Tomographic Image Reconstruction Using Focus Functions to Reduce Artifacts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current tomographic imaging methods, such as CT and CBCT, are costly, large, and expose patients to high x-ray doses, while tomosynthesis provides lower x-ray dosage but suffers from image artifacts and spatial instability, making it difficult to obtain high-quality diagnostic images, especially in dense oral environments.
Innovation Solution
A method and system for identifying high-focus tomographic images within a dataset by processing a plurality of projection images to reconstruct tomosynthesis image slices, allowing for the generation of clinical information and reducing image artifacts through the use of a processor and memory that specify a region of interest and apply focus functions to enhance image clarity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If CT or CBCT machines are used to acquire three-dimensional data, then depth information and image quality are improved, but cost of ownership, device size, and x-ray dosage increase
Solution Approach 1:
The patent segments the three-dimensional imaging task into multiple two-dimensional projection images taken at different angles, which are then reconstructed into tomographic slices. This segmentation approach allows obtaining depth information without requiring a full CT or CBCT system, thereby reducing x-ray dosage while maintaining diagnostic capability.
Solution Approach 2:
The patent transitions from two-dimensional projection imaging to three-dimensional tomographic imaging by adding the angular dimension. Multiple projections taken at different angles are reconstructed into depth-resolved slices, enabling depth information acquisition with lower x-ray dosage compared to traditional CT or CBCT.
2Productivity
If tomosynthesis is used to reduce x-ray dosage and acquisition time, then cost and speed are improved, but image artifacts and spatial instability increase
Solution Approach 1:
The patent employs feedback mechanisms through image processing algorithms that analyze the reconstructed tomographic slices to identify and correct artifacts. The system uses focus metrics and artifact detection to iteratively improve image quality, ensuring diagnostic reliability while maintaining the speed advantages of tomosynthesis.
Solution Approach 2:
The patent changes processing parameters such as reconstruction algorithms, filtering techniques, and focus metrics to optimize image quality. By adjusting these parameters, the system reduces artifacts and spatial instability inherent in tomosynthesis while preserving the benefits of rapid acquisition and low x-ray dosage.
3Measurement precision
If multiple tomographic image slices are reconstructed for diagnosis, then depth information is improved, but time to evaluate images and difficulty of localization increase
Solution Approach 1:
The patent extracts and highlights only the most diagnostically relevant features and regions from the multiple tomographic slices. By taking out and emphasizing critical information, the system reduces the time required for clinicians to evaluate images while preserving depth information, as unnecessary slices and features are filtered out.
Solution Approach 2:
The patent creates simplified copies or representations of the three-dimensional data, such as maximum intensity projections or annotated two-dimensional views, that preserve depth information in a more easily evaluable format. This copying approach allows clinicians to quickly assess depth relationships without manually reviewing numerous slices.
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
The system enhances image focus and reduces artifacts, providing clinically relevant information with lower x-ray exposure and faster image acquisition, suitable for chair-side use with improved resolution and cost-effectiveness compared to traditional methods.
Implementation Method 1
Tomosynthesis is an emerging imaging modality that provides three-dimensional information about a patient in the form of tomographic image slices reconstructed from images taken of the patient with an x-ray source from multiple perspectives
Implementation Method 2
X-ray radiography can be performed by positioning an x-ray source on one side of an object (e.g., a patient or a portion thereof) and causing the x-ray source to emit x-rays through the object
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
A method, system and computer readable storage media for segmenting individual intra-oral measurements and registering said individual intraoral measurements to eliminate or reduce registration errors. An operator may use a dental camera to scan teeth and a trained deep neural network may automatically detect portions of the input images that can cause registration errors and reduce or eliminate the effect of these sources of registration errors.