Echocardiography is the most widely used cardiac imaging modality, capturing ultrasound video data to assess cardiac structure and function1. Artificial intelligence (AI) in echocardiography has the potential to streamline manual tasks and improve reproducibility and precision2. However, most echocardiography AI models are single-view, single-task systems that do not synthesize complementary information from multiple views captured during a full exam3,4, and thus lead to limited performance and scope of applications.
In our head-to-head experiments, we observe that offline contrastive training offers a more valuable training signal than traditional SFT methods, demonstrating its effectiveness in model performance.