Publications
424 results found
Domínguez F, Cuenca S, Bilińska Z, et al., 2018, Dilated cardiomyopathy due to BLC2-associated athanogene 3 (BAG3) mutations, Journal of the American College of Cardiology, Vol: 72, Pages: 2471-2481, ISSN: 0735-1097
BackgroundThe BAG3 (BLC2-associated athanogene 3) gene codes for an antiapoptotic protein located on the sarcomere Z-disc. Mutations in BAG3 are associated with dilated cardiomyopathy (DCM), but only a small number of cases have been reported to date, and the natural history of BAG3 cardiomyopathy is poorly understood.ObjectivesThis study sought to describe the phenotype and prognosis of BAG3 mutations in a large multicenter DCM cohort.MethodsThe study cohort comprised 129 individuals with a BAG3 mutation (62% males, 35.1 ± 15.0 years of age) followed at 18 European centers. Localization of BAG3 in cardiac tissue was analyzed in patients with truncating BAG3 mutations using immunohistochemistry.ResultsAt first evaluation, 57.4% of patients had DCM. After a median follow-up of 38 months (interquartile range: 7 to 95 months), 68.4% of patients had DCM and 26.1% who were initially phenotype-negative developed DCM. Disease penetrance in individuals >40 years of age was 80% at last evaluation, and there was a trend towards an earlier onset of DCM in men (age 34.6 ± 13.2 years vs. 40.7 ± 12.2 years; p = 0.053). The incidence of adverse cardiac events (death, left ventricular assist device, heart transplantation, and sustained ventricular arrhythmia) was 5.1% per year among individuals with DCM. Male sex, decreased left ventricular ejection fraction. and increased left ventricular end-diastolic diameter were associated with adverse cardiac events. Myocardial tissue from patients with a BAG3 mutation showed myofibril disarray and a relocation of BAG3 protein in the sarcomeric Z-disc.ConclusionsDCM caused by mutations in BAG3 is characterized by high penetrance in carriers >40 years of age and a high risk of progressive heart failure. Male sex, decreased left ventricular ejection fraction, and enlarged left ventricular end-diastolic diameter are associated with adverse outcomes in patients with BAG3 mutations.
Chin CW, Le T-T, Lim V, et al., 2018, Myocardial Fibrosis and Remodelling in Hypertensive Heart Disease: Defining the Transition to Decompensation and Heart Failure., Publisher: LIPPINCOTT WILLIAMS & WILKINS, ISSN: 0009-7322
Aw T-C, Huang W-T, Le T-T, et al., 2018, High-sensitivitycardiac troponinsin cardio-healthy subjects: a cardiovascular magnetic resonance imaging study, Scientific Reports, Vol: 8, ISSN: 2045-2322
The 99th percentile upper reference limits (URL) of high-sensitivity cardiac troponin (hs-cTn) in healthy subjects are essential for diagnosis and management of cardiovascular diseases. Unless screened stringently, subclinical disease affects the derived URL. In 779 healthy subjects(49% males; 17-88 years) screened by cardiovascular magnetic resonance (CMR), the gold standard for assessing cardiac volumes and myocardial mass; and estimated glomerular filtration rate (eGFR), the 99th percentile URL of hsTnT (Roche) and hs-cTnI (Abbott) were similar to the published URL. The overall 99th percentile URL of hsTnT and hsTnI were 15.2 and 21.2 ng/L, respectively; males had higher values than females (hsTnT: 16.8 versus 11.9 ng/L and hsTnI: 38.8 versus 14.4 ng/L). Correlation between hsTnT and hsTnI was modest (r = 0.45; p < 0.001). A larger proportion of healthy volunteers <60 years had detectable hsTnI compared to hsTnT (n = 534; 30.0% versus 18.3%, p < 0.001). Lower eGFR was an independent clinical determinant of hsTnT, but not hsTnI. Both hs-cTn concentrations were independently associated with myocardial mass and cardiac volumes (p < 0.01 for all), but only hsTnI was independently associated with CMR multi-directional strain measures and extent of LV trabeculations (p < 0.05 for all). Differences exist between hs-cTn assays and may influence their selection depending on cardiac conditions, patient population and local factors.
