BackgroundCardiovascular resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocardial mass, providing information for diagnosis and monitoring of CVDs. However, for years, clinicians have been relying on manual approaches for CMR image analysis, which is time consuming and prone to subjective errors. It is a major clinical challenge to automatically derive quantitative and clinically relevant information from CMR images.MethodsDeep neural networks have shown a great potential in image pattern recognition and segmentation for a variety of tasks. Here we demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network (FCN). The network is trained and evaluated on a large-scale dataset from the UK Biobank, consisting of 4,875 subjects with 93,500 pixelwise annotated images. The performance of the method has been evaluated using a number of technical metrics, including the Dice metric, mean contour distance and Hausdorff distance, as well as clinically relevant measures, including left ventricle (LV) end-diastolic volume (LVEDV) and end-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolic volume (RVEDV) and end-systolic volume (RVESV).ResultsBy combining FCN with a large-scale annotated dataset, the proposed automated method achieves a high performance in segmenting the LV and RV on short-axis CMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR images. On a short-axis image test set of 600 subjects, it achieves an average Dice metric of 0.94 for the LV cavity, 0.88 for the LV myocardium and 0.90 for the RV cavity. The mean absolute difference between automated measurement and manual measurement is 6.1 mL for LVEDV, 5.3 mL for LVESV, 6.9 gram for LVM, 8.5 mL for RVEDV and 7.2 mL for RVESV. On long-axis image test sets, the average Dice metric is 0.93 for the LA cavity (2-chamber view), 0.95 for the LA cavity (4-chamber view) and 0.96 for the RA cavity (4-chamber view). The performance is comparable to human inter-observer variability.ConclusionsWe show that an automated method achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.Electronic supplementary materialThe online version of this article (10.1186/s12968-018-0471-x) contains supplementary material, which is available to authorized users.

BackgroundCardiovascular magnetic resonance (CMR) is the gold standard method for the assessment of cardiac structure and function. Reference ranges permit differentiation between normal and pathological states. To date, this study is the largest to provide CMR specific reference ranges for left ventricular, right ventricular, left atrial and right atrial structure and function derived from truly healthy Caucasian adults aged 45–74.MethodsFive thousand sixty-five UK Biobank participants underwent CMR using steady-state free precession imaging at 1.5 Tesla. Manual analysis was performed for all four cardiac chambers. Participants with non-Caucasian ethnicity, known cardiovascular disease and other conditions known to affect cardiac chamber size and function were excluded. Remaining participants formed the healthy reference cohort; reference ranges were calculated and were stratified by gender and age (45–54, 55–64, 65–74).ResultsAfter applying exclusion criteria, 804 (16.2%) participants were available for analysis. Left ventricular (LV) volumes were larger in males compared to females for absolute and indexed values. With advancing age, LV volumes were mostly smaller in both sexes. LV ejection fraction was significantly greater in females compared to males (mean ± standard deviation [SD] of 61 ± 5% vs 58 ± 5%) and remained static with age for both genders. In older age groups, LV mass was lower in men, but remained virtually unchanged in women. LV mass was significantly higher in males compared to females (mean ± SD of 53 ± 9 g/m2 vs 42 ± 7 g/m2). Right ventricular (RV) volumes were significantly larger in males compared to females for absolute and indexed values and were smaller with advancing age. RV ejection fraction was higher with increasing age in females only. Left atrial (LA) maximal volume and stroke volume were significantly larger in males compared to females for absolute values but not for indexed values. LA ejection fraction was similar for both sexes. Right atrial (RA) maximal volume was significantly larger in males for both absolute and indexed values, while RA ejection fraction was significantly higher in females.ConclusionsWe describe age- and sex-specific reference ranges for the left ventricle, right ventricle and atria in the largest validated normal Caucasian population.Electronic supplementary materialThe online version of this article (doi:10.1186/s12968-017-0327-9) contains supplementary material, which is available to authorized users.

BackgroundUK Biobank’s ambitious aim is to perform cardiovascular magnetic resonance (CMR) in 100,000 people previously recruited into this prospective cohort study of half a million 40-69 year-olds.Methods/designWe describe the CMR protocol applied in UK Biobank’s pilot phase, which will be extended into the main phase with three centres using the same equipment and protocols. The CMR protocol includes white blood CMR (sagittal anatomy, coronary and transverse anatomy), cine CMR (long axis cines, short axis cines of the ventricles, coronal LVOT cine), strain CMR (tagging), flow CMR (aortic valve flow) and parametric CMR (native T1 map).DiscussionThis report will serve as a reference to researchers intending to use the UK Biobank resource or to replicate the UK Biobank cardiovascular magnetic resonance protocol in different settings.

