.001) and concentric remodelling (mass/volume ratio: 0.63±0.12 vs 0.58±0.09 g/mL, p<0.001), but hypertrophy (≥13mm) was only present in 16% (n=7/43, 95% CI 7-31%). Other rare sarcomere-encoding variants had a weak effect on wall thickness (9.5±1.7 vs 9.4±1.6 mm, p=0.002) with no combined excess cardiovascular risk (HR 1.00 95% CI 0.92-1.08, p=0.9).</jats:p></jats:sec><jats:sec><jats:title>Conclusions</jats:title><jats:p>In the general population, SARC-P/LP variants have low aggregate penetrance for overt HCM bu
Dima A, Paetzold JC, Jungmann F, et al., 2021, Segmentation of Peripancreatic Arteries in Multispectral Computed Tomography Imaging, Pages: 596-605, ISSN: 0302-9743
Pancreatic ductal adenocarcinoma is an aggressive form of cancer with a poor prognosis, where the operability and hence chance of survival is strongly affected by the tumor infiltration of the arteries. In an effort to enable an automated analysis of the relationship between the local arteries and the tumor, we propose a method for segmenting the peripancreatic arteries in multispectral CT images in the arterial phase. A clinical dataset was collected, and we designed a fast semi-manual annotation procedure, which requires around 20 min of annotation time per case. Next, we trained a U-Net based model to perform binary segmentation of the peripancreatic arteries, where we obtained a near perfect segmentation with a Dice score of 95.05 % in our best performing model. Furthermore, we designed a clinical evaluation procedure for our models; performed by two radiologists, yielding a complete segmentation of 85.31 % of the clinically relevant arteries, thereby confirming the clinical relevance of our method.
Hammernik K, Pan J, Rueckert D, et al., 2021, Motion-Guided Physics-Based Learning for Cardiac MRI Reconstruction, Pages: 900-907, ISSN: 1058-6393
In this work, we propose a robust learning-based cardiac motion estimation framework, to estimate non-rigid cardiac motion fields from undersampled cardiac data. Our proposed frameworks leverages the advantages of a lightweight motion estimation network and a combination of photometric and smoothness losses. This framework enables the prediction of cardiac motion fields to further improve on the downstream task of motion-compensated image reconstruction. We evaluate our motion estimation framework qualitatively and quantitatively on 41 in-house acquired 2D cardiac CINE MRIs. Our proposed method provides quantitatively competitive results to state-of-the art methods in motion estimation, and superior results in image reconstruction in terms of structural similarity metric and peak-signal-to-noise ratio. Furthermore, our frameworks allows for ~3500x faster motion estimation compared to state-of-the-art approaches, opening up the practical application potential for motion-guided physics-based image reconstruction.
Lu P, Bai W, Rueckert D, et al., 2021, Multiscale Graph Convolutional Networks for Cardiac Motion Analysis, Pages: 264-272, ISBN: 9783030787097
We propose a multiscale spatio-temporal graph convolutional network (MST-GCN) approach to learn the left ventricular (LV) motion patterns from cardiac MR image sequences. The MST-GCN follows an encoder-decoder framework. The encoder uses a sequence of multiscale graph computation units (MGCUs). The myocardial geometry is represented as a graph. The network models the internal relations of the graph nodes via feature extraction at different scales and fuses the feature across scales to form a global representation of the input cardiac motion. Based on this, the decoder employs a graph-based gated recurrent unit (G-GRU) to predict future cardiac motion. We show that the MST-GCN can automatically quantify the spatio-temporal patterns in cardiac MR that characterise cardiac motion. Experiments are performed on mid-ventricular short-axis view cardiac MR image sequence from the UK Biobank dataset. We compare the performance of cardiac motion prediction of the proposed method with ten different architectures and parameter settings. Experiments show that the proposed method inputting node positions and node velocities with multiscale graphs achieves the best performance with a mean squared error of 0.25 pixel between the ground truth node locations and our prediction. We also show that the proposed method can estimate a number of motion-related metrics, including endocardial radii, thickness and strain which are useful for regional LV function assessment.
Lu P, Bai W, Rueckert D, et al., 2021, Modelling Cardiac Motion via Spatio-Temporal Graph Convolutional Networks to Boost the Diagnosis of Heart Conditions, Pages: 56-65, ISSN: 0302-9743
We present a novel spatio-temporal graph convolutional networks (ST-GCN) approach to learn spatio-temporal patterns of left ventricular (LV) motion in cardiac MR cine images for improving the characterization of heart conditions. Specifically, a novel GCN architecture is used, where the sample nodes of endocardial and epicardial contours are connected as a graph to represent the myocardial geometry. We show that the ST-GCN can automatically quantify the spatio-temporal patterns in cine MR that characterise cardiac motion. Experiments are performed on healthy volunteers from the UK Biobank dataset. We compare different strategies for constructing cardiac structure graphs. Experiments show that the proposed methods perform well in estimating endocardial radii and characterising cardiac motion features for regional LV analysis.
