Priori Model and Image Feedback-based Automatic Ultrasound Scanning Probe Position Control Method

Compared with traditional manual scanning, using a robotic arm for automatic scanning can assist doctors in obtaining better quality ultrasound images. However, most automatic scanning processes require patients to hold their breath to reduce the impact of skin surface undulations caused by breathing and other movements on the image quality of ultrasound images, which may cause discomfort to patients due to hypoxia during the scanning process. In response to the problem of poor imaging quality caused by respiratory motion, this paper proposes a terminal pose control method based on prior models and image feedback. Different strategies are adopted based on sampled data within a certain period of time and prior models of respiratory motion in different parts of the human body to obtain the optimal probe pose. Finally, the pr<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>obe pose is adjusted based on the ultrasound confidence map to obtain the best quality ultrasound image in the shortest possible time. The experimental results show that the method proposed in this paper can make the initial pose scanned by the probe close to the optimal pose, reducing the closed-loop adjustment time of the probe.