Genotype-Phenotype Taxonomy of Hypertrophic Cardiomyopathy.

BACKGROUND: Hypertrophic cardiomyopathy (HCM) is an important cause of sudden cardiac death associated with heterogeneous phenotypes, but there is no systematic framework for classifying morphology or assessing associated risks. Here, we quantitatively survey genotype-phenotype associations in HCM to derive a data-driven taxonomy of disease expression. METHODS: We enrolled 436 patients with HCM (median age, 60 years; 28.8% women) with clinical, genetic, and imaging data. An independent cohort of 60 patients with HCM from Singapore (median age, 59 years; 11% women) and a reference population from the UK Biobank (n=16 691; mean age, 55 years; 52.5% women) were also recruited. We used machine learning to analyze the 3-dimensional structure of the left ventricle from cardiac magnetic resonance imaging and build a tree-based classification of HCM phenotypes. Genotype and mortality risk distributions were projected on the tree. RESULTS: Carriers of pathogenic or likely pathogenic variants for HCM had lower left ventricular mass, but greater basal septal hypertrophy, with reduced life span (mean follow-up, 9.9 years) compared with genotype negative individuals (hazard ratio, 2.66 [95% CI, 1.42-4.96]; P<0.002). Four main phenotypic branches were identified using unsupervised learning of 3-dimensional shape: (1) nonsarcomeric hypertrophy with coexisting hypertension; (2) diffuse and basal asymmetrical hypertrophy associated with outflow tract obstruction; (3) isolated basal hypertrophy; and (4) milder nonobstructive hypertrophy enriched for familial sarcomeric HCM (odds ratio for pathogenic or likely pathogenic variants, 2.18 [95% CI, 1.93-2.28]; P=0.0001). Polygenic risk for HCM was also associated with different patterns and degrees of disease expression. The model was generalizable to an independent cohort (trustworthiness, M1: 0.86-0.88). CONCLUSIONS: We report a data-driven taxonomy of HCM for identifying groups of patients with similar morphology while preserving a continuum of disease severity, genetic risk, and outcomes. This approach will be of value in understanding the causes and consequences of disease diversity.

Causality-Inspired Single-Source Domain Generalization for Medical Image Segmentation.

Deep learning models usually suffer from the domain shift issue, where models trained on one source domain do not generalize well to other unseen domains. In this work, we investigate the single-source domain generalization problem: training a deep network that is robust to unseen domains, under the condition that training data are only available from one source domain, which is common in medical imaging applications. We tackle this problem in the context of cross-domain medical image segmentation. In this scenario, domain shifts are mainly caused by different acquisition processes. We propose a simple causality-inspired data augmentation approach to expose a segmentation model to synthesized domain-shifted training examples. Specifically, 1) to make the deep model robust to discrepancies in image intensities and textures, we employ a family of randomly-weighted shallow networks. They augment training images using diverse appearance transformations. 2) Further we show that spurious correlations among objects in an image are detrimental to domain robustness. These correlations might be taken by the network as domain-specific clues for making predictions, and they may break on unseen domains. We remove these spurious correlations via causal intervention. This is achieved by resampling the appearances of potentially correlated objects independently. The proposed approach is validated on three cross-domain segmentation scenarios: cross-modality (CT-MRI) abdominal image segmentation, cross-sequence (bSSFP-LGE) cardiac MRI segmentation, and cross-site prostate MRI segmentation. The proposed approach yields consistent performance gains compared with competitive methods when tested on unseen domains.