The application relates to the technical field of
image processing, and discloses an interventional navigation method and
system based on multi-
modal image fusion. The method comprises the following steps: CT
angiography data is segmented to form a three-dimensional vascular skeleton model, MRI
perfusion data is calculated to generate a
vascular flow field, and a vascular geometric
constraint matrix is constructed; the
constraint matrix and instrument position information are diffused and reconstructed, and an instrument
motion prediction trajectory is output; an X-
ray fluoroscopy image instrument tip posture is estimated, and instrument-vascular
spatial correlation features are formed; safe navigation constraint parameters are calculated and generated through a distance field; and a path planning
algorithm is used to generate real-time navigation instructions containing a pushing distance and a rotation angle. The application solves the technical problems of insufficient multi-
modal image data fusion, inaccurate instrument
motion prediction and imperfect safety constraint mechanism in a traditional interventional
navigation system, and improves the precision, safety and real-time performance of interventional
surgery navigation.