This study sought to develop a fully automated framework for cardiac function analysis from cardiac magnetic resonance (CMR), including comprehensive quality control (QC) algorithms to detect erroneous output. Analysis of cine CMR imaging using deep learning (DL) algorithms could automate ventricular function assessment. However, variable image quality, variability in phenotypes of disease, and unavoidable weaknesses in training of DL algorithms currently prevent their use in clinical practice. The framework consists of a pre-analysis DL image QC, followed by a DL algorithm for biventricular segmentation in long-axis and short-axis views, myocardial feature-tracking (FT), and a post-analysis QC to detect erroneous results. The study validated the framework in healthy subjects and cardiac patients by comparison against manual analysis (n = 100) and evaluation of the QC steps' ability to detect erroneous results (n = 700). Next, this method was used to obtain reference values for cardiac function metrics from the UK Biobank. Automated analysis correlated highly with manual analysis for left and right ventricular volumes (all r > 0.95), strain (circumferential r = 0.89, longitudinal r > 0.89), and filling and ejection rates (all r ≥ 0.93). There was no significant bias for cardiac volumes and filling and ejection rates, except for right ventricular end-systolic volume (bias +1.80 ml; p = 0.01). The bias for FT strain was <1.3%. The sensitivity of detection of erroneous output was 95% for volume-derived parameters and 93% for FT strain. Finally, reference values were automatically derived from 2,029 CMR exams in healthy subjects. The study demonstrates a DL-based framework for automated, quality-controlled characterization of cardiac function from cine CMR, without the need for direct clinician oversight.

Good quality of medical images is a prerequisite for the success of subsequent image analysis pipelines. Quality assessment of medical images is therefore an essential activity and for large population studies such as the UK Biobank (UKBB), manual identification of artefacts such as those caused by unanticipated motion is tedious and time-consuming. Therefore, there is an urgent need for automatic image quality assessment techniques. In this paper, we propose a method to automatically detect the presence of motion-related artefacts in cardiac magnetic resonance (CMR) cine images. We compare two deep learning architectures to classify poor quality CMR images: 1) 3D spatio-temporal Convolutional Neural Networks (3D-CNN), 2) Long-term Recurrent Convolutional Network (LRCN). Though in real clinical setup motion artefacts are common, high-quality imaging of UKBB, which comprises cross-sectional population data of volunteers who do not necessarily have health problems creates a highly imbalanced classification problem. Due to the high number of good quality images compared to the relatively low number of images with motion artefacts, we propose a novel data augmentation scheme based on synthetic artefact creation in k-space. We also investigate a learning approach using a predetermined curriculum based on synthetic artefact severity. We evaluate our pipeline on a subset of the UK Biobank data set consisting of 3510 CMR images. The LRCN architecture outperformed the 3D-CNN architecture and was able to detect 2D+time short axis images with motion artefacts in less than 1ms with high recall. We compare our approach to a range of state-of-the-art quality assessment methods. The novel data augmentation and curriculum learning approaches both improved classification performance achieving overall area under the ROC curve of 0.89.

Background: Artificial intelligence (AI) techniques have been proposed for automation of cine CMR segmentation for functional quantification. However, in other applications AI models have been shown to have potential for sex and/or racial bias. The objective of this paper is to perform the first analysis of sex/racial bias in AI-based cine CMR segmentation using a large-scale database.Methods: A state-of-the-art deep learning (DL) model was used for automatic segmentation of both ventricles and the myocardium from cine short-axis CMR. The dataset consisted of end-diastole and end-systole short-axis cine CMR images of 5,903 subjects from the UK Biobank database (61.5 ± 7.1 years, 52% male, 81% white). To assess sex and racial bias, we compared Dice scores and errors in measurements of biventricular volumes and function between patients grouped by race and sex. To investigate whether segmentation bias could be explained by potential confounders, a multivariate linear regression and ANCOVA were performed.Results: Results on the overall population showed an excellent agreement between the manual and automatic segmentations. We found statistically significant differences in Dice scores between races (white ∼94% vs. minority ethnic groups 86–89%) as well as in absolute/relative errors in volumetric and functional measures, showing that the AI model was biased against minority racial groups, even after correction for possible confounders. The results of a multivariate linear regression analysis showed that no covariate could explain the Dice score bias between racial groups. However, for the Mixed and Black race groups, sex showed a weak positive association with the Dice score. The results of an ANCOVA analysis showed that race was the main factor that can explain the overall difference in Dice scores between racial groups.Conclusion: We have shown that racial bias can exist in DL-based cine CMR segmentation models when training with a database that is sex-balanced but not race-balanced such as the UK Biobank.

