Prior knowledge snake segmentation of ultrasound images denoised by J-divergence anisotropy diffusion

Background: Applying transrectal ultrasound to robot-assisted laparoscopic radical prostatectomy has attracted attention in recent years, and it is considered as a proper method to provide real-time subsurface anatomic features. A precise registration between the ultrasound equipment and robotic surgical system is necessary, which usually requires a fast and accurate recognition of the registration tool in the ultrasound image. Methods: Tissue forceps are chosen as the registration tool. J-divergence anisotropy diffusion and prior knowledge snake segmentation are proposed for the automatic recognition of forceps in ultrasound images. Results: Simulation, gel tissue phantom experiments and in vitro experiments are carried out. Several evaluation indices are calculated to compare results under different methods. Conclusions: The proposed methods are proved to be practicable, reliable and superior to existing ones, with reduced calculation time and higher accuracy.