Key result
Spiking U-Mamba model outperforms state-of-the-art methods with ~90% segmentation accuracy on the CAMUS dataset.
Why the study?
Automatic echocardiographic segmentation lacks optimal performance, with room for improvement in employing temporal information.
The Spiking U-Mamba model improves automated echocardiographic image segmentation accuracy while balancing computational cost, potentially enhancing cardiac function assessment.
May support automated echo analysis in research pipelines; extends spiking models for segmentation but leaves open clinical validation.
The automatic segmentation of the heart from echocardiography can significantly improve the efficiency and effectiveness of assessing cardiac function and provide objective and reproducible quantitative evidence for clinical diagnosis, treatment planning, and disease screening. Many excellent results in the community of medical artificial intelligence have been achieved; however, there is still room for improvement, such as the employment of temporal information in echocardiography. In this paper, we propose the Spiking U-Mamba model, which incorporates three novel modules, i.e., MultiStepLIFEncoder, BidirectionalFeatureFusion and FeatureRefinementBlock. MultiStepLIFEncoder encodes static features into spatio-temporal pulse sequences to enhance the model’s boundary resolution capability, while BidirectionalFeatureFusion enables bidirectional interaction and attention enhancement between the Mamba global features and pulse features, and FeatureRefinementBlock further refines the fused features and ensures stable gradient propagation. Two public echocardiography datasets, CAMUS and EchoNet-Dynamic, were employed to evaluate the proposed Spiking U-Mamba model. On the CAMUS dataset, Spiking U-Mamba achieved a Dice coefficient of 90.16% during the ED phase and 90.54% during the ES phase, outperforming other SOTA methods; on the EchoNet-Dynamic dataset, Spiking U-Mamba also performed well. Since the employment of the Spiking Neural Network, the proposed Spiking U-Mamba model achieved a good balance between segmentation accuracy and computational cost.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) studied Echocardiography segmentation. Spiking U-Mamba model vs. Other state-of-the-art methods was evaluated on Dice coefficient during ED and ES phases on the CAMUS dataset. The Spiking U-Mamba model achieved a Dice coefficient of 90.16% during the ED phase and 90.54% during the ES phase on the CAMUS dataset, outperforming other state-of-the-art methods.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: