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.

CN122090145APending Publication Date: 2026-05-26ZHEJIANG UNIV OF TECH +1
View PDF 0 Cites 0 Cited by

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

Technical Problem

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.

Method used

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.

Benefits of technology

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.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122090145A_ABST
    Figure CN122090145A_ABST
Patent Text Reader

Abstract

This invention relates to the field of medical image artificial intelligence analysis technology, specifically to an automated preoperative precise risk stratification system and method for gastrointestinal stromal tumors. It includes: a data preprocessing module for acquiring the original sequences of multi-phase computed tomography (CT) scans of the patient's abdomen, and performing three-dimensional volume data construction, spatial dimension standardization, and voxel intensity normalization to generate a standardized three-dimensional tensor; a deep learning model module for receiving the three-dimensional tensor and, based on a 3D Swin Transformer architecture, outputting classification probabilities corresponding to four risk levels: very low risk, low risk, intermediate risk, and high risk; and an interpretable visualization module for generating heatmaps identifying key decision-making regions of the model using gradient-weighted class activation mapping technology, and overlaying these heatmaps back onto the original CT images for visualization.
Need to check novelty before this filing date? Find Prior Art