Blunt device injury craniocerebral maximum principal strain prediction method and system based on convolutional neural network model

Abstract

The invention discloses a method for predicting the maximum principal strain of the brain of a blunt device injury based on a convolutional neural network model. The method comprises the following steps: 1, carrying out finite element simulation on a blunt device hitting head; 2, extracting the maximum principal strain of the brain in the simulation data; 3, extracting speed curves of the blunt device in the simulation data in the X, Y and Z directions under the global coordinate system; cutting and filling the speed curve, and mapping and scaling the speed curve to obtain a mapping graph; wherein the mapping graph comprises an X axial speed, a Y axial speed and a Z axial speed; 4, constructing a convolutional neural network for training and predicting the maximum principal strain influence of the blunt device hitting the head on the brain; 5, taking the mapping graph and the maximum principal strain of the brain as input and output to train the convolutional neural network, and selecting an optimal model; 6, using the optimal model to predict the maximum principal strain of the brain.

Description

technical field [0001] The present invention relates to the technical field of deep learning and finite element simulation calculation, and in particular to a rapid quantitative evaluation method for craniocerebral injury caused by hitting the head with a stick based on convolutional neural network and finite element technology. Background technique [0002] The cranial brain is the most important life center of the human body, and the fatality rate and disability rate after injury are extremely high. Brain injury is one of the world's leading public health problems. According to the World Health Organization, more than 40 million people worldwide suffer from mild brain injuries each year. In forensic identification, blunt force trauma is one of the main factors leading to traumatic brain injury. Among them, sticks and blunt weapons accounted for the highest proportion. However, the current quantitative evaluation methods for blunt force-induced brain injury are extremely...

AI Technical Summary

Problems solved by technology

[0003] 1. The finite element simulation experiment requires a lot of computing time and high-performance workstations, and requires operators to have certain professional knowledge

[0004] 2. For larger strain shocks and more complex injury factors, the prediction accuracy of the simplified model will be greatly reduced

[0005] 3. The existing technology model can only conduct an overall quantitative evaluation of the brain tissue, but cannot analyze and evaluate the local brain tissue

Images