- Showing results for:
- Reset all filters
Conference paperQin C, Bai W, Schlemper J, et al., 2018,
© 2018, Springer Nature Switzerland AG. Accelerating the acquisition of magnetic resonance imaging (MRI) is a challenging problem, and many works have been proposed to reconstruct images from undersampled k-space data. However, if the main purpose is to extract certain quantitative measures from the images, perfect reconstructions may not always be necessary as long as the images enable the means of extracting the clinically relevant measures. In this paper, we work on jointly predicting cardiac motion estimation and segmentation directly from undersampled data, which are two important steps in quantitatively assessing cardiac function and diagnosing cardiovascular diseases. In particular, a unified model consisting of both motion estimation branch and segmentation branch is learned by optimising the two tasks simultaneously. Additional corresponding fully-sampled images are incorporated into the network as a parallel sub-network to enhance and guide the learning during the training process. Experimental results using cardiac MR images from 220 subjects show that the proposed model is robust to undersampled data and is capable of predicting results that are close to that from fully-sampled ones, while bypassing the usual image reconstruction stage.
Conference paperBiffi C, Oktay O, Tarroni G, et al., 2018,
Learning interpretable anatomical features through deep generative models: Application to cardiac remodeling, International Conference On Medical Image Computing & Computer Assisted Intervention, Publisher: Springer, Pages: 464-471, ISSN: 0302-9743
Alterations in the geometry and function of the heart define well-established causes of cardiovascular disease. However, current approaches to the diagnosis of cardiovascular diseases often rely on subjective human assessment as well as manual analysis of medical images. Both factors limit the sensitivity in quantifying complex structural and functional phenotypes. Deep learning approaches have recently achieved success for tasks such as classification or segmentation of medical images, but lack interpretability in the feature extraction and decision processes, limiting their value in clinical diagnosis. In this work, we propose a 3D convolutional generative model for automatic classification of images from patients with cardiac diseases associated with structural remodeling. The model leverages interpretable task-specific anatomic patterns learned from 3D segmentations. It further allows to visualise and quantify the learned pathology-specific remodeling patterns in the original input space of the images. This approach yields high accuracy in the categorization of healthy and hypertrophic cardiomyopathy subjects when tested on unseen MR images from our own multi-centre dataset (100%) as well on the ACDC MICCAI 2017 dataset (90%). We believe that the proposed deep learning approach is a promising step towards the development of interpretable classifiers for the medical imaging domain, which may help clinicians to improve diagnostic accuracy and enhance patient risk-stratification.
Conference paperQin C, Bai W, Schlemper J, et al., 2018,
Cardiac motion estimation and segmentation play important roles in quantitatively assessing cardiac function and diagnosing cardiovascular diseases. In this paper, we propose a novel deep learning method for joint estimation of motion and segmentation from cardiac MR image sequences. The proposed network consists of two branches: a cardiac motion estimation branch which is built on a novel unsupervised Siamese style recurrent spatial transformer network, and a cardiac segmentation branch that is based on a fully convolutional network. In particular, a joint multi-scale feature encoder is learned by optimizing the segmentation branch and the motion estimation branch simultaneously. This enables the weakly-supervised segmentation by taking advantage of features that are unsupervisedly learned in the motion estimation branch from a large amount of unannotated data. Experimental results using cardiac MlRI images from 220 subjects show that the joint learning of both tasks is complementary and the proposed models outperform the competing methods significantly in terms of accuracy and speed.
Conference paperSchlemper J, Oktay O, Bai W, et al., 2018,
© Springer Nature Switzerland AG 2018. Reconstructing magnetic resonance imaging (MRI) from undersampled k-space enables the accelerated acquisition of MRI but is a challenging problem. However, in many diagnostic scenarios, perfect reconstructions are not necessary as long as the images allow clinical practitioners to extract clinically relevant parameters. In this work, we present a novel deep learning framework for reconstructing such clinical parameters directly from undersampled data, expanding on the idea of application-driven MRI. We propose two deep architectures, an end-to-end synthesis network and a latent feature interpolation network, to predict cardiac segmentation maps from extremely undersampled dynamic MRI data, bypassing the usual image reconstruction stage altogether. We perform a large-scale simulation study using UK Biobank data containing nearly 1000 test subjects and show that with the proposed approaches, an accurate estimate of clinical parameters such as ejection fraction can be obtained from fewer than 10 k-space lines per time-frame.
