Abstract
Accurate and real-time biomechanical modelling of the liver is a major challenge in computer-assisted surgery. Finite element method is often used to predict the deformation of organs for its high modelling accuracy. However, its high computation cost hinders its application in real time, such as virtual surgery simulations. A liver model with biomechanical properties similar to real one is created using finite element method and a data set of the liver deformation with different forces (whose magnitude ranges from 0.1 to 0.5N in omni-direction) acting on different surface points is generated. The mechanical behaviour of liver is simulated in real time by a tree-based LightGBM regression model trained with the generated data set. In comparison with the Random Forest and XGBoost, the LightGBM model achieves the best accuracy with 0.0774mm, 0.0786mm, 0.0801mm in the mean absolute error (MAE) and 0.0591mm, 0.0609 and 0.0622mm in the root mean square error (RMSE) along x, y and z axis, respectively. In addition, it only takes 33ms for the LightGBM model to estimate the deformation of the liver, which is much faster than finite element model (29.91s). These results lay a foundation for the future development of real-time virtual surgery systems of simulating liver deformation during minimally invasive surgeries using our method.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call