Halliday BP, Gulati A, Ali A, et al., 2018, Sex and age-based differences in the natural history and outcome of dilated cardiomyopathy, European Journal of Heart Failure, Vol: 20, Pages: 1392-1400, ISSN: 1388-9842
Aims: To evaluate the relationship between sex, age and outcome in dilated cardiomyopathy (DCM). Methods & Results: We used proportional hazard modelling to examine the association between sex, age and all-cause mortality in consecutive patients with DCM. Overall, 881 patients (290 women, median age 52 years) were followed for a median of 4.9 years. Women were more likely to present with heart failure (64.0% vs 54.5%; p=0.007) and had more severe symptoms (p<0.001) compared to men. Women had smaller left ventricular end-diastolic volume (125ml/m2 vs 135ml/m2, p<0.001), higher left ventricular ejection fraction (40.2% vs 37.9%, p=0.019) and were less likely to have mid-wall late gadolinium enhancement (23.0% vs 38.9%, p<0.0001). During follow-up 149 (16.9%) patients died, including 41 (4.7%) who died suddenly. After adjustment, all-cause mortality (HR 0.61; 95%CI 0.41:0.92; p=0.018) was lower in women, with similar trends for cardiovascular (HR 0.60; 95%CI 0.35-1.05; p=0.07), non-sudden (HR 0.63; 95%CI 0.39-1.02; p=0.06) and sudden death (HR 0.70, 95%CI 0.30:1.63; p=0.41). All-cause mortality (per 10 yrs: HR 1.36, 95%CI 1.20-1.55; p<0.00001) and non-sudden death (per 10 yrs: HR 1.51, 95%CI 1.26 – 1.82; p<0.00001) increased with age. Cumulative incidence curves confirmed favourable outcomes, particularly in women and those <60 years. Increased all-cause mortality in patients >60 years of age was driven by non-sudden death. Conclusion: Women with DCM have better survival compared to men, which may partly be due to less severe left ventricular dysfunction and a smaller scar burden. There is increased mortality driven by non-sudden death in patients >60 years of age that is less marked in women. Outcomes with contemporary treatment were favourable, with a low incidence of sudden death.
Honti F, Beaman G, Edwards M, et al., 2018, Copy number variants account for at least 2% of non-syndromic cardiomyopathies, 50th European-Society-of-Human-Genetics (ESHG) Conference, Publisher: NATURE PUBLISHING GROUP, Pages: 105-105, ISSN: 1018-4813
Widjaja AA, Schafer S, Cook S, 2018, Neutralizing Anti-IL-11 Antibodies Protect Against Hepatic Fibrosis in Non-Alcoholic Steatohepatitis, Annual Meeting of the American-Association-for-the-Study-of-Liver-Diseases (AASLD) / Liver Meeting, Publisher: WILEY, Pages: 1348A-1348A, ISSN: 0270-9139
Rossi R, Scotton C, Lorenzo M, et al., 2018, POPDC1 gene mutations screening in laminopathies: possible role as a modifier, 50th European-Society-of-Human-Genetics (ESHG) Conference, Publisher: NATURE PUBLISHING GROUP, Pages: 445-446, ISSN: 1018-4813
Whiffin N, Minikel E, Walsh R, et al., 2018, High-resolution variant filtering empowers clinical interpretation and provides insights into variant penetrance and population-specificity, 50th European-Society-of-Human-Genetics (ESHG) Conference, Publisher: NATURE PUBLISHING GROUP, Pages: 97-97, ISSN: 1018-4813
Tarroni G, Oktay O, Sinclair M, et al., 2018, A comprehensive approach for learning-based fully-automated inter-slice motion correction for short-axis cine cardiac MR image stacks, 21st International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) / 8th Eurographics Workshop on Visual Computing for Biology and Medicine (VCBM), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 268-276, ISSN: 0302-9743
In the clinical routine, short axis (SA) cine cardiac MR (CMR) image stacks are acquired during multiple subsequent breath-holds. If the patient cannot consistently hold the breath at the same position, the acquired image stack will be affected by inter-slice respiratory motion and will not correctly represent the cardiac volume, introducing potential errors in the following analyses and visualisations. We propose an approach to automatically correct inter-slice respiratory motion in SA CMR image stacks. Our approach makes use of probabilistic segmentation maps (PSMs) of the left ventricular (LV) cavity generated with decision forests. PSMs are generated for each slice of the SA stack and rigidly registered in-plane to a target PSM. If long axis (LA) images are available, PSMs are generated for them and combined to create the target PSM; if not, the target PSM is produced from the same stack using a 3D model trained from motion-free stacks. The proposed approach was tested on a dataset of SA stacks acquired from 24 healthy subjects (for which anatomical 3D cardiac images were also available as reference) and compared to two techniques which use LA intensity images and LA segmentations as targets, respectively. The results show the accuracy and robustness of the proposed approach in motion compensation.
