Learning a dynamic four-chamber shape model of the human heart for 95,695 UK Biobank participants

Abstract

The human heart is a sophisticated system composed of four cardiac chambers with distinct shapes, which function in a coordinated manner. Existing shape models of the heart mainly focus on the ventricular chambers and they are derived from relatively small datasets. Here, we present a spatio-temporal (3D+t) statistical shape model of all four cardiac chambers, learnt from a large population of nearly 100,000 participants from the UK Biobank. A deep learning-based pipeline is developed to reconstruct 3D+t four-chamber meshes from the cardiac magnetic resonance images of the UK Biobank imaging population. Based on the reconstructed meshes, a 3D+t statistical shape model is learnt to characterise the shape variations and motion patterns of the four cardiac chambers. We reveal the associations of the four-chamber shape model with demographics, anthropometrics, cardiovascular risk factors, and cardiac diseases. Compared to conventional image-derived phenotypes, we validate that the four-chamber shape-derived phenotypes significantly enhance the performance in downstream tasks, including cardiovascular disease classification and heart age prediction. Furthermore, we demonstrate the effectiveness of shape-derived phenotypes in novel applications such as heart shape retrieval and heart re-identification from longitudinal data. To facilitate future research, we will release the learning-based mesh reconstruction pipeline, the four-chamber cardiac shape model, and return all derived four-chamber meshes to the UK Biobank.

Figures (6)

• Figure 1: The deep learning-based pipeline for 3D+t cardiac four-chamber mesh reconstruction.a, The processing pipeline consists of three components: motion correction for multi-view CMR images and segmentations, label completion from 2D+t multi-view sparse segmentations to 3D+t dense segmentations of the four chambers via a label completion U-Net (LC-U-Net), and finally 3D+t four-chamber mesh reconstruction with HeartFFDNet. b, The architecture of HeartFFDNet. HeartFFDNet learns multi-scale and multi-frame free-form deformations (FFDs) from input 3D+t segmentations, warping a template mesh into four-chamber meshes across all time frames of a cardiac cycle. c, Qualitative visualisation of reconstructed 3D+t cardiac four-chamber meshes overlaid on multi-view CMR images. SAX: short-axis view; 4CH: long-axis four-chamber view; 2CH: long-axis two-chamber view.
• Figure 2: Performance of the 3D+t cardiac four-chamber mesh reconstruction pipeline.a, Performance of motion correction measured by segmentation overlap (Dice) at the intersections of multi-view CMR segmentations and intensity consistency (Pearson's $r$) at the intersections of multi-view CMR images. b, Performance (Dice and ASSD) of 3D cardiac four-chamber label completion. c, Geometric errors (ASSD and HD90) of 3D+t four-chamber meshes of the proposed HeartFFDNet compared to DeepMesh and HybridVNet. d, Temporal consistency error and cycle consistency error of 3D+t four-chamber meshes reconstructed by HeartFFDNet compared to baseline methods. e, Geometric errors (ASSD and HD90) of the 3D+t meshes reconstructed by HeartFFDNet averaged across four cardiac chambers, evaluated on randomly selected test samples and participants with cardiovascular diseases.
• Figure 3: The 3D+t statistical shape model of the four-chamber heart.a, The mean shapes (anterior and posterior view) of 3D+t four-chamber hearts derived from HeartSSM. b, The shape variations captured by the first four principle components (PC) of HeartSSM, with $\pm2$ standard deviation (SD) from the mean shape. The colour maps indicate the signed distances to the mean shape along normal directions. Red colour indicates inflation compared to the mean shape, while blue colour indicates contraction. Only end-diastolic (ED) and end-systolic (ES) frames are visualised. c, The mean (line) and standard deviation (shaded area) of cardiac four-chamber volumes, displacements, and left ventricle wall thickness (mean and max) calculated from the HeartSSM fitted four-chamber meshes, displayed across all time frames and averaged over 95,695 UK Biobank participants. d, Performance of the HeartSSM. From left to right: the compactness of HeartSSM; the generalisation ability of HeartSSM on unseen cardiac shapes; performance of HeartSSM on 2D+t sparse contour fitting; performance of HeartSSM on sequence completion with partially observed frames. The shaded areas indicate $\pm1$ standard deviation.
• Figure 4: Correlation analysis of cardiac four-chamber shape model.a, Correlations of PCs with four-chamber phenotypes, demographics, anthropometrics, and cardiovascular risk factors. Only significant correlations are visualised ($p<0.05$). b, Mean cardiac four-chamber shapes and shape variations averaged across all time frames for different sex and age groups. The colour maps depict the signed distances along surface normals to the mean cardiac shape of all participants. Red colour indicates inflation compared to the mean shape, while blue colour indicates contraction. c, Correlations of vertex-wise shape variations with sex, age, BMI, hypertension, atrial fibrillation and flutter, and heart failure. The colour maps visualise significant Pearson correlation coefficients after Bonferroni correction ($p<0.05/n$, $n=27,034$ denoting the number of all vertices).
• Figure 5: Performance for cardiovascular disease classification and chronological age prediction.a, Binary classification performance for six cardiac diseases using different features, including image-derived phenotypes, shape-derived phenotypes, and HeartSSM shape descriptor, with or without confounders (sex, age, weight, height, and BMI). The ROC AUC scores for disease classification using logistic regression and XGBoost models are reported. The symbol * indicates a significant difference (two-sided DeLong test, $p<0.05$). b, Chronological age prediction performance using different features, including image-derived phenotypes, shape-derived phenotypes, 3D four-chamber (4CH) HeartSSM shape descriptor, 3D+t bi-ventricular (2CH+t) HeartSSM shape descriptor, and 3D+t four-chamber (4CH+t) HeartSSM shape descriptor. The mean absolute error, Pearson's $r$, and coefficient of determination $R^2$ for age prediction using CatBoost model are reported. The symbol * indicates statistically significant difference (paired $t$-test, $p<0.05$).