Publications
1026 results found
Dimitrova R, Arulkumaran S, Carney O, et al., 2021, Phenotyping the preterm brain: characterizing individual deviations from normative volumetric development in two large infant cohorts, Cerebral Cortex, Vol: 31, Pages: 3665-3677, ISSN: 1047-3211
The diverse cerebral consequences of preterm birth create significant challenges for understanding pathogenesis or predicting later outcome. Instead of focusing on describing effects common to the group, comparing individual infants against robust normative data offers a powerful alternative to study brain maturation. Here we used Gaussian process regression to create normative curves characterizing brain volumetric development in 274 term-born infants, modeling for age at scan and sex. We then compared 89 preterm infants scanned at term-equivalent age with these normative charts, relating individual deviations from typical volumetric development to perinatal risk factors and later neurocognitive scores. To test generalizability, we used a second independent dataset comprising of 253 preterm infants scanned using different acquisition parameters and scanner. We describe rapid, nonuniform brain growth during the neonatal period. In both preterm cohorts, cerebral atypicalities were widespread, often multiple, and varied highly between individuals. Deviations from normative development were associated with respiratory support, nutrition, birth weight, and later neurocognition, demonstrating their clinical relevance. Group-level understanding of the preterm brain disguises a large degree of individual differences. We provide a method and normative dataset that offer a more precise characterization of the cerebral consequences of preterm birth by profiling the individual neonatal brain.
Jaubert O, Cruz G, Bustin A, et al., 2021, T1, T2, and Fat Fraction Cardiac MR Fingerprinting: Preliminary Clinical Evaluation, JOURNAL OF MAGNETIC RESONANCE IMAGING, Vol: 53, Pages: 1253-1265, ISSN: 1053-1807
- Author Web Link
- Cite
- Citations: 22
Dou Q, So TY, Jiang M, et al., 2021, Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study, npj Digital Medicine, Vol: 4, Pages: 1-11, ISSN: 2398-6352
Data privacy mechanisms are essential for rapidly scaling medical training databases to capture the heterogeneity of patient data distributions toward robust and generalizable machine learning systems. In the current COVID-19 pandemic, a major focus of artificial intelligence (AI) is interpreting chest CT, which can be readily used in the assessment and management of the disease. This paper demonstrates the feasibility of a federated learning method for detecting COVID-19 related CT abnormalities with external validation on patients from a multinational study. We recruited 132 patients from seven multinational different centers, with three internal hospitals from Hong Kong for training and testing, and four external, independent datasets from Mainland China and Germany, for validating model generalizability. We also conducted case studies on longitudinal scans for automated estimation of lesion burden for hospitalized COVID-19 patients. We explore the federated learning algorithms to develop a privacy-preserving AI model for COVID-19 medical image diagnosis with good generalization capability on unseen multinational datasets. Federated learning could provide an effective mechanism during pandemics to rapidly develop clinically useful AI across institutions and countries overcoming the burden of central aggregation of large amounts of sensitive data.
Meng Q, Matthew J, Zimmer VA, et al., 2021, Mutual information-based disentangled neural networks for classifying unseen categories in different domains: application to fetal ultrasound imaging, IEEE Transactions on Medical Imaging, Vol: 40, Pages: 722-734, ISSN: 0278-0062
Deep neural networks exhibit limited generalizability across images with different entangled domain features and categorical features. Learning generalizable features that can form universal categorical decision boundaries across domains is an interesting and difficult challenge. This problem occurs frequently in medical imaging applications when attempts are made to deploy and improve deep learning models across different image acquisition devices, across acquisition parameters or if some classes are unavailable in new training databases. To ad-dress this problem, we propose Mutual Information-based Disentangled Neural Networks (MIDNet), which extract generalizable categorical features to transfer knowledge to unseen categories in a target domain. The proposed MID-Net adopts a semi-supervised learning paradigm to alleviate the dependency on labeled data. This is important for real-world applications where data annotation is time-consuming, costly and requires training and expertise. We extensively evaluate the proposed method on fetal ultra-sound datasets for two different image classification tasks where domain features are respectively defined by shadow artifacts and image acquisition devices. Experimental results show that the proposed method outperforms the state-of-the-art on the classification of unseen categories in a target domain with sparsely labeled training data.
Balaban G, Halliday B, Bradley P, et al., 2021, Late-gadolinium enhancement interface area and electrophysiological simulations predict arrhythmic events in non-ischemic dilated cardiomyopathy patients, JACC: Clinical Electrophysiology, Vol: 7, Pages: 238-249, ISSN: 2405-5018
BACKGROUND: The presence of late-gadolinium enhancement (LGE) predicts life threatening ventricular arrhythmias in non-ischemic dilated cardiomyopathy (NIDCM); however, risk stratification remains imprecise. LGE shape and simulations of electrical activity may be able to provide additional prognostic information.OBJECTIVE: This study sought to investigate whether shape-based LGE metrics and simulations of reentrant electrical activity are associated with arrhythmic events in NIDCM patients.METHODS: CMR-LGE shape metrics were computed for a cohort of 156 NIDCM patients with visible LGE and tested retrospectively for an association with an arrhythmic composite end-point of sudden cardiac death and ventricular tachycardia. Computational models were created from images and used in conjunction with simulated stimulation protocols to assess the potential for reentry induction in each patient’s scar morphology. A mechanistic analysis of the simulations was carried out to explain the associations. RESULTS: During a median follow-up of 1611 [IQR 881-2341] days, 16 patients (10.3%) met the primary endpoint. In an inverse probability weighted Cox regression, the LGE-myocardial interface area (HR:1.75; 95% CI:1.24-2.47; p=0.001), number of simulated reentries (HR: 1.4; 95% CI: 1.23-1.59; p<0.01) and LGE volume (HR:1.44; 95% CI:1.07-1.94; p=0.02) were associated with arrhythmic events. Computational modeling revealed repolarisation heterogeneity and rate-dependent block of electrical wavefronts at the LGE-myocardial interface as putative arrhythmogenic mechanisms directly related to LGE interface area.CONCLUSION: The area of interface between scar and surviving myocardium, as well as simulated reentrant activity, are associated with an elevated risk of major arrhythmic events in NIDCM patients with LGE and represent novel risk predictors.
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
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.