Biffi 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.
Lim E-H, Thu-Thao L, Bryant J, et al., 2018, Importance of Sex-Specific Regression Models to Estimate Synthetic Hematocrit and Extracellular Volume Fraction, JACC-CARDIOVASCULAR IMAGING, Vol: 11, Pages: 1366-1367, ISSN: 1936-878X
- Author Web Link
- Cite
- Citations: 3
Dawes T, Cai J, Quinlan M, et al., 2018, Fractal analysis of right ventricular trabeculae in pulmonary hypertension, Radiology, Vol: 288, Pages: 386-395, ISSN: 0033-8419
Purpose: To measure right ventricular (RV) trabecular complexity by its fractal dimension (FD) in healthy subjects and patients with pulmonary hypertension (PH) and assess its relationship to hemodynamic and functional parameters, and future cardiovascular events. Materials and methods: This retrospective study used data acquired from May 2004 to October 2013 for 256 patients with newly-diagnosed PH that underwent cardiac magnetic resonance (CMR) imaging, right heart catheterization and six-minute walk distance testing with a median follow-up of 4.0 years. 256 healthy controls underwent CMR only. Biventricular FD, volumes and function were assessed on short-axis cine images. Reproducibility was assessed by intraclass correlation coefficient, correlation between variables was assessed by Pearson’s correlation test, and mortality prediction compared by univariable and multivariable Cox regression analysis. Results: RV-FD reproducibility had an intraclass correlation coefficient of 0.97 (95% confidence interval [CI]: 0.96, 0.98).RV-FD was higher in PH patients than healthy subjects (median 1.310, inter-quartile range [IQR] 1.281-1.341 vs 1.264, 1.242-1.295, P<.001) with the greatest difference near the apex. RV-FD was associated with pulmonary vascular resistance (r=0.30, P<.001). In univariable Cox regression analysis, RV-FD was a significant predictor of death (hazards ratio [HR]: 1.256, CI: 1.011, 1.560, P=.04), but in a multivariable analysis did not predict survival independently of conventional parameters of RV remodeling (HR: 1.179, CI: 0.871, 1.596, P=0.29). Conclusion: Fractal analysis of RV trabecular complexity is a highly reproducible measure of remodeling in PH associated with afterload, although the gain in survival prediction over traditional markers is not significant.
Restrepo Cordoba MA, Barton PJ, Bayes-Genis A, et al., 2018, Genetic predisposing factors in chemotherapy-induced cardiomyopathy, European-Society-of-Cardiology Congress, Publisher: OXFORD UNIV PRESS, Pages: 282-283, ISSN: 0195-668X
Ye L, Su L, Wang C, et al., 2018, Truncations of the titin Z-disc predispose to a heart failure with preserved ejection phenotype in the context of pressure overload, PLoS One, Vol: 13
Titin (TTN) Truncating variants (TTNtv) in the A-band of TTN predispose the mouse heart to systolic dysfunction when subjected to pressure-loading. However, the effects of TTNtv of the Z-disc are largely unexplored. A rat model of pressure-loaded heart is developed by trans-aortic constriction (TAC). Rats with TTNtv of the Z-disc were randomly assigned to TAC (Z-TAC) or sham-surgery (Z-Sham) and wildtype (WT) littermates served as controls (WT-TAC or WT-Sham). Left ventricular (LV) function was assessed by echocardiography. Pressure volume (PV) loops, histology and molecular profiling were performed eight months after surgery. Pressure-load by TAC increased LV mass in all cases when compared with Sham animals. Notably, systolic function was preserved in TAC animals throughout the study period, which was confirmed by terminal PV loops. Diastolic function was impaired in Z-disc TTNtv rats at baseline as compared to WT and became impaired further after TAC (dp/dtmin, mmHg/s): Z-TAC = -3435±763, WT-TAC = -6497±1299 (p<0.01). Z-TAC animals had greater cardiac fibrosis, with elevated collagen content and decreased vascular density as compared to WT-TAC animals associated with enhanced apoptosis of myocyte and non-myocyte populations. In the context of pressure overload, Z-disc TTNtv is associated with cardiac fibrosis, diastolic dysfunction, and capillary rarefaction in the absence of overt systolic dysfunction.
