Weakly-supervised High-fidelity Ultrasound Video Synthesis with Feature Decoupling

TL;DR

This paper introduces a weakly-supervised framework for synthesizing high-fidelity ultrasound videos by animating source images based on driving video motion, utilizing keypoint detection, feature decoupling, and adversarial training.

Contribution

It presents a novel weakly-supervised approach combining keypoint detection, feature decoupling, and GANs for realistic ultrasound video synthesis, addressing complex motion handling.

Findings

Effective synthesis validated on pelvic ultrasound dataset

Improved video sharpness and realism demonstrated

User study confirms high-quality video generation

Abstract

Ultrasound (US) is widely used for its advantages of real-time imaging, radiation-free and portability. In clinical practice, analysis and diagnosis often rely on US sequences rather than a single image to obtain dynamic anatomical information. This is challenging for novices to learn because practicing with adequate videos from patients is clinically unpractical. In this paper, we propose a novel framework to synthesize high-fidelity US videos. Specifically, the synthesis videos are generated by animating source content images based on the motion of given driving videos. Our highlights are three-fold. First, leveraging the advantages of self- and fully-supervised learning, our proposed system is trained in weakly-supervised manner for keypoint detection. These keypoints then provide vital information for handling complex high dynamic motions in US videos. Second, we decouple content and texture learning using the dual decoders to effectively reduce the model learning difficulty. Last, we adopt the adversarial training strategy with GAN losses for further improving the sharpness of the generated videos, narrowing the gap between real and synthesis videos. We validate our method on a large in-house pelvic dataset with high dynamic motion. Extensive evaluation metrics and user study prove the effectiveness of our proposed method.