Spine three-dimensional evaluation and intelligent grading system based on multi-view learning
The 3D assessment system, which utilizes multi-view learning and combines graph neural networks and a multi-task learning framework, solves the multi-dimensional and personalized problems in existing scoliosis assessment technologies. It achieves accurate multi-dimensional assessment and personalized rehabilitation grading, generating easy-to-understand reports.
Patent Information
- Application Number
- CN202511486719.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-17
- Publication Date
- 2026-03-17
AI Technical Summary
Existing scoliosis assessment techniques cannot achieve multi-task, multi-label joint modeling, resulting in a lack of comprehensiveness and personalization in the assessment results, making it difficult for ordinary patients to understand the report content.
A three-dimensional assessment system based on multi-view learning is adopted. Through multi-view image acquisition, image preprocessing, feature extraction and multi-label assessment modules, combined with graph neural network and multi-task learning framework, a multi-dimensional assessment and personalized rehabilitation grading of scoliosis can be realized.
It enables precise, multi-dimensional assessment of scoliosis, generates comprehensive and easy-to-understand reports, provides personalized rehabilitation plans, and improves the accuracy of assessments and the interpretability of reports.