Hierarchical Tomographic Reconstruction via Intermediate Line Integrals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional tomographic reconstruction techniques face challenges in achieving a balance between computational efficiency, patient dose, scanning speed, and image quality, often resulting in suboptimal image reconstruction and increased computational complexity.
Innovation Solution
A hierarchical tomographic reconstruction method that processes scan data through a hierarchy of reconstruction steps, including intermediate line integral representations, utilizing deep learning techniques to generate voxel values of a reconstructed image, thereby decomposing the large-scale inverse problem into smaller-scale tasks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional tomographic reconstruction techniques are used, then image reconstruction can be performed, but computational complexity increases and reconstruction efficiency decreases
Solution Approach 1:
The patent divides the reconstruction process into multiple hierarchical stages: (1) generating intermediate line integral representations from projection data, (2) generating voxel values from the intermediate representations. This segmentation transforms a single complex reconstruction problem into smaller, more manageable sub-problems that can be solved more efficiently at each stage.
Solution Approach 2:
The patent introduces intermediate line integral representations as a mediator between the original projection data and the final voxel values. These intermediate representations serve as a bridge that simplifies the reconstruction process by breaking down the direct inversion problem into sequential steps, reducing overall computational complexity.
2Manufacturing precision
If higher image quality is achieved through conventional reconstruction, then diagnostic accuracy improves, but patient dose increases
Solution Approach 1:
The patent changes the representation parameters by working with intermediate line integral representations instead of directly reconstructing from projection data. This parameter transformation allows for more efficient computation and better image quality at lower doses by preserving statistical properties through the hierarchical processing stages.
3Productivity
If scanning speed is increased to improve productivity, then patient throughput increases, but image quality deteriorates
Solution Approach 1:
The patent performs preliminary processing by generating intermediate line integral representations from the projection data before final reconstruction. This preliminary action prepares the data in a form that facilitates faster and more accurate reconstruction, allowing for quicker scanning speeds without compromising image quality.
Data Source
AI summary
The present disclosure relates to the use of a hierarchical tomographic reconstruction approach that employs data representations in intermediate steps are between a full line integral and a voxel (e.g., an intermediate line integral). Each of the steps is progressively more local in nature and therefore has computational advantages and is also amenable to a deep learning solution using trained neural networks. The proposed hierarchical structure provides a mechanism to divide a large-scale inverse problem into a series of smaller-scale problems.