Proximal femur segmentation method and device, computer device and storage medium

Abstract

The invention discloses a proximal femur segmentation method and device, a computer device and a storage medium. The proximal femur segmentation method comprises the following steps: inputting a 3D MRI image of the femur into a segmentation model obtained by the pre-training of a 3D U-net; identifying the segmentation boundary of the proximal femur in the 3D MRI image through the segmentation model; segmenting the proximal femur in the 3D MRI image according to the segmentation boundary. According to the invention, the proximal femur is automatically separated from the 3D MRI image through thesegmentation model, and the proximal femur is separated from the original map, so that the diagnosis interference information can be reduced, and the diagnosis efficiency of a doctor can be greatly improved; a 3D MRI proximal femur segmentation technology based on the 3D U-net is provided, by means of the 3D U-net network with the depth monitoring and learning effects, the precise segmentation model is obtained through a small number of labeled samples, the accurate segmentation of the proximal femur of the 3D MRI proximal femur is achieved, and the technical problem that accurate segmentation is difficult due to the poor marked 3D MRI image data in the prior art is made up.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a method, device, computer equipment and storage medium for segmenting the proximal end of the femur. Background technique [0002] In recent years, due to the improvement of computer hardware level, deep neural network technology has been developed by leaps and bounds. Deep neural network technology has achieved great results in image, text or audio processing, but it has not been widely used in the medical field. Femoroacetabular impingement is one of the causes of hip pain in adults and is considered a key factor in cartilage damage and a precursor to osteoarthritis. MRI diagnosis is now used as a standard tool in the diagnosis of femoroacetabular impingement because it does not pose a radiological hazard. However, in the prior art, doctors generally conduct manual diagnosis by analyzing 2D MRI slice images based on medical experience, which has low diagnostic eff...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of this application is to provide a method for segmenting the proximal femur, aiming to solve the technical problem of accurately separating the proximal femur in 3D MRI images

Images