Radiological Imaging AI for Re-Acquisition Decision Support

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing radiological imaging systems lack user-friendly and accurate methods for determining the need for additional imaging, often requiring technician intervention and causing time and financial burdens on patients.

Innovation Solution

A radiological imaging system using a trained model that analyzes radiological images to automatically suggest the need for additional imaging, incorporating learning data with annotation information for reasons behind the need, and utilizing AI to enhance decision-making.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a technician manually checks radiological images and decides on additional imaging, then the decision can be made with professional judgment, but the process is time-consuming and requires experienced personnel

Engineering Contradiction:

Improveaccuracy of additional imaging decisionVSAvoidtime for decision-making and additional imaging

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The radiological imaging system performs self-evaluation by automatically analyzing the first radiological image and determining whether additional imaging is needed, eliminating the need for manual technician review. The system uses machine learning models to autonomously assess image quality and diagnose whether re-acquisition is necessary, thereby reducing dependency on human operators while maintaining decision accuracy.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual inspection process by technicians is replaced with an automated image analysis system using machine learning algorithms. The system substitutes human visual inspection and decision-making with computational analysis that processes radiological images to determine the need for additional imaging, significantly reducing time loss while maintaining or improving decision reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If additional imaging is performed to confirm suspected lesions, then diagnostic accuracy is improved, but the patient incurs time and financial burdens

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidtime burden on patient

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of the first radiological image to determine whether additional imaging is actually needed before the patient undergoes re-acquisition. By evaluating image quality and detecting potential lesions in advance, the system avoids unnecessary additional imaging, thereby reducing patient time and financial burden while maintaining diagnostic accuracy when it is truly required.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system provides feedback to technicians and patients about the necessity of additional imaging based on automated analysis results. This feedback mechanism includes explaining why additional imaging is or is not needed, enabling informed decision-making and reducing unnecessary patient exposure to additional imaging procedures, thus lowering time and financial burdens while preserving diagnostic accuracy when needed.

Inventive Principle:

Principle #23Feedback

3Reliability

If AI is used to automatically suggest additional imaging, then inexperienced technicians can improve their detection ability, but the system complexity increases

Engineering Contradiction:

Improvedetection ability of technicianVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The machine learning model serves as an intermediary between the radiological image and the technician's decision-making process. The model analyzes images and provides suggestions to technicians, enhancing their detection ability without requiring them to directly interpret complex image features. This intermediary approach improves reliability while keeping the system manageable by delegating complex analysis to the AI component.

Inventive Principle:

Principle #24Intermediary (Mediator)

4Ease of operation

If manual inspection and decision-making processes are used, then the system is simpler to implement, but it requires experienced personnel and increases processing time

Engineering Contradiction:

Improveease of use for technicianVSAvoidtime for image review and decision

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system performs self-evaluation of radiological images automatically without requiring manual inspection by technicians. The machine learning model autonomously analyzes images, determines image quality, and decides whether additional imaging is needed, thereby eliminating time loss associated with manual review while maintaining ease of operation through automated workflows that require minimal human intervention.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20250281141A1Radiological imaging system having storing medium for storing trained model and method for producing trained model

Publication Date: 2025.09.11 GE PRECISION HEALTHCARE LLC

AI summary

In one embodiment, a radiological imaging system is provided, the system including a storing medium having a trained model using, as learning data, a first radiological image obtained using a first condition and a second radiological image obtained by additional imaging using a second condition set on the basis of the first radiological image. The learning data of the trained model has, as annotation information, at least a reason for additional imaging. The trained model outputs, when a third radiological image is input, a need for additional imaging and a reason why the additional imaging is necessary as a re-acquisition factor.