Xiong Z, Xia Q, Hu Z, et al., 2021, A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging, Medical Image Analysis, Vol: 67, Pages: 1-14, ISSN: 1361-8415
Segmentation of medical images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) used for visualizing diseased atrial structures, is a crucial first step for ablation treatment of atrial fibrillation. However, direct segmentation of LGE-MRIs is challenging due to the varying intensities caused by contrast agents. Since most clinical studies have relied on manual, labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the 2018 Left Atrium Segmentation Challenge using 154 3D LGE-MRIs, currently the world's largest atrial LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show that the top method achieved a Dice score of 93.2% and a mean surface to surface distance of 0.7 mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved superior results than traditional methods and machine learning approaches containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for atrial LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field. Furthermore, the findings from this study can potentially be extended to other imaging datasets and modalitie
Qiu H, Qin C, Schuh A, et al., 2021, Learning Diffeomorphic and Modality-invariant Registration using B-splines, Pages: 645-664
We present a deep learning (DL) registration framework for fast mono-modal and multimodal image registration using differentiable mutual information and diffeomorphic B-spline free-form deformation (FFD). Deep learning registration has been shown to achieve competitive accuracy and significant speedups from traditional iterative registration methods. In this paper, we propose to use a B-spline FFD parameterisation of Stationary Velocity Field (SVF) to in DL registration in order to achieve smooth diffeomorphic deformation while being computationally-efficient. In contrast to most DL registration methods which use intensity similarity metrics that assume linear intensity relationship, we apply a differentiable variant of a classic similarity metric, mutual information, to achieve robust mono-modal and multi-modal registration. We carefully evaluated our proposed framework on mono- and multi-modal registration using 3D brain MR images and 2D cardiac MR images.
Andelic N, Røe C, Brunborg C, et al., 2021, Correction to: Frequency of fatigue and its changes in the first 6 months after traumatic brain injury: results from the CENTER-TBI study., J Neurol, Vol: 268, Pages: 74-76
Andelic N, Røe C, Brunborg C, et al., 2021, Frequency of fatigue and its changes in the first 6 months after traumatic brain injury: results from the CENTER-TBI study., J Neurol, Vol: 268, Pages: 61-73
BACKGROUND: Fatigue is one of the most commonly reported subjective symptoms following traumatic brain injury (TBI). The aims were to assess frequency of fatigue over the first 6 months after TBI, and examine whether fatigue changes could be predicted by demographic characteristics, injury severity and comorbidities. METHODS: Patients with acute TBI admitted to 65 trauma centers were enrolled in the study Collaborative European NeuroTrauma Effectiveness Research in TBI (CENTER-TBI). Subjective fatigue was measured by single item on the Rivermead Post-Concussion Symptoms Questionnaire (RPQ), administered at baseline, three and 6 months postinjury. Patients were categorized by clinical care pathway: admitted to an emergency room (ER), a ward (ADM) or an intensive care unit (ICU). Injury severity, preinjury somatic- and psychiatric conditions, depressive and sleep problems were registered at baseline. For prediction of fatigue changes, descriptive statistics and mixed effect logistic regression analysis are reported. RESULTS: Fatigue was experienced by 47% of patients at baseline, 48% at 3 months and 46% at 6 months. Patients admitted to ICU had a higher probability of experiencing fatigue than those in ER and ADM strata. Females and individuals with lower age, higher education, more severe intracranial injury, preinjury somatic and psychiatric conditions, sleep disturbance and feeling depressed postinjury had a higher probability of fatigue. CONCLUSION: A high and stable frequency of fatigue was found during the first 6 months after TBI. Specific socio-demographic factors, comorbidities and injury severity characteristics were predictors of fatigue in this study.
