Motion-Conditioned Multi-View Fusion for Myocardial Infarction Localization from Echocardiography
2026-07-16 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the challenge of detecting heart damage (myocardial infarction) using ultrasound images from different views of the heart. They develop MCF-Net, which combines motion information from heart wall movement with advanced image features from a special pretrained model to better identify damaged areas. Their method uses minimal manual labeling to track motion, making it more practical. Tests show their approach is more accurate than previous methods that used only motion or only visual information. This helps improve locating heart damage more reliably in tricky ultrasound views.
Myocardial InfarctionEchocardiographyRegional Wall Motion AbnormalityFoundation ModelMulti-view FusionPoint TrackingSegment LocalizationMotion-guided AnalysisTemplate FrameF1 Score
Authors
Guang Yang, Wentian Xu, Siyu Wang, Betty Raman, Lei Li, Vicente Grau
Abstract
Myocardial infarction (MI) remains a leading cause of mortality worldwide. Echocardiography (Echo) is a widely available modality for MI assessment, where regional wall motion abnormality is a key indicator. Prior learning based methods for myocardial motion analysis often use handcrafted descriptors or densely supervised estimation, but the need for extensive annotation limits applicability. Foundation models have recently improved vision-based Echo analysis; however, most methods operate on single views and segment-level localization remains unreliable under view-dependent ambiguity, especially in apical views. To address this, we propose MCF-Net, a novel motion-guided multi-view fusion framework that fuses myocardial motion cues with foundation model representations to localize infarction. Visual features are extracted using EchoPrime, a pretrained Echo foundation model shared across dual views. Cardiac motion is modeled with extremely sparse supervision: a single annotated template frame is transferred across videos to initialize point tracking, avoiding dense labels. Motion-derived segment-aware soft masks provide coarse spatial priors that selectively enhance features for challenging myocardial segments. A motion-conditioned fusion mechanism then integrates motion and vision across views, refining predictions without overriding strong appearance cues. On segment-level MI localization, MCF-Net achieves 72.4\% F1 and 84.9\% accuracy, outperforming state-of-the-art motion-only, vision-only, and fusion baselines.