Search

The subject of "fairness" in artificial intelligence (AI) refers to assessing AI algorithms for potential bias based on demographic characteristics such as race and gender, and the development of algorithms to address this bias. Most applications to date have been in computer vision, although some work in healthcare has started to emerge. The use of deep learning (DL) in cardiac MR segmentation has led to impressive results in recent years, and such techniques are starting to be translated into clinical practice. However, no work has yet investigated the fairness of such models. In this work, we perform such an analysis for racial/gender groups, focusing on the problem of training data imbalance, using a nnU-Net model trained and evaluated on cine short axis cardiac MR data from the UK Biobank dataset, consisting of 5,903 subjects from 6 different racial groups. We find statistically significant differences in Dice performance between different racial groups. To reduce the racial bias, we investigated three strategies: (1) stratified batch sampling, in which batch sampling is stratified to ensure balance between racial groups; (2) fair meta-learning for segmentation, in which a DL classifier is trained to classify race and jointly optimized with the segmentation model; and (3) protected group models, in which a different segmentation model is trained for each racial group. We also compared the results to the scenario where we have a perfectly balanced database. To assess fairness we used the standard deviation (SD) and skewed error ratio (SER) of the average Dice values. Our results demonstrate that the racial bias results from the use of imbalanced training data, and that all proposed bias mitigation strategies improved fairness, with the best SD and SER resulting from the use of protected group models., Comment: MICCAI 2021 conference

Additional file 1. Additional reference ranges. Tables reporting additional normal reference ranges of mitral and tricuspid annular dimensions and tethering indices.

Purpose: To demonstrate the feasibility and performance of a fully automated deep learning framework to estimate myocardial strain from short-axis cardiac magnetic resonance tagged images. Methods and Materials: In this retrospective cross-sectional study, 4508 cases from the UK Biobank were split randomly into 3244 training and 812 validation cases, and 452 test cases. Ground truth myocardial landmarks were defined and tracked by manual initialization and correction of deformable image registration using previously validated software with five readers. The fully automatic framework consisted of 1) a convolutional neural network (CNN) for localization, and 2) a combination of a recurrent neural network (RNN) and a CNN to detect and track the myocardial landmarks through the image sequence for each slice. Radial and circumferential strain were then calculated from the motion of the landmarks and averaged on a slice basis. Results: Within the test set, myocardial end-systolic circumferential Green strain errors were -0.001 +/- 0.025, -0.001 +/- 0.021, and 0.004 +/- 0.035 in basal, mid, and apical slices respectively (mean +/- std. dev. of differences between predicted and manual strain). The framework reproduced significant reductions in circumferential strain in diabetics, hypertensives, and participants with previous heart attack. Typical processing time was ~260 frames (~13 slices) per second on an NVIDIA Tesla K40 with 12GB RAM, compared with 6-8 minutes per slice for the manual analysis. Conclusions: The fully automated RNNCNN framework for analysis of myocardial strain enabled unbiased strain evaluation in a high-throughput workflow, with similar ability to distinguish impairment due to diabetes, hypertension, and previous heart attack., Comment: accepted in Radiology Cardiothoracic Imaging

Supplemental Digital Content is available in the text., Background: Exposure to ambient air pollution is strongly associated with increased cardiovascular morbidity and mortality. Little is known about the influence of air pollutants on cardiac structure and function. We aim to investigate the relationship between chronic past exposure to traffic-related pollutants and the cardiac chamber volume, ejection fraction, and left ventricular remodeling patterns after accounting for potential confounders. Methods: Exposure to ambient air pollutants including particulate matter and nitrogen dioxide was estimated from the Land Use Regression models for the years between 2005 and 2010. Cardiac parameters were measured from cardiovascular magnetic resonance imaging studies of 3920 individuals free from pre-existing cardiovascular disease in the UK Biobank population study. The median (interquartile range) duration between the year of exposure estimate and the imaging visit was 5.2 (0.6) years. We fitted multivariable linear regression models to investigate the relationship between cardiac parameters and traffic-related pollutants after adjusting for various confounders. Results: The studied cohort was 62±7 years old, and 46% were men. In fully adjusted models, particulate matter with an aerodynamic diameter

