一种多模态磁共振支架再狭窄预测方法与系统
By standardizing and registering multimodal magnetic resonance imaging (MRI) data with initial clinical data, an alignment index structure is generated, static and dynamic features are extracted, individual feature vectors are constructed, and predictions are made using a pre-trained model. This solves the lag problem in ISR management and enables individualized risk prediction and report generation for intracranial arterial stent restenosis.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- THE NAVAL MEDICAL UNIV OF PLA
- Filing Date
- 2025-11-19
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies have significant limitations in the management of restenosis (ISR) after stent implantation for intracranial atherosclerotic stenosis. They cannot effectively monitor the early pathological process of ISNA, lack personalized prediction tools, and existing multimodal magnetic resonance stent restenosis prediction schemes suffer from problems such as unstable registration across time points and inconsistent feature sets, making it difficult to achieve continuous risk prediction and report generation.
By acquiring multimodal magnetic resonance imaging and structured clinical preliminary data, standardization and artifact suppression, registration and alignment are performed to generate an alignment index structure. Candidate region localization and segmentation are performed to generate static and dynamic feature sets, which are then encoded to construct individual feature vectors. Pre-trained models are used for prediction, risk probability and evidence tracing packages are generated, and visualization reports are generated, achieving consistent alignment and continuous processing across time points.
It enables end-to-end individualized prediction of restenosis risk after intracranial artery stenting, ensuring consistent alignment of static and dynamic characteristics across multiple time points, generating personalized risk prediction reports, and supporting clinical decision-making.
Smart Images
Figure CN121528573B_ABST