X-ray Imaging System with AI View Name Generation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional x-ray imaging systems for breast mammography are prone to human error in image labeling and require significant human input for adjusting parameters, especially when imaging biopsy samples or detecting accessories, leading to inefficiencies and potential errors.

Innovation Solution

An x-ray imaging system equipped with an optical camera and a controller using artificial intelligence to automatically acquire image acquisition factors, generate view names, and adjust imaging parameters based on these factors, including detection of biopsy samples and accessories, thereby reducing human intervention and improving accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual inspection and labeling of x-ray images is performed by medical personnel, then labeling can be performed with human judgment, but the process is time-consuming and prone to human error

Engineering Contradiction:
Improvelabeling accuracyVSAvoidtime for manual inspection
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system enables self-service by having the x-ray imaging system automatically label its own images using an optical camera and AI subsystem, eliminating the need for medical personnel to manually inspect and label images. The system captures optical images, processes them through AI, and generates view names automatically during the imaging process.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual labeling process with an automated optical and AI-based system. The optical camera captures images of the patient's breast, the AI subsystem processes these images to identify view names, and this digital processing replaces the manual mechanical inspection and labeling performed by medical personnel.

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

2Reliability

If preconfigured selectable options with exemplary graphics are provided, then human error can be reduced, but the system still requires human input and selection

Engineering Contradiction:
Improvelabeling accuracyVSAvoidautomation of labeling
Core Design Contradiction:
ReliabilityVSExtent of automation

Solution Approach 1:

The system transitions from requiring human selection from preconfigured options to self-service automation where the AI subsystem independently analyzes optical images, determines view names, and labels images without human intervention. The system serves itself by automatically completing the labeling task that previously required human judgment.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical process of human selection from preconfigured options with an automated optical recognition and AI processing system. The optical camera captures images, the AI subsystem analyzes them to identify view names, and this digital automation replaces the human mechanical selection process.

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

3Adaptability or versatility

If human input is required to inform the machine about biopsy samples, then imaging parameters can be adjusted manually, but the process is time-consuming and error-prone

Engineering Contradiction:
Improveability to image different samplesVSAvoidtime for parameter adjustment
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system enables self-service by automatically detecting biopsy samples through the optical camera and AI subsystem. The system captures optical images, processes them to identify biopsy samples, and automatically adjusts imaging parameters without requiring human input to inform the machine about the sample type.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent applies preliminary action by having the optical camera and AI subsystem analyze images before the actual imaging process begins. The system pre-identifies the sample type (biopsy sample) and pre-adjusts imaging parameters in advance, eliminating the need for post-detection manual parameter adjustment.

Inventive Principle:
Principle #10Preliminary action

4Productivity

If the system images biopsy samples immediately after acquisition, then productivity is improved, but different imaging parameters are required that must be manually adjusted

Engineering Contradiction:
Improveimaging speedVSAvoidparameter adjustment complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system achieves self-service automation where the optical camera and AI subsystem automatically detect biopsy samples and adjust imaging parameters in real-time during immediate imaging. The system serves itself by autonomously adapting to different sample types without requiring manual parameter adjustment, enabling rapid imaging of biopsy samples immediately after acquisition.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent applies dynamics by making the imaging parameters dynamic and automatically adjustable based on real-time detection of sample types. The system continuously monitors the imaging process, detects biopsy samples through optical imaging, and dynamically adjusts parameters on the fly to optimize imaging for each specific sample type, enabling immediate imaging with appropriate parameters.

Inventive Principle:
Principle #15Dynamics

5Extent of automation

If the system is unable to detect imaging accessories, then the system remains simple, but automatic detection capability is lost

Engineering Contradiction:
Improveautomatic accessory detectionVSAvoidsystem complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The patent replaces any potential mechanical detection systems with an optical camera and AI-based recognition system. The optical camera captures images of the imaging environment, the AI subsystem processes these images to automatically detect and identify imaging accessories, and this digital processing replaces any mechanical or manual detection methods.

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

Data Source

PatentEP3669784B1System and method for acquiring an x-ray image
Publication Date: 2021.03.17 GENERAL ELECTRIC CO
  • EP3669784B1 patent drawingFigure 1
  • EP3669784B1 patent drawingFigure 2~3
  • EP3669784B1 patent drawingFigure 4

AI summary

An x-ray imaging system is provided. The system includes an x-ray emitter and an x-ray detector. The system further includes a sensor operative to acquire one or more image acquisition factors, and a controller in electronic communication with the x-ray emitter, the x-ray detector, and the sensor. The controller is operative to: acquire an x-ray image of a patient via the x-ray emitter and the x-ray detector; receive the one or more image acquisition factors from the sensor; and generate a view name of the x-ray image based at least in part on the one or more image acquisition factors.