A method and system for analyzing a blood vessel network of a moyamoya disease and simulating a bypass surgery based on multi-modal images
By using spatial geometric alignment, feature fusion and verification reconstruction, parametric analysis and physical constraint prediction of multimodal image data, the problems of fragmentation and artifacts in the vascular network model of Moyamoya disease were solved, and efficient, real-time simulation and quantitative screening of surgical targets for Moyamoya disease vascular network were achieved.
Patent Information
- Application Number
- CN202610451896.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-08
- Publication Date
- 2026-07-17
AI Technical Summary
Existing vascular analysis and simulation technologies struggle to balance suppressing background noise and preserving realistic vascular details when dealing with moyamoya disease. This results in vascular network models that are prone to breakage or contain artifacts. Furthermore, traditional methods are computationally intensive and time-consuming, making it difficult to achieve real-time assessment during the surgical planning stage.
By using spatial geometric alignment, feature fusion and verification reconstruction, parametric analysis and physical constraint prediction of multimodal image data, the topology of the vascular network in Moyamoya disease is reconstructed. Blood perfusion distribution is predicted using neural network and computational fluid dynamics simulation data, and surgical targets are screened by combining a multidimensional quantitative evaluation mechanism.
It significantly improves the topological reconstruction of the microvascular network in Moyamoya disease, provides objective quantitative surgical target reference, and enables real-time simulation and comparison of blood perfusion effects within seconds, avoiding high-risk anastomosis areas.
Smart Images
Figure CN122417434A_ABST