EUVIMEDOpdag EUVIMED
Multizentrische Studie

Multi‐Center Adversarial Bi‐Phase Cross‐Attention Network for Right Ventricular Segmentation and Functional Classification in Echocardiography

Bozhi Zhang, Weijuan Bai

Echocardiography · 2026-07 · 43 (7)

DOI: 10.1111/echo.70527 ↗

At a glance

Multizentrische Studie in Echocardiography, published online on 2026-06-28. Written by Bozhi Zhang and 1 co-authors. Institution: Department of Ultrasound Diagnostic, Bethune International Peace Hospital, Shijiazhuang City, Hebei Province, China. Major MEDLINE topics: Heart Ventricles, Echocardiography, Image Interpretation, Computer-Assisted, Ventricular Dysfunction, Right. 22 references.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Automated right ventricular (RV) analysis in 2D echocardiography is limited by the morphological complexity of RV segmentation and the domain fragility of single‐center deep learning models across ultrasound vendors. No prior framework has jointly addressed both challenges for RV‐specific segmentation.

Objectives

To develop and prospectively validate TACA‐Net (Bi‐Phase Adversarial Cross‐Attention Network), a unified multi‐center framework for simultaneous RV endocardial segmentation and three‐class functional severity classification (normal, mildly reduced, significantly reduced) in 2D apical four‐chamber echocardiography.

Methods

Data were prospectively collected from three clinical sites within a single tertiary hospital network, each equipped with a different ultrasound vendor. Centers A and B ( n = 1,240 patients) were used for training and 5‐fold cross‐validation; Center C ( n = 320 patients) served as the fully held‐out external test set. TACA‐Net integrates a gradient reversal layer‐based domain discriminator for vendor‐agnostic feature learning, a bidirectional bi‐phase cross‐attention module encoding the complementary information between end‐diastolic and end‐systolic representations, and a dual‐head decoder jointly optimizing segmentation and classification with an auxiliary bi‐phase consistency loss. Performance was benchmarked against six segmentation baselines (U‐Net, Attention U‐Net, TransUNet, Swin‐UNETR, nnU‐Net, MACS) and five classification baselines (ResNet‐50, EfficientNet‐B4, ViT‐B/16, segmentation‐then‐classify pipeline, MACS + head). Primary segmentation endpoints were Dice Similarity Coefficient (DSC) and Hausdorff Distance 95th percentile (HD95); primary classification endpoint was macro‐averaged area under the receiver operating characteristic curve (AUC).

Results

On the external test set, TACA‐Net achieved a DSC of 0.903 ± 0.013 and an HD95 of 7.1 ± 1.0 mm for RV segmentation, and a macro‐averaged AUC of 0.911 (95% CI: 0.885–0.937) for functional classification, statistically significantly superior to all six segmentation and five classification baselines (all p < 0.01). Ablation analyses demonstrated independent contributions of domain alignment (ΔDSC = −0.038 when removed), bi‐phase cross‐attention (ΔAUC = −0.032), and multi‐task joint training (ΔDSC = −0.014). No significant differential performance was detected across diagnosis subgroups, sex, or image quality strata. GradientSHAP attribution maps revealed highest feature importance in the RV lateral free wall, consistent with established RV pathophysiology. Expected calibration error for TACA‐Net was 0.041 on the external test set, the lowest among all classification models evaluated.

Conclusions

TACA‐Net achieves vendor‐agnostic RV segmentation and functional classification from routinely acquired 2D echocardiography, with robust multi‐vendor generalization demonstrated under rigorous prospective external validation. The framework provides a clinically interpretable and methodologically transparent foundation for AI‐assisted right heart assessment at scale.

Subjects

MeSH terms (MEDLINE)

Heart VentriclesEchocardiographyImage Interpretation, Computer-AssistedVentricular Dysfunction, RightDeep LearningHumansProspective StudiesReproducibility of Results

Author keywords

adversarial trainingdeep learningdomain adaptationechocardiographyfunctional classificationmulti‐centerright ventriclesegmentation

Authors and institutions

  • Department of Ultrasound Diagnostic, Bethune International Peace Hospital, Shijiazhuang City, Hebei Province, China.
  • Department of Geriatrics, Bethune International Peace Hospital, Shijiazhuang City, Hebei Province, China.

Cite

APA

Zhang, B., & Bai, W. (2026). Multi‐Center Adversarial Bi‐Phase Cross‐Attention Network for Right Ventricular Segmentation and Functional Classification in Echocardiography. Echocardiography, 43(7). https://doi.org/10.1111/echo.70527

Vancouver

Zhang B, Bai W. Multi‐Center Adversarial Bi‐Phase Cross‐Attention Network for Right Ventricular Segmentation and Functional Classification in Echocardiography. Echocardiography. 2026;43(7). doi:10.1111/echo.70527

BibTeX
@article{Zhang2026,
  author = {Zhang, Bozhi and Bai, Weijuan},
  title = {Multi‐Center Adversarial Bi‐Phase Cross‐Attention Network for Right Ventricular Segmentation and Functional Classification in Echocardiography},
  journal = {Echocardiography},
  year = {2026},
  volume = {43},
  number = {7},
  doi = {10.1111/echo.70527}
}
Start for free →