Semantic Consistency-Guided Hybrid-Invariant Transformer for Domain Adaptation in Multiview Echo Quality Assessment

Yiran Li, Yankun Cao, Xiaoxiao Cui, Yuezhong Zhang, Subhas Chandra Mukhopadhyay, Yujun Li, Lizhen Cui, Zhi Liu, Shuo Li

Abstract: Multiview echo quality assessment in domain adaptation (MEA-DA) has not been explored due to the challenges posed by the significant differences between cardiac anatomical structures and cross-domain distributions. To cope with the robustness, specificity, and diversity limitations encountered when extending the existing DA algorithms to MEA-DA, we introduce a hybrid attention-aware domain-invariant transformer (HEEDformer), which offers three main contributions: 1) locally invariant consistency alignment (LCA) provides enhanced robustness by constraining the cross-domain multiscale semantic structural similarity registration to learn locally invariant knowledge. This approach enhances the correlation and consistency of locally invariant semantic knowledge, thereby enabling the generation of stable locally invariant features that accommodate the substantial transferable differences caused by subtle structural variances and thus improving robustness; 2) hybrid attention excitation (HAE) yields improved specificity by complementarily stimulating significant multidimensional information. It suppresses regions with low contributions and aggregates significant multidimensional feature representations, enhancing specificity; and 3) globally invariant aggregation representation (GAR) improves diversity by modeling global mutually invariant relationships to learn global topological semantic consistency. It aggregates globally invariant knowledge with local structural similarity to capture the cross-domain feature correlations, thus enhancing diversity. Our method achieves the highest performance on two challenging tasks. It demonstrates nearly 100% classification accuracy on both the ten- and seven-view echo datasets. For quality assessment, it achieves an optimal mean absolute error (MAE) of 0.1354 on the homogeneous experiments and a robust Pearson linear correlation coefficient (PLCC) of 0.9140 on the heterogeneous experiments with significant quality variations. We believe that this novel framework will provide a powerful MEA-DA solution.

External IDs:doi:10.1109/tim.2025.3561437