An automated preoperative precise risk stratification system and method for gastrointestinal stromal tumors
By introducing a 3D Swin Transformer architecture and multi-scale feature fusion technology, combined with a visual heatmap, the problems of insufficient feature modeling and interpretability in GIST risk stratification were solved, achieving accurate four-level risk stratification and improving the model's generalization ability and clinical applicability.
Patent Information
- Authority / Receiving Office
- CN Β· China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG UNIV OF TECH
- Filing Date
- 2026-02-10
- Publication Date
- 2026-05-26
AI Technical Summary
Existing technologies for risk stratification of gastrointestinal stromal tumors (GISTs) suffer from limited feature modeling capabilities, coarse risk stratification granularity, poor generalization ability in small samples, and insufficient model interpretability, making it difficult to achieve non-invasive, accurate, and interpretable four-level risk stratification before surgery.
A 3D Swin Transformer architecture is used for global feature calculation and relationship modeling. Combined with multi-scale feature fusion and channel attention, gradient-weighted class activation mapping technology is used to generate a visual heatmap to achieve accurate risk level assessment of tumor regions.
It significantly improves feature representation capabilities, achieves four-level fine stratification, enhances the model's generalization ability and interpretability, adapts to clinical needs, improves the accuracy and clinical reliability of risk stratification, has excellent performance, is applicable to multi-phase CT data, is adaptable to different hospital equipment, and is suitable for promotion and application in primary hospitals.
Smart Images

Figure CN122090145A_ABST