MR Localizer Shape Completion for Patient Burn Risk Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Magnetic Resonance (MR) imaging poses a risk of patient burns due to excessive radio-frequency power application when body parts, such as arms, are too close to the MRI bore, and current methods for preventing burns are either uncomfortable, time-consuming, or inaccurate.

Innovation Solution

Utilizing MR localizer imaging to estimate patient shape and infer missing body parts, employing machine-learned shape completion models to predict burn risk and generate warnings or adjust scan settings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If SAR is set to minimum to prevent MR burn injuries, then patient safety is improved, but examination time increases

Engineering Contradiction:

Improvepatient safetyVSAvoidexamination time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary assessment of patient body shape and arm position using localizer scan images before the actual MR examination. By inferring the position of body parts that may not be visible in the localizer scan, the system predicts burn risk in advance, allowing safe SAR settings to be determined before the examination begins, thus avoiding time loss during the actual scan.

Inventive Principle:

Principle #10Preliminary action

2Object-affected harmful factors

If overhead camera is used to estimate patient body shape, then burn risk assessment is possible, but additional setup and registration are required and accuracy decreases due to body parts being covered

Engineering Contradiction:

Improveburn risk assessmentVSAvoidsetup and registration

Core Design Contradiction:

Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The system uses the localizer scan images, which are already part of the standard MR examination protocol, as a copy or representation of the patient's body shape. Instead of requiring separate camera setup and registration, the system processes the existing localizer scan data to infer body part positions, thereby eliminating additional hardware setup while maintaining assessment capability.

Inventive Principle:

Principle #26Copying

3Loss of information

If localizer scan field of view includes all body parts, then complete body shape information is obtained, but scan time increases

Engineering Contradiction:

Improvebody shape informationVSAvoidscan time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system introduces an image processing and inference algorithm as an intermediary between the localizer scan and burn risk assessment. This intermediary component analyzes the limited field of view from the localizer scan, infers the positions of body parts outside the visible area, and predicts burn risk without requiring the localizer scan to physically include all body parts, thus maintaining fast scanning while obtaining complete information.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20260047772A1Body shape estimation from localizer scan in magnetic resonance medical imaging

Publication Date: 2026.02.19 SIEMENS HEALTHINEERS AG

AI summary

In magnetic resonance imaging, shape estimation is used to limit patient burns. A localizer image or scout scan is used to determine some of the patient shape and corresponding position. A missing part, such as the arm not in the scout scan field of view, is inferred from the localizer image. The position of the inferred body part is used to predict the risk of burn, allowing generation of a warning to reposition the patient and/or change the scan settings.