Dual-Energy X-Ray Material Decomposition Pipeline

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for material decomposition in dual-energy X-ray imaging struggle to achieve accurate and high-quality results, particularly for quantitative analysis, due to limitations in image quality and the potential for overfitting in machine-trained algorithms.

Innovation Solution

The method involves preprocessing X-ray image datasets using a filter module and/or an artifact-reduction module, followed by material decomposition using linear algebra methods and a trained function. This approach enhances the quality of material-specific image data, enabling improved quantitative analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Illumination intensity

If machine-trained algorithms are used for improving image quality, then visual perception quality is improved, but quantitative analysis suitability deteriorates due to overfitting

Engineering Contradiction:

Improveimage qualityVSAvoidquantitative analysis suitability

Core Design Contradiction:

Illumination intensityVSMeasurement precision

Solution Approach 1:

The patent segments the image processing pipeline into distinct functional modules: a trained function module for visual quality enhancement and a decomposition module for quantitative analysis. This segmentation allows each module to specialize in its respective task without interfering with the other, preventing overfitting from degrading quantitative analysis capability

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary decomposition module that processes the output of the trained function. This intermediary acts as a buffer that converts visually enhanced images into material-specific quantitative data, ensuring that the visual enhancement does not directly compromise the accuracy of quantitative measurements

Inventive Principle:

Principle #24Intermediary (Mediator)

2Illumination intensity

If heuristic or empirical methods are used to improve image quality, then visual perception is improved, but quantitative analysis capability remains insufficient

Engineering Contradiction:

Improveimage qualityVSAvoidquantitative analysis capability

Core Design Contradiction:

Illumination intensityVSMeasurement precision

Solution Approach 1:

The patent replaces traditional heuristic/empirical image processing methods with a trained function based on machine learning. This substitution enables the system to learn optimal enhancement parameters from data, improving visual quality while maintaining the ability to perform accurate quantitative analysis through the subsequent decomposition step

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Ease of operation

If material decomposition is performed with low signal-to-noise ratio and scatter effects, then imaging is possible, but image quality and quantitative analysis accuracy deteriorate

Engineering Contradiction:

Improveimaging capabilityVSAvoidquantitative analysis accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent applies preliminary filtering and artifact reduction to the input images before they enter the decomposition module. This preliminary action removes noise and scatter effects early in the processing chain, preventing them from degrading the quantitative analysis accuracy while still allowing imaging to proceed under challenging conditions

Inventive Principle:

Principle #10Preliminary action

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 proposed method significantly improves the quality of material decomposition, facilitating more accurate quantitative material analysis, even with non-optimum image quality, such as in CBCT applications.

Implementation Method 1

different X-ray image data is generated (e.g., two different X-ray projection images or two different three-dimensional volume reconstructions, using different X-ray energy spectra)

Methodology Applied

Scientific EffectX-ray radiation: X-Ray

Implementation Method 2

the attenuation coefficients of different materials (e.g., cerebrospinal fluid (CSF), blood, and X-ray selective contrast agents, such as contrast agents containing iodine or barium) vary by different degrees with varying radiation energies

Methodology Applied

Scientific EffectAttenuation: Absorption (EM radiation)

Data Source

PatentUS20250172511A1Material decomposition in dual-energy x-ray imaging

Publication Date: 2025.05.29 SIEMENS HEALTHINEERS AG

AI summary

In a computer-implemented method for material decomposition in dual-energy X-ray imaging, a first X-ray image dataset corresponding to a first X-ray energy spectrum, and a second X-ray image dataset corresponding to a second X-ray energy spectrum are obtained. At least one material-specific image dataset is generated by applying a decomposition module that contains a first sequence of processing steps or machine learning function to input data that depends on the first X-ray image dataset and the second X-ray image dataset. Before applying the decomposition module, a filter module and/or an artifact-reduction module is applied to the input data.