Background: Pathogenic and likely pathogenic variants associated with arrhythmogenic right ventricular cardiomyopathy (ARVC), dilated cardiomyopathy (DCM), and hypertrophic cardiomyopathy (HCM) are recommended to be reported as secondary findings in genome sequencing studies. This provides opportunities for early diagnosis, but also fuels uncertainty in variant carriers (G+), since disease penetrance is incomplete. We assessed the prevalence and disease expression of G+ in the general population. Methods: We identified pathogenic and likely pathogenic variants associated with ARVC, DCM and/or HCM in 200 643 UK Biobank individuals, who underwent whole exome sequencing. We calculated the prevalence of G+ and analyzed the frequency of cardiomyopathy/heart failure diagnosis. In undiagnosed individuals, we analyzed early signs of disease expression using available electrocardiography and cardiac magnetic resonance imaging data. Results: We found a prevalence of 1:578, 1:251, and 1:149 for pathogenic and likely pathogenic variants associated with ARVC, DCM and HCM respectively. Compared with controls, cardiovascular mortality was higher in DCM G+ (odds ratio 1.67 [95% CI 1.04; 2.59], P =0.030), but similar in ARVC and HCM G+ ( P ≥0.100). Cardiomyopathy or heart failure diagnosis were more frequent in DCM G+ (odds ratio 3.66 [95% CI 2.24; 5.81], P =4.9×10 ⁻⁷ ) and HCM G+ (odds ratio 3.03 [95% CI 1.98; 4.56], P =5.8×10 ⁻⁷ ), but comparable in ARVC G+ ( P =0.172). In contrast, ARVC G+ had more ventricular arrhythmias ( P =3.3×10 ⁻⁴ ). In undiagnosed individuals, left ventricular ejection fraction was reduced in DCM G+ ( P =0.009). Conclusions: In the general population, pathogenic and likely pathogenic variants associated with ARVC, DCM, or HCM are not uncommon. Although G+ have increased mortality and morbidity, disease penetrance in these carriers from the general population remains low (1.2–3.1%). Follow-up decisions in case of incidental findings should not be based solely on a variant, but on multiple factors, including family history and disease expression.

Tissue characterisation with cardiovascular magnetic resonance (CMR) parametric mapping has the potential to detect and quantify both focal and diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T1 mapping in particular has shown promise as a useful biomarker to support diagnostic, therapeutic and prognostic decision-making in ischaemic and non-ischaemic cardiomyopathies. Convolutional neural networks (CNNs) with Bayesian inference are a category of artificial neural networks which model the uncertainty of the network output. This study presents an automated framework for tissue characterisation from native shortened modified Look-Locker inversion recovery ShMOLLI T1 mapping at 1.5 T using a Probabilistic Hierarchical Segmentation (PHiSeg) network (PHCUMIS 119–127, 2019). In addition, we use the uncertainty information provided by the PHiSeg network in a novel automated quality control (QC) step to identify uncertain T1 values. The PHiSeg network and QC were validated against manual analysis on a cohort of the UK Biobank containing healthy subjects and chronic cardiomyopathy patients (N=100 for the PHiSeg network and N=700 for the QC). We used the proposed method to obtain reference T1 ranges for the left ventricular (LV) myocardium in healthy subjects as well as common clinical cardiac conditions. T1 values computed from automatic and manual segmentations were highly correlated (r=0.97). Bland-Altman analysis showed good agreement between the automated and manual measurements. The average Dice metric was 0.84 for the LV myocardium. The sensitivity of detection of erroneous outputs was 91%. Finally, T1 values were automatically derived from 11,882 CMR exams from the UK Biobank. For the healthy cohort, the mean (SD) corrected T1 values were 926.61 (45.26), 934.39 (43.25) and 927.56 (50.36) for global, interventricular septum and free-wall respectively. The proposed pipeline allows for automatic analysis of myocardial native T1 mapping and includes a QC process to detect potentially erroneous results. T1 reference values were presented for healthy subjects and common clinical cardiac conditions from the largest cohort to date using T1-mapping images.