Journal articleBai W, Sinclair M, Tarroni G, et al., 2018,
Automated cardiovascular magnetic resonance image analysis with fully convolutional networks
Cardiovascular magnetic resonance (CMR) imaging is a standard imagingmodality for assessing cardiovascular diseases (CVDs), the leading cause ofdeath globally. CMR enables accurate quantification of the cardiac chambervolume, ejection fraction and myocardial mass, providing information fordiagnosis and monitoring of CVDs. However, for years, clinicians have beenrelying on manual approaches for CMR image analysis, which is time consumingand prone to subjective errors. It is a major clinical challenge toautomatically derive quantitative and clinically relevant information from CMRimages. Deep neural networks have shown a great potential in image patternrecognition and segmentation for a variety of tasks. Here we demonstrate anautomated analysis method for CMR images, which is based on a fullyconvolutional network (FCN). The network is trained and evaluated on alarge-scale dataset from the UK Biobank, consisting of 4,875 subjects with93,500 pixelwise annotated images. The performance of the method has beenevaluated using a number of technical metrics, including the Dice metric, meancontour distance and Hausdorff distance, as well as clinically relevantmeasures, including left ventricle (LV) end-diastolic volume (LVEDV) andend-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolicvolume (RVEDV) and end-systolic volume (RVESV). By combining FCN with alarge-scale annotated dataset, the proposed automated method achieves a highperformance on par with human experts in segmenting the LV and RV on short-axisCMR images and the left atrium (LA) and right atrium (RA) on long-axis CMRimages.
Conference paperRobinson R, Oktay O, Bai W, et al., 2018,
Recent advances in deep learning based image segmentationmethods have enabled real-time performance with human-level accuracy.However, occasionally even the best method fails due to low image qual-ity, artifacts or unexpected behaviour of black box algorithms. Beingable to predict segmentation quality in the absence of ground truth is ofparamount importance in clinical practice, but also in large-scale studiesto avoid the inclusion of invalid data in subsequent analysis.In this work, we propose two approaches of real-time automated qualitycontrol for cardiovascular MR segmentations using deep learning. First,we train a neural network on 12,880 samples to predict Dice SimilarityCoefficients (DSC) on a per-case basis. We report a mean average error(MAE) of 0.03 on 1,610 test samples and 97% binary classification accu-racy for separating low and high quality segmentations. Secondly, in thescenario where no manually annotated data is available, we train a net-work to predict DSC scores from estimated quality obtained via a reversetesting strategy. We report an MAE = 0.14 and 91% binary classifica-tion accuracy for this case. Predictions are obtained in real-time which,when combined with real-time segmentation methods, enables instantfeedback on whether an acquired scan is analysable while the patient isstill in the scanner. This further enables new applications of optimisingimage acquisition towards best possible analysis results.
Conference paperDuan J, Schlemper J, Bai W, et al., 2018,
Journal articleTimmermann C, Timmermann Slater C, Roseman L, et al., 2018,
Near-death experiences (NDEs) are complex subjective experiences, which have been previously associated with the psychedelic experience and more specifically with the experience induced by the potent serotonergic, N,N-Dimethyltryptamine (DMT). Potential similarities between both subjective states have been noted previously, including the subjective feeling of transcending one’s body and entering an alternative realm, perceiving and communicating with sentient ‘entities’ and themes related to death and dying. In this within-subjects placebo-controled study we aimed to test the similarities between the DMT state and NDEs, by administering DMT and placebo to 13 healthy participants, who then completed a validated and widely used measure of NDEs. Results revealed significant increases in phenomenological features associated with the NDE, following DMT administration compared to placebo. Also, we found significant relationships between the NDE scores and DMT-induced ego-dissolution and mystical-type experiences, as well as a significant association between NDE scores and baseline trait ‘absorption’ and delusional ideation measured at baseline. Furthermore, we found a significant overlap in nearly all of the NDE phenomenological features when comparing DMT-induced NDEs with a matched group of ‘actual’ NDE experiencers. These results reveal a striking similarity between these states that warrants further investigation.
