Method, device, equipment and medium for removing metal artifacts in CBCT images

By using dual-energy CBCT equipment and substrate decomposition technology, metal artifacts in CBCT images can be accurately located and removed, solving the problem of low segmentation accuracy in metal regions and improving image clarity and accuracy.

CN121527210BActive Publication Date: 2026-05-29BEIJING GREAT ROBOTICS TECH LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING GREAT ROBOTICS TECH LTD
Filing Date
2025-11-13
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

In the process of removing metal artifacts in CBCT images, the existing technology has insufficient segmentation accuracy of the metal region, resulting in residual artifact stripes that cannot clearly show the details of normal tissue around the metal, thus affecting clinical diagnosis.

Method used

High- and low-energy projection data are acquired using a dual-energy CBCT device. The projection of the metal matrix material is obtained through matrix material decomposition. Combined with back projection and 3D reconstruction, the boundary of the metal region is accurately located and stitched with the non-metal region to remove artifacts.

Benefits of technology

It effectively eliminates metal artifacts, clearly presents the fine tissues around the metal, and meets the requirements of clinical diagnosis for image detail.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121527210B_ABST
    Figure CN121527210B_ABST
Patent Text Reader

Abstract

The application provides a method, device, equipment and medium for removing metal artifacts in a CBCT image. The method comprises: scanning a target region by a dual-energy CBCT device to obtain high-energy and low-energy projections of the target region; performing base material decomposition on the high-energy and low-energy projections to obtain metal base material projections and non-metal base material projections; performing contour segmentation on the metal base material projections to extract the two-dimensional boundary of a metal region and generate a binary metal projection; back-projecting the binary metal projection to a three-dimensional space to determine the three-dimensional boundary of the metal region; cutting a three-dimensional CBCT image based on the three-dimensional boundary to obtain a three-dimensional metal region image; determining a non-metal projection based on the high-energy projection data and the binary metal projection, and performing three-dimensional reconstruction on the non-metal projection to obtain a three-dimensional non-metal region image; and splicing the three-dimensional metal region image and the three-dimensional non-metal region image according to spatial positions to obtain a three-dimensional CBCT image with metal artifacts removed.
Need to check novelty before this filing date? Find Prior Art