- Showing results for:
- Reset all filters
Journal articleBalaban G, Halliday BP, Bai W, et al., 2019,
Scar shape analysis and simulated electrical instabilities in a non-ischemic dilated cardiomyopathy patient cohort., PLoS Computational Biology, Vol: 15, Pages: 1-18, ISSN: 1553-734X
This paper presents a morphological analysis of fibrotic scarring in non-ischemic dilated cardiomyopathy, and its relationship to electrical instabilities which underlie reentrant arrhythmias. Two dimensional electrophysiological simulation models were constructed from a set of 699 late gadolinium enhanced cardiac magnetic resonance images originating from 157 patients. Areas of late gadolinium enhancement (LGE) in each image were assigned one of 10 possible microstructures, which modelled the details of fibrotic scarring an order of magnitude below the MRI scan resolution. A simulated programmed electrical stimulation protocol tested each model for the possibility of generating either a transmural block or a transmural reentry. The outcomes of the simulations were compared against morphological LGE features extracted from the images. Models which blocked or reentered, grouped by microstructure, were significantly different from one another in myocardial-LGE interface length, number of components and entropy, but not in relative area and transmurality. With an unknown microstructure, transmurality alone was the best predictor of block, whereas a combination of interface length, transmurality and number of components was the best predictor of reentry in linear discriminant analysis.
Journal articleMontaldo P, Lally P, Oliveira V, et al., 2019,
Therapeutic hypothermia initiated within 6 hours of birth is associated with reduced brain injury on MR biomarkers in mild hypoxic ischemic encephalopathy: a non-randomised cohort study, Archives of Disease in Childhood. Fetal and Neonatal Edition, Vol: 104, Pages: F515-F520, ISSN: 1359-2998
Objective To examine the effect of therapeutic hypothermia on MR biomarkers and neurodevelopmental outcomes in babies with mild hypoxic-ischaemic encephalopathy (HIE).Design Non-randomised cohort study.Setting Eight tertiary neonatal units in the UK and the USA.Patients 47 babies with mild HIE on NICHD neurological examination performed within 6 hours after birth.Interventions Whole-body cooling for 72 hours (n=32) or usual care (n=15; of these 5 were cooled for <12 hours).Main outcome measures MRI and MR spectroscopy (MRS) within 2 weeks after birth, and a neurodevelopmental outcome assessment at 2 years.Results The baseline characteristics in both groups were similar except for lower 10 min Apgar scores (p=0.02) in the cooled babies. Despite this, the mean (SD) thalamic NAA/Cr (1.4 (0.1) vs 1.6 (0.2); p<0.001) and NAA/Cho (0.67 (0.08) vs 0.89 (0.11); p<0.001) ratios from MRS were significantly higher in the cooled group. Cooled babies had lower white matter injury scores than non-cooled babies (p=0.02). Four (27%) non-cooled babies with mild HIE developed seizures after 6 hours of age, while none of the cooled babies developed seizures (p=0.008). Neurodevelopmental outcomes at 2 years were available in 40 (85%) of the babies. Adverse outcomes were seen in 2 (14.3%) non-cooled babies, and none of the cooled babies (p=0.09).Conclusions Therapeutic hypothermia may have a neuroprotective effect in babies with mild HIE, as demonstrated by improved MRS biomarkers and reduced white matter injury on MRI. This may warrant further evaluation in adequately powered randomised controlled trials.
Conference paperWang S, Dai C, Mo Y, et al., 2019,
Automatic Brain Tumour Segmentation and Biophysics-Guided Survival Prediction, MICCAI BraTS 2019 Challenge
Gliomas are the most common malignant brain tumourswith intrinsicheterogeneity. Accurate segmentation of gliomas and theirsub-regions onmulti-parametric magnetic resonance images (mpMRI)is of great clinicalimportance, which defines tumour size, shape andappearance and providesabundant information for preoperative diag-nosis, treatment planning andsurvival prediction. Recent developmentson deep learning have significantlyimproved the performance of auto-mated medical image segmentation. In thispaper, we compare severalstate-of-the-art convolutional neural network modelsfor brain tumourimage segmentation. Based on the ensembled segmentation, wepresenta biophysics-guided prognostic model for patient overall survivalpredic-tion which outperforms a data-driven radiomics approach. Our methodwonthe second place of the MICCAI 2019 BraTS Challenge for theoverall survivalprediction.
Conference paperDuan J, Schlemper J, Qin C, et al., 2019,
In this work, we propose a deep learning approach for parallel magnetic resonance imaging (MRI) reconstruction, termed a variable splitting network (VS-Net), for an efficient, high-quality reconstruction of undersampled multi-coil MR data. We formulate the generalized parallel compressed sensing reconstruction as an energy minimization problem, for which a variable splitting optimization method is derived. Based on this formulation we propose a novel, end-to-end trainable deep neural network architecture by unrolling the resulting iterative process of such variable splitting scheme. VS-Net is evaluated on complex valued multi-coil knee images for 4-fold and 6-fold acceleration factors. We show that VS-Net outperforms state-of-the-art deep learning reconstruction algorithms, in terms of reconstruction accuracy and perceptual quality. Our code is publicly available at https://github.com/j-duan/VS-Net.
