Clean visual field reconstruction in robot-assisted laparoscopic surgery based on dynamic prediction

Robot-assisted minimally invasive surgery has been broadly employed in complicated operations. However, the multiple surgical instruments may occupy a large amount of visual space in complex operations performed in narrow spaces, which affects the surgeon’s judgment on the shape and position of the lesion as well as the course of its adjacent vessels/lacunae. In this paper, a surgical scene reconstruction method is proposed, which involves the tracking and removal of surgical instruments and the dynamic prediction of the obscured region. For tracking and segmentation of instruments, the image sequences are preprocessed by a modified U-Net architecture composed of a pre-trained ResNet101 encoder and a redesigned decoder. Also, the segmentation boundaries of the instrument shafts are extended using image filtering and a real-time index mask algorithm to achieve precise localization of the obscured elements. For predicting the deformation of soft tissues, a soft tissue deformation prediction algorithm is proposed based on dense optical flow gravitational field and entropy increase, which can achieve local dynamic visualization of the surgical scene by integrating image morphological operations. Finally, the preliminary experiments and the pre-clinical evaluation were presented to demonstrate the performance of the proposed method. The results show that the proposed method can provide the surgeon with a clean and comprehensive surgical scene, reconstruct the course of important vessels/lacunae, and avoid inadvertent injuries. •Removal of instrument shafts based on deep learning.•Achievement of the dynamic reconstruction of soft tissues in the obscured region.•Provision of a clear and comprehensive surgical scene for surgeons.