Motion-enhanced Cardiac Anatomy Segmentation via an Insertable Temporal Attention Module

Cardiac anatomy segmentation is useful for clinical assessment of cardiac morphology to inform diagnosis and intervention. Deep learning (DL), especially with motion information, has improved segmentation accuracy. However, existing techniques for motion enhancement are not yet optimal, and they have high computational costs due to increased dimensionality or reduced robustness due to suboptimal approaches that use non-DL motion registration, non-attention models, or single-headed attention. They further have limited adaptability and are inconvenient for incorporation into existing networks where motion awareness is desired. Here, we propose a novel, computationally efficient Temporal Attention Module (TAM) that offers robust motion enhancement, modeled as a small, multi-headed, cross-temporal attention module. TAM's uniqueness is that it is a lightweight, plug-and-play module that can be inserted into a broad range of segmentation networks (CNN-based, Transformer-based, or hybrid) for motion enhancement without requiring substantial changes in the network's backbone. This feature enables high adaptability and ease of integration for enhancing both existing and future networks. Extensive experiments on multiple 2D and 3D cardiac ultrasound and MRI datasets confirm that TAM consistently improves segmentation across a range of networks while maintaining computational efficiency and improving on currently reported performance. The evidence demonstrates that it is a robust, generalizable solution for motion-awareness enhancement that is scalable (such as from 2D to 3D).