Ultrasound Video
Ultrasound video analysis leverages the temporal dimension of ultrasound scans to improve diagnostic accuracy and efficiency across various medical applications, primarily focusing on automated lesion detection and classification. Current research heavily employs deep learning, incorporating convolutional and recurrent neural networks, transformers, and contrastive learning methods, often enhanced by attention mechanisms to focus on relevant features within the video sequences. This field is significant due to its potential to alleviate the burden on healthcare professionals, improve diagnostic accuracy, particularly in resource-limited settings, and facilitate earlier and more precise interventions.
Papers
Weakly-supervised High-fidelity Ultrasound Video Synthesis with Feature Decoupling
Jiamin Liang, Xin Yang, Yuhao Huang, Kai Liu, Xinrui Zhou, Xindi Hu, Zehui Lin, Huanjia Luo, Yuanji Zhang, Yi Xiong, Dong Ni
A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videos
Zhi Lin, Junhao Lin, Lei Zhu, Huazhu Fu, Jing Qin, Liansheng Wang