Three-dimensional medical image segmentation method and system based on large language model prior knowledge

By constructing a medical image-text pair dataset and using a large language model to generate prior text knowledge, combined with a cross-modal attention mechanism for multi-level semantic perception fusion, the problem of lack of prior knowledge in the medical field in existing 3D medical image segmentation methods is solved, and high-precision and high-generalization tumor segmentation is achieved.

CN122244062APending Publication Date: 2026-06-19XIDIAN UNIV
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
XIDIAN UNIV
Filing Date
2026-02-28
Publication Date
2026-06-19

AI Technical Summary

⚠Technical Problem

Existing 3D medical image tumor segmentation methods lack effective integration and constraints of prior knowledge in the medical field, resulting in low accuracy and poor generalization in small sample and small/irregular lesion segmentation scenarios. The segmentation results may have problems such as anatomical inconsistencies, missed lesion detection/false positives.

⚗Method used

A 3D medical image segmentation method based on prior knowledge of a large language model is adopted. By constructing a medical image-text pair dataset, text prior knowledge is generated. Multi-level semantic perception fusion is performed using a cross-modal attention mechanism to generate fused semantic features. Finally, lesion prediction masks are generated through element-wise multiplication fusion processing.

🎯Benefits of technology

It significantly improves the accuracy and interpretability of segmentation, ensuring that the segmentation results conform to image features and follow clinical logic, and solves the problem of insufficient segmentation accuracy and generalization in small sample scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

This invention discloses a 3D medical image segmentation method and system based on prior knowledge from a large language model, belonging to the field of 3D medical image computing technology. The method first constructs a medical image-text pair dataset containing 3D medical images and prior information on manually labeled organs and lesions. Then, it generates text prior knowledge by combining the prior information with a large medical language model. Text prior features and high-dimensional image features are extracted by text and image encoders, respectively. Subsequently, a multi-level semantic perception fusion strategy based on a cross-modal attention mechanism is used to fuse the dual features, generating fused semantic features. The high-dimensional image features are decoded into 3D image features matching the spatial dimensions of the original image. Finally, element-wise multiplication fusion processing is used to generate a lesion prediction mask, completing the segmentation. This invention effectively integrates prior knowledge from the medical field, solving the problems of low accuracy and poor generalization of purely data-driven segmentation methods in scenarios with small samples and small lesions.
Need to check novelty before this filing date? Find Prior Art