The MACS framework improved generalization performance for cross-domain echocardiography segmentation by 2.2% in the Dice metric without requiring manual annotations.
The MACS framework improves cross-domain echocardiography segmentation performance without requiring manual annotations, addressing data distribution shifts between different medical centers and vendors.
Effect estimate: 2.2% improvement
) in echocardiography plays an important role in clinical diagnosis. Recently, deep neural networks have been the most commonly used approach for echocardiography segmentation. However, the performance of a well-trained segmentation network may degrade in unseen domain datasets due to the distribution shift of the data. Adaptation algorithms can improve the generalization of deep neural networks to different domains. In this paper, we present a multi-space adaptation-segmentation-joint framework, named MACS, for cross-domain echocardiography segmentation. It adopts a generative adversarial architecture; the generator fulfills the segmentation task and the multi-space discriminators align the two domains on both the feature space and output space. We evaluated the MACS method on two echocardiography datasets from different medical centers and vendors, the publicly available CAMUS dataset and our self-acquired dataset. The experimental results indicated that the MACS could handle unseen domain datasets well, without requirements for manual annotations, and improve the generalization performance by 2.2% in the Dice metric.
Chen et al. (Sat,) conducted a other in Echocardiography segmentation. MACS (multi-space adaptation-segmentation-joint framework) was evaluated on Dice metric (2.2% improvement). The MACS framework improved generalization performance for cross-domain echocardiography segmentation by 2.2% in the Dice metric without requiring manual annotations.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: