Search

Background: Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for non-invasive myocardial tissue characterisation. However, accurate segmentation of the left ventricular (LV) myocardium remains a challenge due to limited training data and lack of quality control. This study addresses these issues by leveraging generative adversarial networks (GAN)-generated virtual native enhancement (VNE) images to expand the training set and incorporating an automated quality control-driven (QCD) framework to improve segmentation reliability., Methods: A dataset comprising 4,716 LGE images (from 1,363 patients with hypertrophic cardiomyopathy and myocardial infarction) was used for development. To generate additional clinically validated data, LGE data were augmented with a GAN-based generator to produce VNE images. LV was contoured on these images manually by clinical observers. To create diverse candidate segmentations, the QCD framework involved multiple U-Nets, which were combined using statistical rank filters. The framework predicted the Dice Similarity Coefficient (DSC) for each candidate segmentation, with the highest predicted DSC indicating the most accurate and reliable result. The performance of the QCD ensemble framework was evaluated on both LGE and VNE test datasets (309 LGE/VNE images from 103 patients), assessing segmentation accuracy (DSC) and quality prediction (mean absolute error (MAE) and binary classification accuracy)., Results: The QCD framework effectively and rapidly segmented the LV myocardium (<1 s per image) on both LGE and VNE images, demonstrating robust performance on both test datasets with similar mean DSC (LGE: 0.845 ± 0.075 ; VNE: 0.845 ± 0.071 ; p = n s ). Incorporating GAN-generated VNE data into the training process consistently led to enhanced performance for both individual models and the overall framework. The quality control mechanism yielded a high performance ( MAE = 0.043 , accuracy = 0.951 ) emphasising the accuracy of the quality control-driven strategy in predicting segmentation quality in clinical settings. Overall, no statistical difference ( p = n s ) was found when comparing the LGE and VNE test sets across all experiments., Conclusions: The QCD ensemble framework, leveraging GAN-generated VNE data and an automated quality control mechanism, significantly improved the accuracy and reliability of LGE segmentation, paving the way for enhanced and accountable diagnostic imaging in routine clinical use., Competing Interests: VF, QZ, and SP have authorship rights for patent WO2021/044153 (“Enhancement of Medical Images”; granted March 11, 2021). EH, IP, VF, QZ and SP have authorship rights for patent WO/2020/161481 (“Method and Apparatus for Quality Prediction”; granted August 13, 2020). SP has patent authorship rights for US patent US20120078084A1 (“Systems and Methods for Shortened Look Locker Inversion Recovery [Sh-MOLLI] Cardiac Gated Mapping of T1”; granted March 15, 2016). DI was employed by Artificio Inc. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (© 2023 Gonzales, Ibáñez, Hann, Popescu, Burrage, Lee, Altun, Weintraub, Kwong, Kramer, Neubauer, Ferreira, Zhang and Piechnik.)

Background: Patients with a history of COVID-19 infection are reported to have cardiac abnormalities on cardiovascular magnetic resonance (CMR) during convalescence. However, it is unclear whether these abnormalities were present during the acute COVID-19 illness and how they may evolve over time., Methods: We prospectively recruited unvaccinated patients hospitalized with acute COVID-19 ( n  = 23), and compared them with matched outpatient controls without COVID-19 ( n  = 19) between May 2020 and May 2021. Only those without a past history of cardiac disease were recruited. We performed in-hospital CMR at a median of 3 days (IQR 1-7 days) after admission, and assessed cardiac function, edema and necrosis/fibrosis, using left and right ventricular ejection fraction (LVEF, RVEF), T1-mapping, T2 signal intensity ratio (T2SI), late gadolinium enhancement (LGE) and extracellular volume (ECV). Acute COVID-19 patients were invited for follow-up CMR and blood tests at 6 months., Results: The two cohorts were well matched in baseline clinical characteristics. Both had normal LVEF (62 ± 7 vs. 65 ± 6%), RVEF (60 ± 6 vs. 58 ± 6%), ECV (31 ± 3 vs. 31 ± 4%), and similar frequency of LGE abnormalities (16 vs. 14%; all p  > 0.05). However, measures of acute myocardial edema (T1 and T2SI) were significantly higher in patients with acute COVID-19 when compared to controls (T1 = 1,217 ± 41 ms vs. 1,183 ± 22 ms; p  = 0.002; T2SI = 1.48 ± 0.36 vs. 1.13 ± 0.09; p  < 0.001). All COVID-19 patients who returned for follow up ( n  = 12) at 6 months had normal biventricular function, T1 and T2SI., Conclusion: Unvaccinated patients hospitalized for acute COVID-19 demonstrated CMR imaging evidence of acute myocardial edema, which normalized at 6 months, while biventricular function and scar burden were similar when compared to controls. Acute COVID-19 appears to induce acute myocardial edema in some patients, which resolves in convalescence, without significant impact on biventricular structure and function in the acute and short-term. Further studies with larger numbers are needed to confirm these findings., Competing Interests: SP has patent authorship rights for U.S. patent 9285446 B2 [systems and methods for Shortened Look Locker Inversion Recovery (Sh-MOLLI) cardiac gated mapping of T1], granted March 15, 2016; IPs are owned and managed by Oxford University Innovations. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Shanmuganathan, Kotronias, Burrage, Ng, Banerjee, Xie, Fletcher, Manley, Borlotti, Emfietzoglou, Mentzer, Marin, Raman, Oxford Acute Myocardial Infarction (OxAMI) investigators, Tunnicliffe, Neubauer, Piechnik, Channon and Ferreira.)

