Medical image three-dimensional reconstruction method and system

CN122454050APending Publication Date: 2026-07-24BEIJING RAND TECHNOLOGY DEVELOPMENT CO LTD

View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office: CN · China
Patent Type: Applications(China)
Current Assignee / Owner: BEIJING RAND TECHNOLOGY DEVELOPMENT CO LTD
Filing Date: 2026-05-08
Publication Date: 2026-07-24

AI Technical Summary

Technical Problem

Existing medical image 3D reconstruction methods struggle to adequately consider the consistency of voxel feature vector directions and spatial adjacency topology when processing multi-layer 2D slice sequences, resulting in discontinuities and suboptimal topological connectivity in the reconstructed 3D model.

Method used

An initial voxel spatial distribution matrix is constructed through multi-scale feature analysis, spatial potential field intensity parameters are calculated, an initial spatial constraint topology network is established, spatial affinity alignment and spatial interpolation field are performed across slice voxel nodes, spatial conformation optimization is performed in combination with deformation displacement field constraints, local motion trajectory and global state energy minimum state are iteratively solved, and finally global meshing encapsulation and topology connectivity verification are performed.

Benefits of technology

It improves the morphological accuracy and structural stability of 3D reconstruction of medical images, ensures the topological connectivity and spatial structural integrity of the reconstructed model, reduces image artifacts, and enhances visualization effects.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN122454050A_ABST

Patent Text Reader

Abstract

The application provides a medical image three-dimensional reconstruction method and system, and relates to the technical field of medical image processing. The method comprises the following steps: acquiring a multi-layer medical image slice sequence to be processed, performing multi-scale feature analysis on the multi-layer medical image slice sequence, and constructing an initial voxel space distribution matrix; based on the direction consistency and spatial adjacency topology of adjacent voxel feature vectors in the initial voxel space distribution matrix, calculating the spatial potential field strength parameters between each voxel node to obtain an initial spatial constraint topology network; receiving the initial spatial constraint topology network, performing spatial affinity alignment of cross-slice voxel nodes based on the spatial potential field strength parameters, constructing a voxel-level cross-slice feature alignment and spatial interpolation field, performing feature fusion and spatial position interpolation operation on the initial spatial constraint topology network, and obtaining a continuous voxel three-dimensional feature map. The application improves the three-dimensional reconstruction efficiency of medical images, reduces image artifacts, and enhances the visualization effect.

Need to check novelty before this filing date? Find Prior Art