Soft tissue puncture force modeling method based on segmented artificial neural networks

Abstract

The invention relates to a soft tissue puncture force modeling method based on segmented artificial neural networks, including the following steps: 1) selecting a soft tissue sample to be modeled forpuncture experiment to collect sample data; 2) analyzing and sorting the sample data, dividing all the data into before puncture, after puncture, and to the deepest point according to the puncture stage, and pulling out three groups, and dividing each group of data into a training group and a test group; 3) using the training group for neural network training, and then using the test group to evaluate the neural networks; and 4) calling the three neural networks obtained by training in a segmented way according to the puncture stage to complete modeling. The soft tissue puncture force modelingmethod based on segmented artificial neural networks has the advantages that being small in the prediction error of modeling, and being within the range of being difficult to be detected by human hands; being easy for modeling is easy, being time-saving and laborsaving; being able to mechanically model the complete process of soft tissue puncture, and being able to preferably complete modeling even in the most nonlinear phase; and having a certain universal applicability to the same tissue of different individuals for the model, wherein the overall predictive power trend is consistent with the experimental data.

Description

technical field [0001] The invention belongs to the field of information technology and relates to a biomechanical modeling method. Background technique [0002] In recent years, as the development of virtual reality technology has been highly valued by the country, virtual surgery systems have gradually been accepted and applied in the medical field. Currently, virtual surgery systems on the market are relatively mature in terms of interactive equipment, cutting image modeling, and medical image processing. However, due to the complexity of biomechanics, most systems only stop at the visualization stage, and few have good results A complete system for haptic feedback. The lack of tactile force feedback makes virtual surgery different from clinical surgery, which is also the biggest drawback of the virtual surgery system, which directly causes the virtual surgery system to be ineffective in teaching doctors. [0003] Most of the current soft tissue mechanics models use mas...

AI Technical Summary

Problems solved by technology

Currently, virtual surgery systems on the market are relatively mature in terms of interactive equipment, cutting image modeling, and medical image processing. However, due to the complexity of biomechanics, most systems only stop at the visualization stage, and few have good results A Complete System for Haptic Feedback

The lack of tactile force feedback makes virtual surgery different from clinical surgery, which is also the biggest disadvantage of the virtual surgery system, which directly causes the virtual surgery system to be ineffective in teaching doctors

[0003] Most of the current soft tissue mechanics models use the mass-spring-damper model or finite element model. These methods can achieve certain results, but the former is difficult to accurately model the whole puncture process, and the latter takes a long time and has poor real-time performance.

Images