Pan J, Rueckert D, Kuestner T, et al., 2021, Efficient Image Registration Network for Non-Rigid Cardiac Motion Estimation, 4th International Workshop on Machine Learning for Medical Reconstruction (MLMIR) held as part of the e 24th Medical Image Computing and Computer Assisted Intervention (MICCAI), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 14-24, ISSN: 0302-9743
- Author Web Link
- Cite
- Citations: 1
Dahan S, Williams LZJ, Rueckert D, et al., 2021, Improving Phenotype Prediction Using Long-Range Spatio-Temporal Dynamics of Functional Connectivity, 4th International Workshop on Machine Learning in Clinical Neuroimaging (MLCN), Publisher: SPRINGER-VERLAG SINGAPORE PTE LTD, Pages: 145-154, ISSN: 0302-9743
- Author Web Link
- Cite
- Citations: 2
Bintsi K-M, Baltatzis V, Hammers A, et al., 2021, Voxel-Level Importance Maps for Interpretable Brain Age Estimation, 4th Int Workshop on Interpretabil of Machine Intelligence in Med Image Comp (iMIMIC) / 1st Int Workshop on Topol Data Analysis and Its Applicat for Med Data (TDA4MedicalData) at 24th Int Conf on Med Image Comp and Comp Assisted Intervent (MICCAI), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 65-74, ISSN: 0302-9743
- Author Web Link
- Cite
- Citations: 2
Kart T, Bai W, Glocker B, et al., 2021, DeepMCAT: Large-Scale Deep Clustering for Medical Image Categorization, 1st Workshop on Deep Generative Models for Medical Image Computing and Computer Assisted Intervention (DGM4MICCAI) / 1st MICCAI Workshop on Data Augmentation, Labelling, and Imperfections (DALI), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 259-267, ISSN: 0302-9743
- Author Web Link
- Cite
- Citations: 2
Hassan ON, Menten MJ, Bogunovic H, et al., 2021, DEEP LEARNING PREDICTION OF AGE AND SEX FROM OPTICAL COHERENCE TOMOGRAPHY, 18th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 238-242, ISSN: 1945-7928
- Author Web Link
- Cite
- Citations: 2
Johnson PM, Jeong G, Hammernik K, et al., 2021, Evaluation of the Robustness of Learned MR Image Reconstruction to Systematic Deviations Between Training and Test Data for the Models from the fastMRI Challenge, 4th International Workshop on Machine Learning for Medical Reconstruction (MLMIR) held as part of the e 24th Medical Image Computing and Computer Assisted Intervention (MICCAI), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 25-34, ISSN: 0302-9743
- Author Web Link
- Cite
- Citations: 3
Knolle M, Kaissis G, Jungmann F, et al., 2021, Efficient, high-performance semantic segmentation using multi-scale feature extraction, PLOS ONE, Vol: 16, ISSN: 1932-6203
- Author Web Link
- Cite
- Citations: 5
Kamnitsas K, Winzeck S, Kornaropoulos EN, et al., 2021, Transductive Image Segmentation: Self-training and Effect of Uncertainty Estimation., Publisher: Springer, Pages: 79-89
Kart T, Bai W, Glocker B, et al., 2021, DeepMCAT: Large-Scale Deep Clustering for Medical Image Categorization., CoRR, Vol: abs/2110.00109
Kart T, Bai W, Glocker B, et al., 2021, DeepMCAT: Large-Scale Deep Clustering for Medical Image Categorization., Publisher: Springer, Pages: 259-267
Budd S, Sinclair M, Day T, et al., 2021, Detecting Hypo-plastic Left Heart Syndrome in Fetal Ultrasound via Disease-Specific Atlas Maps., Publisher: Springer, Pages: 207-217
Lu P, Bai W, Rueckert D, et al., 2021, DYNAMIC SPATIO-TEMPORAL GRAPH CONVOLUTIONAL NETWORKS FOR CARDIAC MOTION ANALYSIS, 18th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 122-125, ISSN: 1945-7928
- Author Web Link
- Cite
- Citations: 3
Weatheritt J, Joules R, Wolz R, et al., 2020, Fully Automatic AI Segmentation of Subcortical Regions, Publisher: SPRINGER, Pages: 21-21, ISSN: 1933-7213
- Author Web Link
- Cite
- Citations: 1
Fitzgibbon SP, Harrison SJ, Jenkinson M, et al., 2020, The developing Human Connectome Project (dHCP) automated resting-state functional processing framework for newborn infants, NEUROIMAGE, Vol: 223, ISSN: 1053-8119
- Author Web Link
- Cite
- Citations: 40
Cullen H, Dimitrakopoulou K, Batalle D, et al., 2020, Can genetic determinants of brain structure be detected soon after birth?, Publisher: SPRINGERNATURE, Pages: 984-985, ISSN: 1018-4813
Haralampieva V, Rueckert D, Passerat-Palmbach J, 2020, A systematic comparison of encrypted machine learning solutions for image classification, CCS '20: 2020 ACM SIGSAC Conference on Computer and Communications Security, Publisher: ACM, Pages: 55-59
This work provides a comprehensive review of existing frameworks based on secure computing techniques in the context of private image classification. The in-depth analysis of these approaches is followed by careful examination of their performance costs, in particular runtime and communication overhead.To further illustrate the practical considerations when using different privacy-preserving technologies, experiments were conducted using four state-of-the-art libraries implementing secure computing at the heart of the data science stack: PySyft and CrypTen supporting private inference via Secure Multi-Party Computation, TF-Trusted utilising Trusted Execution Environments and HE-Transformer relying on Homomorphic encryption.Our work aims to evaluate the suitability of these frameworks from a usability, runtime requirements and accuracy point of view. In order to better understand the gap between state-of-the-art protocols and what is currently available in practice for a data scientist, we designed three neural network architecture to obtain secure predictions via each of the four aforementioned frameworks. Two networks were evaluated on the MNIST dataset and one on the Malaria Cell image dataset. We observed satisfying performances for TF-Trusted and CrypTen and noted that all frameworks perfectly preserved the accuracy of the corresponding plaintext model.
