AUTHOR=Tian Haozhe , Cai Wenjia , Ding Wenzhen , Liang Ping , Yu Jie , Huang Qinghua
TITLE=Long-term liver lesion tracking in contrast-enhanced ultrasound videos via a siamese network with temporal motion attention
JOURNAL=Frontiers in Physiology
VOLUME=14
YEAR=2023
URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2023.1180713
DOI=10.3389/fphys.2023.1180713
ISSN=1664-042X
ABSTRACT=Propose: Contrast-enhanced ultrasound has shown great promises for diagnosis and monitoring in a wide range of clinical conditions. Meanwhile, to obtain accurate and effective location of lesion in contrast-enhanced ultrasound videos is the basis for subsequent diagnosis and qualitative treatment, which is a challenging task nowadays.
Methods: We propose to upgrade a siamese architecture-based neural network for robust and accurate landmark tracking in contrast-enhanced ultrasound videos. Due to few researches on it, the general inherent assumptions of the constant position model and the missing motion model remain unaddressed limitations. In our proposed model, we overcome these limitations by introducing two modules into the original architecture. We use a temporal motion attention based on Lucas Kanade optic flow and Karman filter to model the regular movement and better instruct location prediction. Moreover, we design a pipeline of template update to ensure timely adaptation to feature changes.
Results: Eventually, the whole framework was performed on our collected datasets. It has achieved the average mean IoU values of 86.43% on 33 labeled videos with a total of 37,549 frames. In terms of tracking stability, our model has smaller TE of 19.2 pixels and RMSE of 27.6 with the FPS of 8.36 ± 3.23 compared to other classical tracking models.
Conclusion: We designed and implemented a pipeline for tracking focal areas in contrast-enhanced ultrasound videos, which takes the siamese network as the backbone and uses optical flow and Kalman filter algorithm to provide position prior information. It turns out that these two additional modules are helpful for the analysis of CEUS videos. We hope that our work can provide an idea for the analysis of CEUS videos.