AI Sinogram Metal Detection for X-Ray Dental Tomography Artefact Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for metal artefact reduction in x-ray dental volume tomography are unreliable and time-consuming, particularly when metal objects are outside the reconstructed volume, leading to incomplete correction of artifacts and increased processing load.
Innovation Solution
A method utilizing trained artificial intelligence algorithms to detect metal objects directly from two-dimensional x-ray images or sinograms, generating 2D/3D masks to correct and reconstruct three-dimensional tomographic images, reducing the need for initial 3D image analysis and improving detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional metal artifact reduction method is used, then metal artifacts can be reduced, but the process is time-consuming and unreliable when metal objects are outside the reconstructed volume
Solution Approach 1:
The patent applies preliminary action by detecting metal objects in the sinogram domain before the actual tomographic reconstruction. The sinogram is analyzed to identify metal object positions and orientations, and this information is stored as metadata before reconstruction. This preliminary detection avoids the need for time-consuming post-reconstruction artifact correction, directly resolving the contradiction between reliability and processing time.
Solution Approach 2:
The patent transitions from conventional 3D image-based metal detection to 2D sinogram-based detection. By analyzing the sinogram (a 2D representation of projection data) instead of reconstructing and analyzing 3D images, the system achieves faster and more reliable metal object identification. This dimensional change enables direct detection of metal objects outside the reconstructed volume without requiring full 3D reconstruction.
2Use of energy by moving object
If only a small volume of patient jaw is reconstructed, then radiation dose is reduced, but metal artifacts from objects outside the volume cannot be corrected
Solution Approach 1:
The system performs preliminary metal object detection in the sinogram domain before reconstruction, identifying all metal objects in the entire field of view regardless of whether they fall within the final reconstructed volume. This preliminary detection enables the system to correct artifacts from external metal objects while maintaining the benefit of restricted reconstruction volume and reduced radiation dose.
Solution Approach 2:
The sinogram serves as an intermediary data structure that bridges the gap between the full patient jaw data and the limited reconstructed volume. By analyzing the sinogram (which contains projection data from all angles) before reconstruction, the system can identify metal objects outside the reconstruction volume and use this information to correct artifacts in the final image, effectively mediating between limited scan coverage and comprehensive artifact correction.
3Productivity
If classical image processing methods are used to detect metal objects, then detection can be performed on 2D images, but dense structures like bones are erroneously recognized as metal objects
Solution Approach 1:
The patent moves metal object detection from the 2D image domain to the 2D sinogram domain. In the sinogram, metal objects produce characteristic patterns that are distinct from bone structures, enabling accurate differentiation. This dimensional transition to the sinogram space maintains detection efficiency while dramatically improving accuracy by avoiding the confusion between dense bone structures and metal objects that plagues 2D image-based methods.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances the speed and reliability of metal artefact reduction, ensuring accurate detection of metallic objects outside the reconstructed volume, and improving tomographic image quality independently of the volume size, with continuous training for enhanced performance.
Implementation Method 1
a first step of obtaining two-dimensional x-ray images or a sinogram of at least part of a patient jaw, acquired through relatively rotating an x-ray source and a detector around the patient jaw
Data Source
AI summary
The present invention relates to a method of metal artefact reduction in x-ray dental volume tomography, the method comprising: a step (S1) of obtaining two-dimensional x-ray images (1) or a sinogram (2) of at least part (v) of a patient jaw (3a), acquired through relatively rotating an x-ray source (4) and a detector (5) around the patient jaw (3a); the method being characterized by further comprising: a step (S2) of detecting metal objects (6) in the two-dimensional x-ray images (1) or the sinogram (2) by using at least a trained artificial intelligence algorithm to generate 2D masks (7) which represent the metal objects (6) in the two-dimensional x-ray images (1) or 3D masks which represent the metal objects (6) in the sinogram (2), respectively; and a step (S4;S5) of reconstructing a three dimensional tomographic image (8) respectively based on two-dimensional x-ray images (1) or the sinogram (2) and the 2D masks (7) or the 3D masks as generated.