Augmented Reality Detector Positioning for Mobile X-Ray Imaging

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In mobile X-ray imaging systems, the manual positioning of portable detectors relative to the X-ray source and patient can lead to inadequate image quality and increased retakes due to human error and lack of precise geometric alignment, especially in three-dimensional positioning.

Innovation Solution

Integration of augmented reality and machine learning-based anatomical atlas registration, using cameras and sensors to determine relative positions and orientations, generating a virtual fluoroscopic image for alignment, and updating it in real-time to facilitate accurate positioning of the detector and patient relative to the X-ray source.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If manual positioning of portable detector is used, then device complexity is reduced, but positioning precision deteriorates

Engineering Contradiction:
Improvedetector positioning systemVSAvoiddetector positioning accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces manual mechanical positioning with an automated computer vision system. Cameras capture images of the patient and detector, and software automatically calculates the detector's position and orientation relative to the patient anatomy, eliminating the need for manual mechanical alignment while achieving precise positioning.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a virtual copy or representation of the patient's anatomy through image processing and registration. By generating a digital model that mirrors the physical patient geometry, the system can simulate and visualize the detector's projected area and alignment without physical trial-and-error positioning.

Inventive Principle:
Principle #26Copying

2Ease of operation

If manual positioning is used, then operation simplicity is maintained, but image quality deteriorates

Engineering Contradiction:
Improvedetector positioning operationVSAvoidimage quality
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The system enables self-service positioning where the computer vision algorithm automatically determines the optimal detector position and orientation based on captured images. The technology performs the positioning task itself without requiring operator skill or judgment, making complex precision positioning as easy as pressing a button while ensuring consistent high-quality images.

Inventive Principle:
Principle #25Self-service

3Loss of time

If manual positioning estimation is used, then setup time is reduced, but positioning accuracy deteriorates

Engineering Contradiction:
Improvepositioning setup timeVSAvoidanatomical alignment precision
Core Design Contradiction:
Loss of timeVSMeasurement precision

Solution Approach 1:

The patent performs preliminary actions by capturing patient images and pre-calculating the detector's projected area and optimal positioning before the actual imaging procedure. The system prepares the virtual alignment model in advance, so when positioning is needed, the information is already available, eliminating time-consuming trial-and-error adjustments while ensuring accurate anatomical alignment.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3453330B1Virtual positioning image for use in imaging
Publication Date: 2024.01.03 GENERAL ELECTRIC CO
  • EP3453330B1 patent drawingFigure 1
  • EP3453330B1 patent drawingFigure 2
  • EP3453330B1 patent drawingFigure 3

AI summary

The present approach relates to the use of augmented or enhanced reality to facilitate positioning of one or more of a patient 20, X-ray source 16, or detector 22 during an image acquisition. In certain implementations, sensors 102 and/or cameras provide quantitative information about the position of system components and the patient 20, which may be used to generate a positioning image 168 based upon reference to an anatomic atlas.