Method and system, storage medium and electronic equipment for identifying force lines using neural network

Abstract

A method and system for assisting identification of force lines using a neural network, which can be used to detect force lines before and after surgery, assist surgery and understand postoperative recovery status. The method comprises the steps of: obtaining a first image by combining lines of CT file sequences into a complete three-dimensional image, and then performing slices from the coronal plane, and inputting the first image into a first multi-class segmentation based on unet and using a softmax activation function The neural network classifies the femur and tibia differently, thereby segmenting the models of the femur and tibia at one time; and using the second segmentation to find the center point of the femoral head on the femoral model with the neural network to determine the line of force, which is also based on the point cloud Calculate other key physiological points: the center point of the femoral knee joint, the center point of the tibial knee joint and the center point of the tibial ankle joint. Wherein, bilinear quantization processing is performed on the first image, so that down-quantization can also be performed while upward interpolation is performed through bilinear interpolation.

Description

technical field [0001] The present invention relates to the field of medical technology, that is, the field of computer-aided planning technology for joint replacement and the technical field of medical image data processing. More specifically, it involves a method based on image reconstruction, deep learning, and numerical algorithms to calibrate the line of force, especially redesigning a different deep learning marking scheme based on the coronal plane. Background technique [0002] With the rapid development of modern society, all walks of life have begun to have an inseparable connection with the IT industry, and the same is true for the medical industry. Determining the position of the force line is very important in assisted knee arthroplasty by surgical robot, which can determine the success of the operation and the postoperative recovery status of the patient. If the calibration of the force line is not accurate, it may cause the patient to re-introduce the lesion ...

AI Technical Summary

Problems solved by technology

If the calibration of the force line is inaccurate, it may cause the patient to cause lesions again during the postoperative recovery process, and even lead to the complete failure of the entire operation

Images