Cardiovascular three-dimensional reconstruction system based on multi-modal image data fusion

The cardiovascular 3D reconstruction system, which integrates multimodal image data, solves the problem of poor 3D reconstruction results caused by irregular cardiac pulsation under atrial fibrillation rhythm. It achieves accurate matching and robust reconstruction of the dynamic contour of the heart, improving reconstruction accuracy and robustness.

CN122176242AActive Publication Date: 2026-06-09SECOND MEDICAL CENT OF CHINESE PLA GENERAL HOSPITAL
7 Cites 1 Cited by

Patent Information

Application Number
CN202610637296.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-05-11
Publication Date
2026-06-09
Estimated Expiration
2046-05-11

AI Technical Summary

Technical Problem

In atrial fibrillation scenarios, irregular heartbeats lead to poor cardiovascular 3D reconstruction results. Existing technologies struggle to accurately match the dynamic cardiac contour during surgery, easily resulting in anatomical alignment deviations and artifact interference.

Method used

A cardiovascular 3D reconstruction system employing multimodal image data fusion utilizes modules for data acquisition, initialization, matching analysis, and model updating. By leveraging the temporal continuity of cardiac motion and anatomical constraints, it accurately matches 3D predicted contour points with 2D observed edge points, removes artifact interference, and updates the 3D reconstruction model.

Benefits of technology

It enables continuous tracking of the complex motion trajectory of the heart under atrial fibrillation rhythm, accurately distinguishes between real anatomical edges and artifacts, significantly improves the accuracy and robustness of cardiovascular 3D reconstruction, and ensures robust anatomical topology.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of three-dimensional modeling, in particular to a cardiovascular three-dimensional reconstruction system based on multi-modal image data fusion. The method comprises the following steps: determining a composite matching cost between two corresponding points and determining an optimal matching pair set between three-dimensional prediction contour points and two-dimensional observation edge points based on the position difference between the three-dimensional prediction contour points and the two-dimensional observation edge points at each moment, anatomical structure space constraint and direction feature consistency; and based on the geometric error cost and the anatomical structure spatial constraint after the influence of the anatomical structure spatial constraint is removed from the composite matching cost of the matching point pairs in the optimal matching pair set, adjusting the projection deviation between the matching point pairs, updating the positions of the three-dimensional prediction contour points of the three-dimensional reference model, and obtaining a three-dimensional reconstruction model. According to the method, the accurate reconstruction of the cardiovascular model under the atrial fibrillation irregular heart rhythm is realized by utilizing multi-dimensional constraint composite cost accurate matching and based on a double-constraint updating strategy of geometric errors and anatomical resistance.
Need to check novelty before this filing date? Find Prior Art