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, e.g. image segmentation methods, are employed to derive quantitative measures or biomarkers for later analyses. Manual inspection and visual QC of each segmentation isn't feasible at large scale. However, it's important to be able to automatically detect when a segmentation method fails so as to avoid inclusion of wrong measurements into subsequent analyses which could 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 4,800 cardiac magnetic resonance scans. We then apply our method to a large cohort of 7,250 cardiac MRI 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 predicted DSC scores. As further validation we show high correlation between real and predicted scores and 95% classification accuracy on 4,800 scans for which manual segmentations were available. We mimic real-world application of the method on 7,250 cardiac MRI where we show good agreement between predicted quality metrics and manual visual QC scores. Conclusions: We show that RCA 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., Comment: 14 pages, 7 figures, Journal of Cardiovascular Magnetic Resonance

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., Comment: This work is published at MLMIR 2018: Machine Learning for Medical Image Reconstruction

Large prospective epidemiological studies acquire cardiovascular magnetic resonance (CMR) images for pre-symptomatic populations and follow these over time. To support this approach, fully automatic large-scale 3D analysis is essential. In this work, we propose a novel deep neural network using both CMR images and patient metadata to directly predict cardiac shape parameters. The proposed method uses the promising ability of statistical shape models to simplify shape complexity and variability together with the advantages of convolutional neural networks for the extraction of solid visual features. To the best of our knowledge, this is the first work that uses such an approach for 3D cardiac shape prediction. We validated our proposed CMR analytics method against a reference cohort containing 500 3D shapes of the cardiac ventricles. Our results show broadly significant agreement with the reference shapes in terms of the estimated volume of the cardiac ventricles, myocardial mass, 3D Dice, and mean and Hausdorff distance., Comment: Accepted for publication in MICCAI 2019

Background In patients with angina and nonobstructive coronary artery disease (NOCAD), confirming symptoms due to coronary microvascular dysfunction (CMD) remains challenging. Cardiac magnetic resonance (CMR) assesses myocardial perfusion with high spatial resolution and is widely used for diagnosing obstructive coronary artery disease (CAD). Objectives The goal of this study was to validate CMR for diagnosing microvascular angina in patients with NOCAD, compared with patients with obstructive CAD and correlated to the index of microcirculatory resistance (IMR) during invasive coronary angiography. Methods Fifty patients with angina (65 ± 9 years of age) and 20 age-matched healthy control subjects underwent adenosine stress CMR (1.5- and 3-T) to assess left ventricular function, inducible ischemia (myocardial perfusion reserve index [MPRI]; myocardial blood flow [MBF]), and infarction (late gadolinium enhancement). During subsequent angiography within 7 days, 28 patients had obstructive CAD (fractional flow reserve [FFR] ≤0.8) and 22 patients had NOCAD (FFR >0.8) who underwent 3-vessel IMR measurements. Results In patients with NOCAD, myocardium with IMR 0.8) (area under the curve: 0.90; specificity: 95%; sensitivity: 89%; p < 0.001). Impaired MPRI in patients with NOCAD was driven by impaired augmentation of MBF during stress, with normal resting MBF. Myocardium with FFR >0.8 and normal IMR (, Central Illustration

Aims To assess the prognostic value of myocardial pre-contrast T1 and extracellular volume (ECV) in systemic amyloid light-chain (AL) amyloidosis using cardiovascular magnetic resonance (CMR) T1 mapping. Methods and results One hundred patients underwent CMR and T1 mapping pre- and post-contrast. Myocardial ECV was calculated at contrast equilibrium (ECVi) and 15 min post-bolus (ECVb). Fifty-four healthy volunteers served as controls. Patients were followed up for a median duration of 23 months and survival analyses were performed. Mean ECVi was raised in amyloid (0.44 ± 0.12) as was ECVb (mean 0.44 ± 0.12) compared with healthy volunteers (0.25 ± 0.02), P < 0.001. Native pre-contrast T1 was raised in amyloid (mean 1080 ± 87 ms vs. 954 ± 34 ms, P < 0.001). All three correlated with pre-test probability of cardiac involvement, cardiac biomarkers, and systolic and diastolic dysfunction. During follow-up, 25 deaths occurred. An ECVi of >0.45 carried a hazard ratio (HR) for death of 3.84 [95% confidence interval (CI): 1.53–9.61], P = 0.004 and pre-contrast T1 of >1044 ms = HR 5.39 (95% CI: 1.24–23.4), P = 0.02. Extracellular volume after primed infusion and ECVb performed similarly. Isolated post-contrast T1 was non-predictive. In Cox regression models, ECVi was independently predictive of mortality (HR = 4.41, 95% CI: 1.35–14.4) after adjusting for E:E′, ejection fraction, diastolic dysfunction grade, and NT-proBNP. Conclusion Myocardial ECV (bolus or infusion technique) and pre-contrast T1 are biomarkers for cardiac AL amyloid and they predict mortality in systemic amyloidosis.