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., Competing Interests: SEP provided consultancy to and is shareholder of Circle Cardiovascular Imaging, Inc., Calgary, Alberta, Canada. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Puyol-Antón, Ruijsink, Mariscal Harana, Piechnik, Neubauer, Petersen, Razavi, Chowienczyk and King.)

Background: Quantitative cardiovascular magnetic resonance (CMR) T1 mapping has shown promise for advanced tissue characterisation in routine clinical practise. However, T1 mapping is prone to motion artefacts, which affects its robustness and clinical interpretation. Current methods for motion correction on T1 mapping are model-driven with no guarantee on generalisability, limiting its widespread use. In contrast, emerging data-driven deep learning approaches have shown good performance in general image registration tasks. We propose MOCOnet, a convolutional neural network solution, for generalisable motion artefact correction in T1 maps. Methods: The network architecture employs U-Net for producing distance vector fields and utilises warping layers to apply deformation to the feature maps in a coarse-to-fine manner. Using the UK Biobank imaging dataset scanned at 1.5T, MOCOnet was trained on 1,536 mid-ventricular T1 maps (acquired using the ShMOLLI method) with motion artefacts, generated by a customised deformation procedure, and tested on a different set of 200 samples with a diverse range of motion. MOCOnet was compared to a well-validated baseline multi-modal image registration method. Motion reduction was visually assessed by 3 human experts, with motion scores ranging from 0% (strictly no motion) to 100% (very severe motion). Results: MOCOnet achieved fast image registration (<1 second per T1 map) and successfully suppressed a wide range of motion artefacts. MOCOnet significantly reduced motion scores from 37.1±21.5 to 13.3±10.5 ( p < 0.001), whereas the baseline method reduced it to 15.8±15.6 ( p < 0.001). MOCOnet was significantly better than the baseline method in suppressing motion artefacts and more consistently ( p = 0.007). Conclusion: MOCOnet demonstrated significantly better motion correction performance compared to a traditional image registration approach. Salvaging data affected by motion with robustness and in a time-efficient manner may enable better image quality and reliable images for immediate clinical interpretation., Competing Interests: SP has patent authorship rights for U.S. patent 9285446 B2 systems and methods for Shortened Look-Locker Inversion Recovery ShMOLLI cardiac gated mapping of T1, granted March 15, 2016; licensed to Siemens Medical. KW is an employee of Circle Cardiovascular Imaging since 2019. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Gonzales, Zhang, Papież, Werys, Lukaschuk, Popescu, Burrage, Shanmuganathan, Ferreira and Piechnik.)

Background: Greater red and processed meat consumption has been linked to adverse cardiovascular outcomes. However, the impact of these exposures on cardiovascular magnetic resonance (CMR) phenotypes has not been adequately studied. Objective: We describe novel associations of meat intake with cardiovascular phenotypes and investigate underlying mechanisms through consideration of a range of covariates. Design: We studied 19,408 UK Biobank participants with CMR data available. Average daily red and processed meat consumption was determined through food frequency questionnaires and expressed as a continuous variable. Oily fish was studied as a comparator, previously associated with favourable cardiac outcomes. We considered associations with conventional CMR indices (ventricular volumes, ejection fraction, stroke volume, left ventricular mass), novel CMR radiomics features (shape, first-order, texture), and arterial compliance measures (arterial stiffness index, aortic distensibility). We used multivariable linear regression to investigate relationships between meat intake and cardiovascular phenotypes, adjusting for confounders (age, sex, deprivation, educational level, smoking, alcohol intake, exercise) and potential covariates on the causal pathway (hypertension, hypercholesterolaemia, diabetes, body mass index). Results: Greater red and processed meat consumption was associated with an unhealthy pattern of biventricular remodelling, worse cardiac function, and poorer arterial compliance. In contrast, greater oily fish consumption was associated with a healthier cardiovascular phenotype and better arterial compliance. There was partial attenuation of associations between red meat and conventional CMR indices with addition of covariates potentially on the causal pathway, indicating a possible mechanistic role for these cardiometabolic morbidities. However, other associations were not altered with inclusion of these covariates, suggesting importance of alternative biological mechanisms underlying these relationships. Radiomics analysis provided deeper phenotyping, demonstrating association of the different dietary habits with distinct ventricular geometry and left ventricular myocardial texture patterns. Conclusions: Greater red and processed meat consumption is associated with impaired cardiovascular health, both in terms of markers of arterial disease and of cardiac structure and function. Cardiometabolic morbidities appeared to have a mechanistic role in the associations of red meat with ventricular phenotypes, but less so for other associations suggesting importance of alternative mechanism for these relationships., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Raisi-Estabragh, McCracken, Gkontra, Jaggi, Ardissino, Cooper, Biasiolli, Aung, Piechnik, Neubauer, Munroe, Lekadir, Harvey and Petersen.)

