Lesser trochanter recognition method, device and electronic equipment based on deep learning

Abstract

The present application discloses a method, device, and electronic device for identifying the lesser trochanter based on deep learning. The method includes: acquiring a two-dimensional cross-sectional image to be identified; using a segmentation network to segment the femur on the two-dimensional cross-sectional image to be identified ; Using a level classifier to classify the image of the femur segmentation result to obtain a level of the lesser trochanter; using a point recognition network to identify the level of the lesser trochanter to locate key points of the lesser trochanter. Using artificial intelligence to identify the lesser trochanter can get the key points of the lesser trochanter area defined by traditional medicine. Compared with manually positioning points in the lesser trochanter area by doctors and calculating the leg length difference, the accuracy of lesser trochanter positioning can be greatly improved. It can greatly improve the calculation accuracy of leg length difference, and provide reliable data support for doctors to operate.

Description

technical field [0001] The present application relates to the field of medical technology, in particular, to a deep learning-based identification method, device and electronic equipment for the lesser trochanter of the femur. Background technique [0002] Whether some key positions can be accurately determined in the medical field is an important factor affecting the success of some medical operations. For example, in osteotomy surgery, due to the perpendicular line connecting the protrusion of the lesser trochanter and the ischial tuberosity, the difference between the two sides (L1-L2) can represent the shortening distance of the limbs. figure 1 Therefore, the position of the lesser trochanter determines the position of the femoral neck osteotomy. Generally, the position of the femoral neck osteotomy should not be less than 3mm above the upper edge of the lesser trochanter. Therefore, accurate positioning of the lesser trochanter can determine the difference in the length...

AI Technical Summary

Problems solved by technology

[0003] At present, the calculation of leg length difference in digitally reconstructed radiographic images can only be calculated by manual points taken by doctors. Because the medical definition of the small trochanter is a region, such as figure 1 The lesser trochanter shown, together with manually taking points in the lesser trochanter area, leads to low accuracy and poor calibration stability, which may lead to too large differences in the length of the lower limbs of patients after surgery, which cannot meet actual needs

Images