Ye L, D'Agostino G, Loo SJ, et al., 2018, Early regenerative capacity in the Porcine heart, Circulation, Vol: 138, Pages: 2798-2808, ISSN: 0009-7322
Background -The adult mammalian heart has limited ability to repair itself following injury. Zebrafish, newts and neonatal mice can regenerate cardiac tissue, largely by cardiac myocyte (CM) proliferation. It is unknown if hearts of young large mammals can regenerate. Methods -We examined the regenerative capacity of the pig heart in neonatal animals (ages: 2, 3 or 14 days postnatal) after myocardial infarction (MI) or sham procedure. Myocardial scar and left ventricular function were determined by cardiac magnetic resonance (CMR) imaging and echocardiography. Bromodeoxyuridine pulse-chase labeling, histology, immunohistochemistry and Western blotting were performed to study cell proliferation, sarcomere dynamics and cytokinesis and to quantify myocardial fibrosis. RNA-sequencing was also performed. Results -After MI, there was early and sustained recovery of cardiac function and wall thickness in the absence of fibrosis in 2-day old pigs. In contrast, older animals developed full-thickness myocardial scarring, thinned walls and did not recover function. Genome wide analyses of the infarct zone revealed a strong transcriptional signature of fibrosis in 14-day old animals that was absent in 2-day old pigs, which instead had enrichment for cytokinesis genes. In regenerating hearts of the younger animals, up to 10% of CMs in the border zone of the MI showed evidence of DNA replication that was associated with markers of myocyte division and sarcomere disassembly. Conclusions -Hearts of large mammals have regenerative capacity, likely driven by cardiac myocyte division, but this potential is lost immediately after birth.
Dawes TJW, Serrani M, Bai W, et al., 2018, Myocardial trabeculae improve left ventricular function: a combined UK Biobank and computational analysis, GAT Annual Scientific Meeting 2018, Publisher: Association of Anaesthetists of Great Britain and Ireland
Ware JS, Amor-Salamanca A, Tayal U, et al., 2018, A genetic etiology for alcohol-induced cardiac toxicity, Journal of the American College of Cardiology, Vol: 71, Pages: 2293-2302, ISSN: 0735-1097
Background: Alcoholic cardiomyopathy (ACM) is defined by a dilated and impaired left ventricle due to chronic excess alcohol consumption. It is largely unknown what factors determine cardiac toxicity on exposure to alcohol.Objectives: We sought to evaluate the role of variation in cardiomyopathy-associated genes in the pathophysiology of ACM, and to examine the effects of alcohol intake and genotype on DCM severity.Methods: We characterized 141 ACM cases, 716 dilated cardiomyopathy (DCM) cases and 445 healthy volunteers. We compared the prevalence of rare, protein-altering variants in 9 genes associated with inherited DCM. We evaluated the effect of genotype and alcohol-consumption on phenotype in DCM.Results: Variants in well-characterized DCM-causing genes were more prevalent in patients with ACM than controls (13.5% vs 2.9%; P=1.2e-05), but similar between patients with ACM and DCM (19.4%; P=0.12) and with a predominant burden of Titin-truncating variants (TTNtv, 9.9%). Separately, we identified an interaction between TTN genotype and excess alcohol consumption in a cohort of DCM patients not meeting ACM criteria. On multivariate analysis, DCM patients with a TTNtv who consumed excess alcohol had an 8.7% absolute reduction in ejection fraction (95% CI -2.3 to -15.1, P<0.007) compared with those without TTNtv and excess alcohol consumption. The presence of TTNtv did not predict phenotype, outcome or functional recovery on treatment in ACM patients. Conclusions: TTNtv represent a prevalent genetic predisposition for ACM, and are also associated with a worse LVEF in DCM patients who consume alcohol above recommended levels. Familial evaluation and genetic testing should be considered in patients presenting with ACM.
