A 2.5D medical image osteoporosis probability prediction system and method based on double fusion of Transformer and stacking

By constructing a two-layer fusion prediction pipeline based on Transformer and Stacking, the problem of insufficient accuracy and robustness in predicting the risk of osteoporosis after cervical cancer radiotherapy in existing technologies is solved, realizing high-precision and personalized osteoporosis risk prediction and supporting prospective clinical intervention.

CN122158081APending Publication Date: 2026-06-05LIAONING UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
LIAONING UNIVERSITY
Filing Date
2026-03-13
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing technologies lack foresight in predicting the risk of osteoporosis after cervical cancer radiotherapy, have limited predictive accuracy, and cannot meet the needs of personalized precision medicine. Furthermore, traditional methods suffer from information loss and insufficient robustness in feature fusion and decision fusion.

Method used

We construct a two-layer fusion prediction pipeline by employing Transformer-based deep feature pre-fusion and Stacking post-decision fusion. Through heterogeneous CNN feature extraction, Transformer encoder feature fusion, multimodal feature concatenation, and Stacking decision optimization, we achieve multi-level information fusion at the feature level and decision level.

Benefits of technology

It significantly improves the model's prediction accuracy and robustness, enabling early, accurate, and individualized prediction of osteoporosis risk in cervical cancer radiotherapy patients, supporting prospective clinical intervention, reducing the risk of overfitting, and improving the model's generalization ability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122158081A_ABST
    Figure CN122158081A_ABST
Patent Text Reader

Abstract

The application provides a 2.5D medical image osteoporosis prediction method and system based on double fusion of a Transformer and stacking, and belongs to the field of artificial intelligence and medical image analysis. First, deep features are extracted in parallel from a 2.5D pelvic CT slice group by using a plurality of pre-training convolutional neural networks; then multi-head self-attention pre-fusion is performed by using a Transformer encoder to generate a unified image feature vector; then the unified image feature vector is spliced with key clinical features such as age and radiotherapy dose to form a multi-modal feature, and the multi-modal feature is input into a plurality of base classifiers to obtain preliminary prediction probabilities; finally, a stacking strategy is used for post-fusion to obtain a final osteoporosis risk probability. Experiments show that the method has excellent prediction performance, the external validation AUC reaches 0.964, and individualized bone damage risk assessment before radiotherapy can be realized.
Need to check novelty before this filing date? Find Prior Art