Improved segmentation of cardiac structures in echocardiograms for diastolic function evaluation

Noninvasive assessment of diastolic dysfunction relies on multiple echocardiographic indicators, including measurements from both standard B-mode images and Doppler, obtained at various cardiac locations such as the mitral annulus, tricuspid annulus, left ventricle, and left atrium. The diagnostic process is complex and subject to interobserver variability, making accurate and rapid evaluation challenging. Automated semantic segmentation of key cardiac structures, such as the left atrium, left ventricle, and mitral valve annulus, offers a potential solution by capturing temporal changes throughout the cardiac cycle.

This study aims to improve the accuracy of segmenting the left atrium, left ventricle, and mitral valve annulus in echocardiographic images and to leverage the resulting temporal segmentation features for more reliable identification of diastolic dysfunction.

This study presents Diff-TransUNet, a novel segmentation model incorporating a noise-robust Differential Transformer module. Evaluations on private (1137 training images, 135 validation images, and 88 test images), CAMUS (1400 training images, 200 validation images, and 200 test images), and EchoNet-Dynamic (5000 training images, 2546 validation images, and 2528 test images) datasets demonstrate improved performance over state-of-the-art methods, assessed by Dice coefficient (Dice), Intersection-over-Union (IoU), and 95th percentile Hausdorff Distance (HD₉₅) metrics. Statistical analysis was performed to compare Diff-TransUNet with baseline methods across evaluation metrics. To control for errors arising from multiple comparisons, p-values were adjusted using the Benjamini-Hochberg false discovery rate (FDR) correction. Statistical significance was assessed at a 95% confidence level. In addition to p-values, Cohen's d effect size was computed to quantify the practical significance of performance differences.

The proposed Diff-TransUNet achieved a Dice of 87.49%, IoU of 79.07%, and HD₉₅ of 1.48 on the private dataset. Compared with state-of-the-art models, Dice improved by 1.35%-4.30% (p < 0.05, Cohen's d = 0.32-0.90), IoU by 1.97%-5.67% (p < 0.05, Cohen's d = 0.37-1.03), and HD₉₅ by 0.16-0.83 (p < 0.05, Cohen's d = 0.21-0.90). On the CAMUS dataset, the model achieved a Dice of 88.74%, IoU of 80.58%, and HD₉₅ of 2.83, showing improvements of 1.07%-4.96% (p < 0.05, Cohen's d = 0.18-0.63) in Dice, 1.55%-6.89% (p < 0.05, Cohen's d = 0.19-0.71) in IoU, and 0.41-2.85 (p < 0.05, Cohen's d = 0.12-0.46) in HD₉₅ compared to advanced models. On the EchoNet-Dynamic dataset, the model obtained a Dice of 92.25%, IoU of 85.87%, and HD₉₅ of 1.65, outperforming other methods by 0.42%-2.00% (p < 0.05, Cohen's d = 0.10-0.40) in Dice, 0.69%-3.21% (p < 0.05, Cohen's d = 0.10-0.43) in IoU, and 0.21-1.12 (p < 0.05, Cohen's d = 0.09-0.34) in HD₉₅. Furthermore, by extracting volumetric segmentation features, the proposed method achieved an accuracy of 88.95% (95 % CI 87.15% to 90.08%) in identifying diastolic dysfunction.

The proposed Diff-TransUNet model achieves significant improvements in ultrasound segmentation. Features extracted from the left ventricle, left atrium, and mitral annulus segmented by Diff-TransUNet can be effectively used for the identification of diastolic dysfunction.