Femoral head necrosis staging analysis method and system based on artificial intelligence
A femoral head necrosis and artificial intelligence technology, applied in image analysis, neural learning methods, instruments, etc., can solve problems such as high skill requirements, poor repeatability of staging judgment of femoral head necrosis, and difficulty in identifying ARCO1-2 stages of femoral head necrosis. , to achieve the effect of reducing requirements and reducing reading time
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2021-11-26
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the field of medical image classification, in particular to an artificial intelligence-based method and system for staging analysis of femoral head necrosis. Background technique
[0002] Femoral head necrosis is a kind of ischemic osteonecrosis disease caused by multiple factors. The course of the disease develops rapidly, which can easily lead to femoral head collapse and high disability rate. It is a common refractory disease in orthopedics. About 20,000-30,000 new cases of osteonecrosis of the femoral head occur each year in the United States. In my country, the incidence of femoral head necrosis is increasing year by year due to the increase of trauma, alcohol consumption and hormone abuse. The first large-scale epidemiological survey of non-traumatic osteonecrosis in China shows that the cumulative number of patients with non-traumatic osteonecrosis has reached 8.12 million, and the prevalence rate of men (1.02%) is sign...
Examples
Embodiment 1
[0059] figure 1 It is a schematic diagram of an artificial intelligence system for identifying and staging femoral head necrosis lesions, and the staging of femoral head necrosis is mainly based on ARCO staging 1-4.
[0060] A staging analysis method for femoral head necrosis based on artificial intelligence:
[0061] S1, acquiring a hip MRI image of a patient, and performing preprocessing on the acquired hip MRI image;
[0062] S2. Constructing a femoral head necrosis lesion recognition model, identifying and locating the femoral head necrosis region and side of the patient based on the femoral head necrosis lesion recognition model, and generating a visual class activation map for the lesion;
[0063] S3, constructing a femoral head necrosis lesion staging model, inputting the visualization class activation map into the femoral head necrosis lesion staging model, judging the femoral head necrosis staging of the MRI image, and obtaining a lesion staging judgment result;
[...