Fenchel D, Dimitrova R, Seidlitz J, et al., 2020, Development of microstructural and morphological cortical profiles in the neonatal brain, Cerebral Cortex, Vol: 30, Pages: 5767-5779, ISSN: 1047-3211
Interruptions to neurodevelopment during the perinatal period may have long-lasting consequences. However, to be able to investigate deviations in the foundation of proper connectivity and functional circuits, we need a measure of how this architecture evolves in the typically developing brain. To this end, in a cohort of 241 term-born infants, we used magnetic resonance imaging to estimate cortical profiles based on morphometry and microstructure over the perinatal period (37-44 weeks postmenstrual age, PMA). Using the covariance of these profiles as a measure of inter-areal network similarity (morphometric similarity networks; MSN), we clustered these networks into distinct modules. The resulting modules were consistent and symmetric, and corresponded to known functional distinctions, including sensory-motor, limbic, and association regions, and were spatially mapped onto known cytoarchitectonic tissue classes. Posterior regions became more morphometrically similar with increasing age, while peri-cingulate and medial temporal regions became more dissimilar. Network strength was associated with age: Within-network similarity increased over age suggesting emerging network distinction. These changes in cortical network architecture over an 8-week period are consistent with, and likely underpin, the highly dynamic processes occurring during this critical period. The resulting cortical profiles might provide normative reference to investigate atypical early brain development.
Chen L, Cuervas-Mons CG, Ramji S, et al., 2020, AUTOMATED AGE ESTIMATION OF ISCHAEMIC LESIONS FROM UNENHANCED CT, Publisher: SAGE PUBLICATIONS LTD, Pages: 296-296, ISSN: 1747-4930
Voormolen DC, Polinder S, von Steinbuechel N, et al., 2020, Health-related quality of life after traumatic brain injury: deriving value sets for the QOLIBRI-OS for Italy, The Netherlands and The United Kingdom., Qual Life Res, Vol: 29, Pages: 3095-3107
PURPOSE: The Quality of Life after Brain Injury overall scale (QOLIBRI-OS) measures health-related quality of life (HRQoL) after traumatic brain injury (TBI). The aim of this study was to derive value sets for the QOLIBRI-OS in three European countries, which will allow calculation of utility scores for TBI health states. METHODS: A QOLIBRI-OS value set was derived by using discrete choice experiments (DCEs) and visual analogue scales (VAS) in general population samples from the Netherlands, United Kingdom and Italy. A three-stage procedure was used: (1) A selection of health states, covering the entire spectrum of severity, was defined; (2) General population samples performed the health state valuation task using a web-based survey with three VAS questions and an at random selection of sixteen DCEs; (3) DCEs were analysed using a conditional logistic regression and were then anchored on the VAS data. Utility scores for QOLIBRI-OS health states were generated resulting in estimates for all potential health states. RESULTS: The questionnaire was completed by 13,623 respondents. The biggest weight increase for all attributes is seen from "slightly" to "not at all satisfied", resulting in the largest impact on HRQoL. "Not at all satisfied with how brain is working" should receive the greatest weight in utility calculations in all three countries. CONCLUSION: By transforming the QOLIBRI-OS into utility scores, we enabled the application in economic evaluations and in summary measures of population health, which may be used to inform decision-makers on the best interventions and strategies for TBI patients.
Ball G, Seidlitz J, O'Muircheartaigh J, et al., 2020, Cortical morphology at birth reflects spatiotemporal patterns of gene expression in the fetal human brain, PLOS BIOLOGY, Vol: 18, ISSN: 1544-9173
- Author Web Link
- Cite
- Citations: 22
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.