Background Left ventricular (LV) trabeculation is highly variable between individuals, is increased in some diseases (e.g. congenital heart disease or cardiomyopathies), but its significance in population representative individuals is unknown. Objectives To determine if excessive LV trabeculation in population representative subjects is associated with preceding changes in cardiac volumes and function. Methods The extent of trabeculation, expressed as the ratio of non-compacted to compacted (NC/C) myocardium was measured for technical reasons on cardiac magnetic resonance (CMR) long-axis cine images in 2742 subjects in the Multi-Ethnic Study of Atherosclerosis (mean age 68.7 years, 52.3% women, 56.4% with hypertension, 16.8% with diabetes) at the exam 5. These were considered in quintiles of trabeculation extent, with quintile 5’s NC/C 2.46 – 5.41. We determined the relationship between maximal NC/C ratio and preceding change (9.5 year between exam 1 and 5) in end-systolic volume indexed to the body surface area (ESVi). Secondary analysis assessed associations between maximal NC/C and preceding changes in end-diastolic volume indexed to the body surface area (EDVi) and ejection fraction (EF). Results Over 9.5 years, ESVi decreased by 1.3 ml/m2, EDVi decreased by 5.1 ml/m2 and EF decreased by 0.6% (p<0.0001). There were no clinically relevant differences in LV volumes and systolic function change between the quintiles of trabeculation extent, even in subjects with the excessive trabeculation. Conclusions Greater extent of and even excessive LV trabeculations measured in end-diastole in asymptomatic population representative individuals appears benign and is not associated with deterioration in left ventricular volumes or function over an almost 10 year period.

Background The trend towards large-scale studies including population imaging poses new challenges in terms of quality control (QC). This is a particular issue when automatic processing tools such as image segmentation methods are employed to derive quantitative measures or biomarkers for further analyses. Manual inspection and visual QC of each segmentation result is not feasible at large scale. However, it is important to be able to automatically detect when a segmentation method fails in order to avoid inclusion of wrong measurements into subsequent analyses which could otherwise lead to incorrect conclusions. Methods To overcome this challenge, we explore an approach for predicting segmentation quality based on Reverse Classification Accuracy, which enables us to discriminate between successful and failed segmentations on a per-cases basis. We validate this approach on a new, large-scale manually-annotated set of 4800 cardiovascular magnetic resonance (CMR) scans. We then apply our method to a large cohort of 7250 CMR on which we have performed manual QC. Results We report results used for predicting segmentation quality metrics including Dice Similarity Coefficient (DSC) and surface-distance measures. As initial validation, we present data for 400 scans demonstrating 99% accuracy for classifying low and high quality segmentations using the predicted DSC scores. As further validation we show high correlation between real and predicted scores and 95% classification accuracy on 4800 scans for which manual segmentations were available. We mimic real-world application of the method on 7250 CMR where we show good agreement between predicted quality metrics and manual visual QC scores. Conclusions We show that Reverse classification accuracy has the potential for accurate and fully automatic segmentation QC on a per-case basis in the context of large-scale population imaging as in the UK Biobank Imaging Study.

The evidence is increasing that left ventricular noncompaction cardiomyopathy as it is currently defined does not represent a failure of compaction of pre-existing trabecular myocardium found during embryonic development to form the compact component of the ventricular walls. Neither is there evidence of which we are aware to favour the notion that the entity is a return to a phenotype seen in cold-blooded animals. It is also known that when seen in adults, the presence of excessive ventricular trabeculations does not portend a poor prognosis when the ejection fraction is normal, with the risks of complications such as arrhythmia and stroke being rare in this setting. It is also the case that images of "noncompaction" as provided from children or autopsy studies are quite different from the features observed clinically in asymptomatic adults with excessive trabeculation. Our review suggests that the presence of an excessively trabeculated left ventricular wall is not in itself a clinical entity. It is equally possible that the excessive trabeculation is no more than a bystander in the presence of additional lesions such as dilated cardiomyopathy, with the additional lesions being responsible for the reduced ejection fraction bringing a given patient to clinical attention. We, therefore, argue that the term "noncompaction cardiomyopathy" is misleading, because there is neither failure of compaction nor a cardiomyopathic process in most individuals that fulfill widely used diagnostic criteria.