Journal articleUnderwood J, Cole JH, Leech R, et al., 2018,
Multivariate pattern analysis of volumetric neuroimaging data and its relationship with cognitive function in treated HIV-disease, Journal of Acquired Immune Deficiency Syndromes, Vol: 78, Pages: 429-436, ISSN: 1525-4135
BACKGROUND: Accurate prediction of longitudinal changes in cognitive function would potentially allow targeted intervention in those at greatest risk of cognitive decline. We sought to build a multivariate model using volumetric neuroimaging data alone to accurately predict cognitive function. METHODS: Volumetric T1-weighted neuroimaging data from virally suppressed HIV-positive individuals from the CHARTER cohort (n=139) were segmented into grey and white matter and spatially normalised before were entering into machine learning models. Prediction of cognitive function at baseline and longitudinally was determined using leave-one-out cross validation. Additionally, a multivariate model of brain ageing was used to measure the deviation of apparent brain age from chronological age and assess its relationship with cognitive function. RESULTS: Cognitive impairment, defined using the global deficit score, was present in 37.4%. However, it was generally mild and occurred more commonly in those with confounding comorbidities (p<0.001). Although multivariate prediction of cognitive impairment as a dichotomous variable at baseline was poor (AUC 0.59), prediction of the global T-score was better than a comparable linear model (adjusted R=0.08, p<0.01 vs. adjusted R=0.01, p=0.14). Accurate prediction of longitudinal changes in cognitive function was not possible (p=0.82).Brain-predicted age exceeded chronological age by mean (95% confidence interval) 1.17 (-0.14-2.53) years, but was greatest in those with confounding comorbidities (5.87 [1.74-9.99] years) and prior AIDS (3.03 [0.00-6.06] years). CONCLUSION: Accurate prediction of cognitive impairment using multivariate models using only T1-weighted data was not achievable, which may reflect the small sample size, heterogeneity of the data or that impairment was usually mild.
Journal articleDeb S, Leeson V, Aimola L, et al., 2018,
Aggression following traumatic brain injury: effectiveness of Risperidone (AFTER): study protocol for a feasibility randomised controlled trial, Trials, Vol: 19, ISSN: 1745-6215
BackgroundTraumatic brain injury (TBI) is a major public health concern and many people develop long-lasting physical and neuropsychiatric consequences following a TBI. Despite the emphasis on physical rehabilitation, it is the emotional and behavioural consequences that have greater impact on people with TBI and their families. One such problem behaviour is aggression which can be directed towards others, towards property or towards the self. Aggression is reported to be common after TBI (37–71%) and causes major stress for patients and their families. Both drug and non-drug interventions are used to manage this challenging behaviour, but the evidence-base for these interventions is poor and no drugs are currently licensed for the treatment of aggression following TBI. The most commonly used drugs for this purpose are antipsychotics, particularly second-generation drugs such as risperidone. Despite this widespread use, randomised controlled trials (RCTs) of antipsychotic drugs, including risperidone, have not been conducted. We have, therefore, set out to test the feasibility of conducting an RCT of this drug for people who have aggressive behaviour following TBI.Methods/designWe will examine the feasibility of conducting a placebo-controlled, double-blind RCT of risperidone for the management of aggression in adults with TBI and also assess participants’ views about their experience of taking part in the study.We will randomise 50 TBI patients from secondary care services in four centres in London and Kent to up to 4 mg of risperidone orally or an inert placebo and follow them up 12 weeks later. Participants will be randomised to active or control treatment in a 1:1 ratio via an external and remote web-based randomisation service. Participants will be assessed at baseline and 12-week follow-up using a battery of assessment scales to measure changes in aggressive behaviour (MOAS, IRQ) as well as global functioning (GOS-E, CGI), quality of life (EQ-5D-5L
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.