Radiographic Image Sharpening With Local Detector Corrections

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional image processing techniques for radiographic images, such as those used in X-ray imaging, fail to account for variations in detector characteristics, leading to blurriness and artifacts that hinder accurate diagnosis and analysis, resulting in unnecessary additional imaging and patient exposure to radiation.

Innovation Solution

The use of localized digital corrections, including adaptive convolution kernels and Wiener filtering, to apply different corrections to different areas of the detector based on factors like detector position and beam angle, improving image sharpness and clarity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If conventional uniform image processing techniques are used, then the processing is simple and fast, but the image sharpness and diagnostic accuracy deteriorate due to detector variations

Engineering Contradiction:
Improveimage sharpnessVSAvoidprocessing complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent divides the detector into multiple regions and applies different processing parameters to each region. The system segments the image processing task by creating region-specific correction maps that account for local detector variations, thereby improving image sharpness while managing complexity through structured segmentation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements local quality enhancement by applying different processing parameters to different regions of the detector. Each region receives customized correction based on its specific characteristics, such as local MTF measurements and detector response variations, which improves overall image quality without requiring complete reprocessing of the entire image with uniform high complexity.

Inventive Principle:
Principle #3Local quality

2Reliability

If additional imaging procedures are performed to ensure diagnostic accuracy, then diagnostic confidence improves, but patient radiation exposure increases

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidradiation exposure
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent implements feedback mechanisms where the system measures actual detector performance (MTF, noise characteristics) and uses this information to automatically adjust processing parameters. This closed-loop approach ensures diagnostic accuracy is maintained through optimized processing rather than repeated imaging, thereby reducing patient radiation exposure while preserving reliability.

Inventive Principle:
Principle #23Feedback

3Manufacturing precision

If detector variations are not compensated, then the processing is straightforward, but image quality and diagnostic usefulness deteriorate due to blurriness and artifacts

Engineering Contradiction:
Improveimage qualityVSAvoidcorrection complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary characterization of detector variations during system setup or calibration phases. By pre-measuring MTF, noise characteristics, and response uniformity across the detector, the system prepares correction maps and processing parameters in advance, which are then applied during routine operation. This preliminary action reduces the complexity of real-time correction while maintaining high image quality.

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

Enhances image sharpness and clarity by accurately compensating for detector variations, reducing blurriness and artifacts, thereby improving diagnostic accuracy and reducing unnecessary imaging procedures.

Implementation Method 1

an intermediate layer of scintillator material to convert the incident X-ray photons into a plurality of visible light photons

Methodology Applied
Scientific EffectScintillation: Scintillation

Data Source

PatentEP4685733A1Methods and apparatus to sharpen a radiographic image
Publication Date: 2026.01.28 GE PRECISION HEALTHCARE LLC
  • EP4685733A1 patent drawingFigure 1
  • EP4685733A1 patent drawingFigure 2
  • EP4685733A1 patent drawingFigure 3

AI summary

Systems, apparatus, articles of manufacture, and methods are disclosed to sharpen a radiographic image by capturing a radiographic image with a detector receiving a beam from a source and performing a digital correction to the radiographic image to generate a digital image with increased uniformity in sharpness compared to the radiographic image.