Method and system for auxiliary calculation of leg length by using deep learning, and readable storage medium

Abstract

The invention discloses a method and system for auxiliary calculation of leg length using deep learning, and the method comprises the following steps: using a first classification neural network to narrow an image range where anterior superior spine is located, using a second segmentation neural network sepnet to detect a pelvis within the image range, determining the position of the anterior superior spine according to a medical definition, adopting a third segmentation neural network deeplab for segmentation to identify a femur part without a femur head, determining a lesser trochanter according to a medical concept, and calculating the leg length based on the vertical distance between the cross section where the lesser trochanter is located and the cross section where the anterior superior spine is located. The first classification neural network is a vgg16-lspp obtained by improvement on the basis of a vgg16 network using a mish activation function and a spp structure using dilated cavity sampling. Point cloud data forming the left femoral stem and the right femoral stem are equally divided into two sets on the axis of the sagittal plane, and the innermost points are found to serve as the positions of the left lesser trochanter and the right lesser trochanter.

Description

technical field [0001] The present invention relates to the technical field of medical image analysis and processing. Specifically, it relates to a solution for using a neural network to assist in identifying leg length. More specifically, it relates to a method for calibrating legs based on deep learning, image reconstruction, and numerical algorithms. Long, especially to redesign a technical solution to find the lesser trochanter and anterior superior iliac spine. 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. For example, in robot-assisted total hip replacement surgery, it is important to determine leg length, which can determine the success of the operation and the recovery of the patient after surgery. If the leg length is not calibrated correctly, it may lead to unequal lengths of the lower limbs of patients a...

AI Technical Summary

Problems solved by technology

If the leg length is not calibrated correctly, it may lead to unequal lengths of the lower limbs of the patient after surgery, resulting in lameness, various injuries caused by uneven force on the legs, etc.

Images