Lahrouchi N, Raju H, Lodder E, et al., 2018, Yield and clinical utility of the ‘molecular autopsy’ in cases of the Sudden Arrhythmic Death Syndrome (SADS) and their families, Journal of the American College of Cardiology, ISSN: 1558-3597
Post-mortem genetic testing (‘molecular autopsy’) of sudden arrhythmicdeath syndrome (SADS) cases can establish a clear molecular diagnosis in a substantial minority.This complements family evaluation. Classification of pathogenicity of genetic variants must,however, be stringent in order to avoid the over calling of variants of unknown significance ascausative. Children and young adults presenting with seizures and syncope, especially whenassociated with stress or exercise, require thorough cardiac evaluation in order to not misscatecholaminergic polymorphic ventricular tachycardia. Molecular autopsy should not howeverbe restricted to the young as cases over 35 years old also carry diagnostic variants.
de Marvao A, Biffi C, Walsh R, et al., 2018, Defining The Effects Of Genetic Variation Using Machine Learning Analysis Of CMRs: A Study In Hypertrophic Cardiomyopathy And In A Healthy Population, Joint Meeting of the British-Society-of-Cardiovascular-Imaging/British-Society-of-Cardiovascular-CT, British-Society-of-Cardiovascular-Magnetic-Resonance and British-Nuclear-Cardiac-Society on British Cardiovascular Imaging, Publisher: BMJ PUBLISHING GROUP, Pages: A7-A8, ISSN: 1355-6037
Halliday BP, Baksi AJ, Izgi C, et al., 2018, Improving risk stratification for sudden cardiac death in dilated cardiomyopathy using late gadolinium enhancement cardiovascular magnetic resonance, Heart Failure 2018, Publisher: WILEY, Pages: 184-184, ISSN: 1388-9842
Halliday BP, Wassall R, Khalique Z, et al., 2018, Comprehensive phenoptyping of patients with dilated cardiomyopathy and recovered ejection fraction, Heart Failure 2018, Publisher: WILEY, Pages: 185-185, ISSN: 1388-9842
Ostrowski PJ, de Marvao A, Quinlan M, et al., 2018, Fractal dimension as an index of left ventricular trabeculation: normal values in healthy subjects, and association with age, Quality of Care and Outcomes Research Scientific Sessions, Publisher: Lippincott, Williams & Wilkins, Pages: 1-8, ISSN: 0009-7322
Background: Evaluation of left ventricular non-compaction (LVNC) is an increasingly common indication for cardiac magnetic resonance imaging (MRI). Fractal dimension (FD) is a unitless measure of geometrical complexity which can be used to quantify LV trabeculation. FD is increased in LVNC, but there have been few studies on FD in normal subjects. The aim of the study was to establish reference ranges for FD in a healthy population, and identify covariates which are associated with FD.Methods: MRI was performed in 1,913 volunteers without hypertension, diabetes, or heart disease (1055 female, 858 male; median age 40, range 19-82). FD was derived from LV short-axis images, using a custom MATLAB box-counting algorithm. The maximal FD in the apical half of the LV was used for all analyses, as previously described.Results: Normal ranges (2.5-97.5th percentile) for female and male subjects were 1.154 - 1.367 and 1.179 - 1.392, respectively. FD was significantly correlated with age, gender, ethnicity, body surface area (BSA), activity score, and systolic blood pressure. In multivariable analysis, FD was independently correlated with increased age (β 0.11, p<0.001), male gender (β 0.09, p<0.001), African/Afro-Caribbean ethnicity (β 0.18, p<0.001), increased BSA (β 0.27, p<0.001), and increased activity score (β 0.07, p=0.002). Since ethnicity was found to significantly affect FD, normal ranges were calculated for each subgroup (see table).Conclusions: This is the largest study on FD in healthy subjects, and the first to present gender- and race-specific normal ranges. The association between FD and age suggests that LV trabeculation is a dynamic phenotype which may change with age.