BackgroundDiffuse myocardial fibrosis (DMF) is important in cardiovascular disease, however until recently could only be assessed by invasive biopsy. We hypothesised that DMF measured by T1 mapping is elevated in isolated systemic hypertension.MethodsIn a study of well-controlled hypertensive patients from a specialist tertiary centre, 46 hypertensive patients (median age 56, range 21 to 78, 52 % male) and 50 healthy volunteers (median age 45, range 28 to 69, 52 % male) underwent clinical CMR at 1.5 T with T1 mapping (ShMOLLI) using the equilibrium contrast technique for extracellular volume (ECV) quantification. Patients underwent 24-hours Automated Blood Pressure Monitoring (ABPM), echocardiographic assessment of diastolic function, aortic stiffness assessment and measurement of NT-pro-BNP and collagen biomarkers.ResultsLate gadolinium enhancement (LGE) revealed significant unexpected underlying pathology in 6 out of 46 patients (13 %; myocardial infarction n = 3; hypertrophic cardiomyopathy (HCM) n = 3); these were subsequently excluded. Limited, non-ischaemic LGE patterns were seen in 11 out of the remaining 40 (28 %) patients. Hypertensives on therapy (mean 2.2 agents) had a mean ABPM of 152/88 mmHg, but only 35 % (14/40) had left ventricular hypertrophy (LVH; LV mass male > 90 g/m2; female > 78 g/m2). Native myocardial T1 was similar in hypertensives and controls (955 ± 30 ms versus 965 ± 38 ms, p = 0.16). The difference in ECV did not reach significance (0.26 ± 0.02 versus 0.27 ± 0.03, p = 0.06). In the subset with LVH, the ECV was significantly higher (0.28 ± 0.03 versus 0.26 ± 0.02, p < 0.001).ConclusionIn well-controlled hypertensive patients, conventional CMR discovered significant underlying diseases (chronic infarction, HCM) not detected by echocardiography previously or even during this study. T1 mapping revealed increased diffuse myocardial fibrosis, but the increases were small and only occurred with LVH.

AimsThe UK Biobank is a large-scale population-based study utilising cardiovascular magnetic resonance (CMR) to generate measurements of atrial and ventricular structure and function. This study aimed to quantify the association between modifiable cardiovascular risk factors and cardiac morphology and function in individuals without known cardiovascular disease.MethodsAge, sex, ethnicity (non-modifiable) and systolic blood pressure, diastolic blood pressure, smoking status, exercise, body mass index (BMI), high cholesterol, diabetes, alcohol intake (modifiable) were considered important cardiovascular risk factors. Multivariable regression models were built to ascertain the association of risk factors on left ventricular (LV), right ventricular (RV), left atrial (LA) and right atrial (RA) CMR parameters.Results4,651 participants were included in the analysis. All modifiable risk factors had significant effects on differing atrial and ventricular parameters. BMI was the modifiable risk factor most consistently associated with subclinical changes to CMR parameters, particularly in relation to higher LV mass (+8.3% per SD [4.3 kg/m2], 95% CI: 7.6 to 8.9%), LV (EDV: +4.8% per SD, 95% CI: 4.2 to 5.4%); ESV: +4.4% per SD, 95% CI: 3.5 to 5.3%), RV (EDV: +5.3% per SD, 95% CI: 4.7 to 5.9%; ESV: +5.4% per SD, 95% CI: 4.5 to 6.4%) and LA maximal (+8.6% per SD, 95% CI: 7.4 to 9.7%) volumes. Increases in SBP were associated with higher LV mass (+6.8% per SD, 95% CI: 5.9 to 7.7%), LV (EDV: +4.5% per SD, 95% CI: 3.6 to 5.4%; ESV: +2.0% per SD, 95% CI: 0.8 to 3.3%) volumes. The presence of diabetes or high cholesterol resulted in smaller volumes and lower ejection fractions.ConclusionsModifiable risk factors are associated with subclinical alterations in structure and function in all four cardiac chambers. BMI and systolic blood pressure are the most important modifiable risk factors affecting CMR parameters known to be linked to adverse outcomes.