Journal articleDuan J, Bello G, Schlemper J, et al., 2019,
Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach, IEEE Transactions on Medical Imaging, Vol: 38, Pages: 2151-2164, ISSN: 0278-0062
Deep learning approaches have achieved state-of-the-art performance incardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-constrained bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localisation tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, the refinement step is designed to explicitly enforce a shape constraint and improve segmentation quality. This step is effective for overcoming image artefacts (e.g. due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The proposed pipeline is fully automated, due to network's ability to infer landmarks, which are then used downstream in the pipeline to initialise atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution and anatomically smooth bi-ventricular3D models, despite the artefacts in input CMR volumes.
Conference paperDai C, Mo Y, Angelini E, et al., 2019,
Brain MR image segmentation is a key task in neuroimaging studies. It is commonly conducted using standard computational tools, such as FSL, SPM, multi-atlas segmentation etc, which are often registration-based and suffer from expensive computation cost. Recently, there is an increased interest using deep neural networks for brain image segmentation, which have demonstrated advantages in both speed and performance. However, neural networks-based approaches normally require a large amount of manual annotations for optimising the massive amount of network parameters. For 3D networks used in volumetric image segmentation, this has become a particular challenge, as a 3D network consists of many more parameters compared to its 2D counterpart. Manual annotation of 3D brain images is extremely time-consuming and requires extensive involvement of trained experts. To address the challenge with limited manual annotations, here we propose a novel multi-task learning framework for brain image segmentation, which utilises a large amount of automatically generated partial annotations together with a small set of manually created full annotations for network training. Our method yields a high performance comparable to state-of-the-art methods for whole brain segmentation.
Conference paperBai W, Chen C, Tarroni G, et al., 2019,
Self-supervised learning for cardiac MR image segmentation by anatomicalposition prediction, International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)
In the recent years, convolutional neural networks have transformed the field of medical image analysis due to their capacity to learn discriminative image features for a variety of classification and regression tasks. However, successfully learning these features requires a large amount of manuallyannotated data, which is expensive to acquire and limited by the availableresources of expert image analysts. Therefore, unsupervised, weakly-supervised and self-supervised feature learning techniques receive a lot of attention, which aim to utilise the vast amount of available data, while at the same time avoid or substantially reduce the effort of manual annotation. In this paper, we propose a novel way for training a cardiac MR image segmentation network, in which features are learnt in a self-supervised manner by predicting anatomical positions. The anatomical positions serve as a supervisory signal and do not require extra manual annotation. We demonstrate that this seemingly simple task provides a strong signal for feature learning and with self-supervised learning, we achieve a high segmentation accuracy that is better than or comparable to a U-net trained from scratch, especially at a small data setting. When only five annotated subjects are available, the proposed method improves the mean Dice metric from 0.811 to 0.852 for short-axis image segmentation, compared to the baseline U-net.
Journal articleHampshire A, Daws RE, Neves ID, et al., 2019,
Probing cortical and sub-cortical contributions to instruction-based learning: Regional specialisation and global network dynamics, NeuroImage, Vol: 192, Pages: 88-100, ISSN: 1053-8119
Diverse cortical networks and striatal brain regions are implicated in instruction-based learning (IBL); however, their distinct contributions remain unclear. We use a modified fMRI paradigm to test two hypotheses regarding the brain mechanisms that underlie IBL. One hypothesis proposes that anterior caudate and frontoparietal regions transiently co-activate when new rules are being bound in working memory. The other proposes that they mediate the application of the rules at different stages of the consolidation process. In accordance with the former hypothesis, we report strong activation peaks within and increased connectivity between anterior caudate and frontoparietal regions when rule-instruction slides are presented. However, similar effects occur throughout a broader set of cortical and sub-cortical regions, indicating a metabolically costly reconfiguration of the global brain state. The distinct functional roles of cingulo-opercular, frontoparietal and default-mode networks are apparent from their activation throughout, early and late in the practice phase respectively. Furthermore, there is tentative evidence of a peak in anterior caudate activity mid-way through the practice stage. These results demonstrate how performance of the same simple task involves a steadily shifting balance of brain systems as learning progresses. They also highlight the importance of distinguishing between regional specialisation and global dynamics when studying the network mechanisms that underlie cognition and learning.
Journal articleTarroni G, Oktay O, Bai W, et al., 2019,
The effectiveness of a cardiovascular magnetic resonance (CMR) scan depends on the ability of the operator to correctly tune the acquisition parameters to the subject being scanned and on the potential occurrence of imaging artefacts such as cardiac and respiratory motion. In the clinical practice, a quality control step is performed by visual assessment of the acquired images: however, this procedure is strongly operatordependent, cumbersome and sometimes incompatible with the time constraints in clinical settings and large-scale studies. We propose a fast, fully-automated, learning-based quality control pipeline for CMR images, specifically for short-axis image stacks. Our pipeline performs three important quality checks: 1) heart coverage estimation, 2) inter-slice motion detection, 3) image contrast estimation in the cardiac region. The pipeline uses a hybrid decision forest method - integrating both regression and structured classification models - to extract landmarks as well as probabilistic segmentation maps from both long- and short-axis images as a basis to perform the quality checks. The technique was tested on up to 3000 cases from the UK Biobank as well as on 100 cases from the UK Digital Heart Project, and validated against manual annotations and visual inspections performed by expert interpreters. The results show the capability of the proposed pipeline to correctly detect incomplete or corrupted scans (e.g. on UK Biobank, sensitivity and specificity respectively 88% and 99% for heart coverage estimation, 85% and 95% for motion detection), allowing their exclusion from the analysed dataset or the triggering of a new acquisition.
Journal articleCox DJ, Bai W, Price AN, et al., 2019,
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.