Halliday B, Gulati A, Ali A, et al., 2018, SEX DIFFERENCES IN THE NATURAL HISTORY AND OUTCOME OF DILATED CARDIOMYOPATHY, 67th Annual Scientific Session and Expo of the American-College-of-Cardiology (ACC), Publisher: ELSEVIER SCIENCE INC, Pages: 704-704, ISSN: 0735-1097
Lota A, Tsao A, Al-Balah A, et al., 2018, PROGNOSTIC SIGNIFICANCE OF NON-ISCHAEMIC MYOCARDIAL FIBROSIS IN PATIENTS WITH NORMAL LV SIZE AND FUNCTION: A LARGE CMR REGISTRY STUDY, 67th Annual Scientific Session and Expo of the American-College-of-Cardiology (ACC), Publisher: ELSEVIER SCIENCE INC, Pages: 436-436, ISSN: 0735-1097
Halliday B, Baksi A, Gulati A, et al., 2018, DEFINING THE RELATIONSHIP BETWEEN THE EXTENT OF MID-WALL LATE GADOLINIUM ENHANCEMENT AND ADVERSE HEART FAILURE EVENTS IN PATIENTS WITH DILATED CARDIOMYOPATHY, 67th Annual Scientific Session and Expo of the American-College-of-Cardiology (ACC), Publisher: ELSEVIER SCIENCE INC, Pages: 1473-1473, ISSN: 0735-1097
Lota A, Fazal S, Wassall R, et al., 2018, NATIONAL TRENDS IN THE EPIDEMIOLOGY OF HOSPITAL ADMISSIONS FOR ACUTE MYOCARDITIS: INSIGHTS FROM THE UK NATIONAL HEALTH SERVICE, 67th Annual Scientific Session and Expo of the American-College-of-Cardiology (ACC), Publisher: ELSEVIER SCIENCE INC, Pages: 875-875, ISSN: 0735-1097
Lim WK, Davila S, Teo JX, et al., 2018, Beyond fitness tracking: The use of consumer-grade wearable data from normal volunteers in cardiovascular and lipidomics research, PLoS Biology, Vol: 16, Pages: 1-18, ISSN: 1544-9173
The use of consumer-grade wearables for purposes beyond fitness tracking has not been comprehensively explored. We generated and analyzed multidimensional data from 233 normal volunteers, integrating wearable data, lifestyle questionnaires, cardiac imaging, sphingolipid profiling, and multiple clinical-grade cardiovascular and metabolic disease markers. We show that subjects can be stratified into distinct clusters based on daily activity patterns and that these clusters are marked by distinct demographic and behavioral patterns. While resting heart rates (RHRs) performed better than step counts in being associated with cardiovascular and metabolic disease markers, step counts identified relationships between physical activity and cardiac remodeling, suggesting that wearable data may play a role in reducing overdiagnosis of cardiac hypertrophy or dilatation in active individuals. Wearable-derived activity levels can be used to identify known and novel activity-modulated sphingolipids that are in turn associated with insulin sensitivity. Our findings demonstrate the potential for wearables in biomedical research and personalized health.
