The Studies of Early Intelligent Diagnosis of Limb Deformity in Children by AI and Clinic Application
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Limb Deformity
- Sponsor
- Children's Hospital of Fudan University
- Enrollment
- 9000
- Primary Endpoint
- Deformity detection
- Status
- Not yet recruiting
- Last Updated
- last year
Overview
Brief Summary
The limb deformity in children include congenital limb malformations or acquired from the damage of epiphyseal plate which caused by tumor, inflammation and trauma. Due to the complexity of the disease itself, rapid dynamic development and the characteristics of children's growth and development, the deformities are constantly changing. In addition, the serious lack of clinical diagnosis and treatment resources in the Department of Pediatric Orthopedics has led to the misdiagnosis and improper treatment of children's limb deformities. Thus, its necessary to find an intelligent way to help doctor to early diagnosis of limb deformity and provide a proper treatment in children.
Detailed Description
The extraction and application of big data of children's limb deformities, intelligent labeling of image data, precise positioning, and perfecting the anatomical data of children's limb deformities.Improve the positioning accuracy of key points in X-ray images of children's limb deformities by means of step-by-step supervision to improve the accuracy of diagnosis.Realize an intelligent report generation system that combines patient background information, establish an end-to-end auxiliary diagnosis and treatment suggestion demonstration application system; realize a full set of artificial intelligence solutions for children's skeletal deformities, early screening and diagnosis of children, and forming an intelligent referral system of children's limb deformities.
Investigators
Eligibility Criteria
Inclusion Criteria
- •Children with limb deformity
Exclusion Criteria
- •Children without limb deformity
Outcomes
Primary Outcomes
Deformity detection
Time Frame: At enrollment
It is a binary variable (1/0). The radiographic features of children would be evaluated by artificial Intelligence. If the deformity was detected, variable would be setted into 1.