Semi-Supervised Landmark Tracking in Echocardiography Video via Spatial–Temporal Co-Training and Perception-Aware Attention
- 6 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (5) , 2187-2197
Abstract
Precise landmark annotation in cardiac ultrasound images is fundamental for quantitative cardiac health assessment. However, the time-intensive nature of manual annotation typically constrains clinicians to annotate only selected key frames, limiting comprehensive temporal analysis capabilities. While recent automated landmark detection methods have demonstrated success for key-frame analysis, they fail to effectively utilize the intrinsic temporal information across cardiac sequence. To bridge this gap, we present SemiEchoTracker, a novel semi-supervised framework that enables comprehensive landmark tracking throughout echocardiography sequences while requiring supervision only on key frames. Our framework introduces three key innovative strategies: 1) a co-training mechanism that enforces mutual consistency between spatial detection and temporal tracking, enabling accurate intermediate frame detection without additional annotations, 2) a guided DINOv2 pretraining strategy that is specially tailored for extracting fine-grained echocardiography-specific spatial features, and 3) a perception-aware spatial-temporal (PAST) attention module that efficiently captures inter- and intra-frame relationships in echocardiography videos. Extensive validation on three datasets across multiple cardiac views demonstrates that our method not only achieves state-of-the-art detection performance on the keyframes but also yields accurate frame-by-frame prediction, which is important for dynamic cardiac analysis in clinicians.Keywords
Funding Information
- National Natural Science Foundation of China (U23A20295)
- National Natural Science Foundation of China (82441023)
- National Natural Science Foundation of China (62131015)
- National Natural Science Foundation of China (82394432)
- China Ministry of Science and Technology (S20240085)
- China Ministry of Science and Technology (STI2030)
- China Ministry of Science and Technology (2022ZD0209000)
- China Ministry of Science and Technology (STI2030)
- China Ministry of Science and Technology (2022ZD0213100)
- Shanghai Municipal Central Guided Local Science and Technology Development Fund (YDZX20233100001001)
- Key Research and Development Program of Guangdong Province, China (2023B0303040001)
- ShanghaiTech University
This publication has 29 references indexed in Scilit:
- A Semi-Supervised Knowledge Distillation Framework for Left Ventricle Segmentation and Landmark Detection in Echocardiograms2025
- Agent Attention: On the Integration of Softmax and Linear Attention2024
- EchoTracker: Advancing Myocardial Point Tracking in Echocardiography2024
- Cephalometric Landmark Detection Across Ages with Prototypical Network2024
- Multi-view Vertebra Localization and Identification from CT Images2023
- EchoGLAD: Hierarchical Graph Neural Networks for Left Ventricle Landmark Detection on Echocardiograms2023
- Light-weight Spatio-Temporal Graphs for Segmentation and Ejection Fraction Prediction in Cardiac Ultrasound2022
- High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy With Cardiovascular Deep LearningJAMA Cardiology, 2022
- Structured Landmark Detection via Topology-Adapting Deep Graph Learning2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015