Cardiovascular magnetic resonance (CMR) radiomics is a novel technique for advanced cardiac image phenotyping by analyzing multiple quantifiers of shape and tissue texture. In this paper, we assess, in the largest sample published to date, the performance of CMR radiomics models for identifying changes in cardiac structure and tissue texture due to cardiovascular risk factors. We evaluated five risk factor groups from the first 5,065 UK Biobank participants: hypertension ( n = 1,394), diabetes ( n = 243), high cholesterol ( n = 779), current smoker ( n = 320), and previous smoker ( n = 1,394). Each group was randomly matched with an equal number of healthy comparators (without known cardiovascular disease or risk factors). Radiomics analysis was applied to short axis images of the left and right ventricles at end-diastole and end-systole, yielding a total of 684 features per study. Sequential forward feature selection in combination with machine learning (ML) algorithms (support vector machine, random forest, and logistic regression) were used to build radiomics signatures for each specific risk group. We evaluated the degree of separation achieved by the identified radiomics signatures using area under curve (AUC), receiver operating characteristic (ROC), and statistical testing. Logistic regression with L1-regularization was the optimal ML model. Compared to conventional imaging indices, radiomics signatures improved the discrimination of risk factor vs. healthy subgroups as assessed by AUC [diabetes: 0.80 vs. 0.70, hypertension: 0.72 vs. 0.69, high cholesterol: 0.71 vs. 0.65, current smoker: 0.68 vs. 0.65, previous smoker: 0.63 vs. 0.60]. Furthermore, we considered clinical interpretation of risk-specific radiomics signatures. For hypertensive individuals and previous smokers, the surface area to volume ratio was smaller in the risk factor vs. healthy subjects; perhaps reflecting a pattern of global concentric hypertrophy in these conditions. In the diabetes subgroup, the most discriminatory radiomics feature was the median intensity of the myocardium at end-systole, which suggests a global alteration at the myocardial tissue level. This study confirms the feasibility and potential of CMR radiomics for deeper image phenotyping of cardiovascular health and disease. We demonstrate such analysis may have utility beyond conventional CMR metrics for improved detection and understanding of the early effects of cardiovascular risk factors on cardiac structure and tissue., (Copyright © 2020 Cetin, Raisi-Estabragh, Petersen, Napel, Piechnik, Neubauer, Gonzalez Ballester, Camara and Lekadir.)

Background: Convolutional neural network (CNN) based segmentation methods provide an efficient and automated way for clinicians to assess the structure and function of the heart in cardiac MR images. While CNNs can generally perform the segmentation tasks with high accuracy when training and test images come from the same domain (e.g., same scanner or site), their performance often degrades dramatically on images from different scanners or clinical sites. Methods: We propose a simple yet effective way for improving the network generalization ability by carefully designing data normalization and augmentation strategies to accommodate common scenarios in multi-site, multi-scanner clinical imaging data sets. We demonstrate that a neural network trained on a single-site single-scanner dataset from the UK Biobank can be successfully applied to segmenting cardiac MR images across different sites and different scanners without substantial loss of accuracy. Specifically, the method was trained on a large set of 3,975 subjects from the UK Biobank. It was then directly tested on 600 different subjects from the UK Biobank for intra-domain testing and two other sets for cross-domain testing: the ACDC dataset (100 subjects, 1 site, 2 scanners) and the BSCMR-AS dataset (599 subjects, 6 sites, 9 scanners). Results: The proposed method produces promising segmentation results on the UK Biobank test set which are comparable to previously reported values in the literature, while also performing well on cross-domain test sets, achieving a mean Dice metric of 0.90 for the left ventricle, 0.81 for the myocardium, and 0.82 for the right ventricle on the ACDC dataset; and 0.89 for the left ventricle, 0.83 for the myocardium on the BSCMR-AS dataset. Conclusions: The proposed method offers a potential solution to improve CNN-based model generalizability for the cross-scanner and cross-site cardiac MR image segmentation task., (Copyright © 2020 Chen, Bai, Davies, Bhuva, Manisty, Augusto, Moon, Aung, Lee, Sanghvi, Fung, Paiva, Petersen, Lukaschuk, Piechnik, Neubauer and Rueckert.)