A CT Image-Based Virtual Sensing Method to Estimate Bone Drilling Force for Surgery Robots.

AbstractObjective: Understanding medical images like the human surgeon is a challenge for current surgical robots. It is still hard for surgical robots to achieve safe and stable operations with the help of priori information from preoperative images. We proposed a method to estimate drilling force information based on preoperative images, which can provide priori force information for surgical robots to perform bone drilling tasks. Methods A visual sensing computing framework is proposed to obtain the 3D image information from the drill-tissue contact area in a one-dimensional signal format. Under this computing framework, a computed tomography (CT) image-weighted bone drilling mechanical model is built. The model considers both targets bone shape and material properties to predict the thrust force, torque, and radial force of a drilling process based on preoperative CT images. Results The built model can respond to multiple bone drilling process factors, such as personalized surgery plans, varying tissue densities, uneven drilling surfaces, different drilling speeds, feed rates, and drill bit geometries. The minimum error of the predicted thrust force on bovine bones is 1.130.95 N, and the best normalized average prediction error on porcine bones is 0.070.08. Experiments in spinal pedicle screw placement surgery also show potential application abilities. Conclusion Our method predicts the bone drilling force well based on preoperative images, providing robots with more efficient preoperative information. Significance This work offers a new perspective to study the interaction relationship between robot surgical instruments and tissues with the assistance of preoperative images.