Oktay O, Ferrante E, Kamnitsas K, et al., 2018, Anatomically Constrained Neural Networks (ACNN): application to cardiac image enhancement and segmentation, IEEE Transactions on Medical Imaging, Vol: 37, Pages: 384-395, ISSN: 0278-0062
Incorporation of prior knowledge about organ shape and location is key to improve performance of image analysis approaches. In particular, priors can be useful in cases where images are corrupted and contain artefacts due to limitations in image acquisition. The highly constrained nature of anatomical objects can be well captured with learning based techniques. However, in most recent and promising techniques such as CNN based segmentation it is not obvious how to incorporate such prior knowledge. State-of-the-art methods operate as pixel-wise classifiers where the training objectives do not incorporate the structure and inter-dependencies of the output. To overcome this limitation, we propose a generic training strategy that incorporates anatomical prior knowledge into CNNs through a new regularisation model, which is trained end-to-end. The new framework encourages models to follow the global anatomical properties of the underlying anatomy (e.g. shape, label structure) via learnt non-linear representations of the shape. We show that the proposed approach can be easily adapted to different analysis tasks (e.g. image enhancement, segmentation) and improve the prediction accuracy of the state-of-the-art models. The applicability of our approach is shown on multi-modal cardiac datasets and public benchmarks. Additionally, we demonstrate how the learnt deep models of 3D shapes can be interpreted and used as biomarkers for classification of cardiac pathologies.
Zhang S, Le TT, Kabus S, et al., 2018, Cardiac magnetic resonance T1 and extracellular volume mapping with motion correction and co-registration based on fast elastic image registration, Magnetic Resonance Materials in Physics, Biology and Medicine, Vol: 31, Pages: 115-129, ISSN: 0968-5243
OBJECTIVE: Our aim was to investigate the technical feasibility of a novel motion compensation method for cardiac magntic resonance (MR) T1 and extracellular volume fraction (ECV) mapping. MATERIALS AND METHODS: Native and post-contrast T1 maps were obtained using modified look-locker inversion recovery (MOLLI) pulse sequences with acquisition scheme defined in seconds. A nonrigid, nonparametric, fast elastic registration method was applied to generate motion-corrected T1 maps and subsequently ECV maps. Qualitative rating was performed based on T1 fitting-error maps and overlay images. Local deformation vector fields were produced for quantitative assessment. Intra- and inter-observer reproducibility were compared with and without motion compensation. RESULTS: Eighty-two T1 and 39 ECV maps were obtained in 21 patients with diverse myocardial diseases. Approximately 60% demonstrated clear quality improvement after motion correction for T1 mapping, particularly for the poor-rating cases (23% before vs 2% after). Approximately 67% showed further improvement with co-registration in ECV mapping. Although T1 and ECV values were not clinically significantly different before and after motion compensation, there was improved intra- and inter-observer reproducibility after motion compensation. CONCLUSIONS: Automated motion correction and co-registration improved the qualitative assessment and reproducibility of cardiac MR T1 and ECV measurements, allowing for more reliable ECV mapping.
Whiffin N, walsh R, Govind R, et al., 2018, CardioClassifier: disease- and gene-specific computational decision support for clinical genome interpretation, Genetics in Medicine, Vol: 20, Pages: 1246-1254, ISSN: 1098-3600
PurposeInternationally adopted variant interpretation guidelines from the American College of Medical Genetics and Genomics (ACMG) are generic and require disease-specific refinement. Here we developed CardioClassifier (http://www.cardioclassifier.org), a semiautomated decision-support tool for inherited cardiac conditions (ICCs).MethodsCardioClassifier integrates data retrieved from multiple sources with user-input case-specific information, through an interactive interface, to support variant interpretation. Combining disease- and gene-specific knowledge with variant observations in large cohorts of cases and controls, we refined 14 computational ACMG criteria and created three ICC-specific rules.ResultsWe benchmarked CardioClassifier on 57 expertly curated variants and show full retrieval of all computational data, concordantly activating 87.3% of rules. A generic annotation tool identified fewer than half as many clinically actionable variants (64/219 vs. 156/219, Fisher’s P = 1.1 × 10−18), with important false positives, illustrating the critical importance of disease and gene-specific annotations. CardioClassifier identified putatively disease-causing variants in 33.7% of 327 cardiomyopathy cases, comparable with leading ICC laboratories. Through addition of manually curated data, variants found in over 40% of cardiomyopathy cases are fully annotated, without requiring additional user-input data.ConclusionCardioClassifier is an ICC-specific decision-support tool that integrates expertly curated computational annotations with case-specific data to generate fast, reproducible, and interactive variant pathogenicity reports, according to best practice guidelines.
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.