MRI Motion-Artifact Reduction via K-Space ETL Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Magnetic Resonance Imaging (MRI) scans are prone to motion-related image artifacts due to the relatively long duration of scans, leading to non-diagnostic images and increased costs.

Innovation Solution

A method that identifies motion-affected k-space echo train lengths (ETLs) and those corresponding to non-dominant poses, generates an undersampled version of the k-space data by removing these ETLs, and uses a reconstruction model to produce artifact-free images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If MRI scan duration is extended to improve image quality and coverage, then diagnostic accuracy is improved, but motion artifacts increase leading to non-diagnostic images

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidmotion artifacts

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent segments the k-space data into multiple echo train lengths (ETLs) and further identifies and segments out the motion-affected portions. By dividing the k-space acquisition into discrete ETL units, the system can selectively remove only the motion-corrupted segments while retaining usable data from other segments, thereby maintaining diagnostic accuracy while reducing motion artifact impact.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent extracts and removes motion-affected ETLs from the k-space data before image reconstruction. By identifying ETLs that contain motion artifacts and extracting only the clean, motion-free portions for reconstruction, the system eliminates the harmful motion artifacts while preserving the diagnostic information contained in the unaffected data segments.

Inventive Principle:

Principle #2Taking out (Extraction)

2Object-affected harmful factors

If MRI scan time is reduced to minimize motion artifacts, then motion artifacts are reduced, but image quality and diagnostic accuracy deteriorate

Engineering Contradiction:

Improvemotion artifactsVSAvoiddiagnostic accuracy

Core Design Contradiction:

Object-affected harmful factorsVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary processing step between data acquisition and image reconstruction. A motion detection mechanism acts as an intermediary that analyzes the acquired k-space data to identify motion-affected ETLs, then selectively removes only those portions before passing the clean data to the reconstruction algorithm. This intermediary step allows the system to use longer scan times for comprehensive coverage while still producing high-quality diagnostic images by eliminating motion artifacts.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the parameter selection during reconstruction by dynamically choosing which ETLs to include based on motion detection results. Instead of using a fixed acquisition window, the system adjusts the effective scan parameters by selecting only the motion-free ETLs for reconstruction, thereby maintaining high diagnostic accuracy even when the total acquisition time is extended.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If repeated scans are performed to obtain diagnostic images, then diagnostic accuracy is improved, but costs and loss of time increase

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidscan time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent converts the potentially harmful effect of motion during extended scans into a beneficial selection criterion. By detecting motion artifacts and using them to identify which ETLs to exclude, the system transforms the presence of motion (which would normally require repeated scans) into a useful indicator for selective data rejection. This allows a single extended scan to produce diagnostic-quality images without requiring time-consuming repeat acquisitions.

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The patent discards only the motion-affected portions of the k-space data while recovering and utilizing the motion-free portions for image reconstruction. By selectively discarding corrupted ETLs and recovering the usable data from the same acquisition session, the system avoids the need for repeated scans, thereby reducing both time loss and associated costs while maintaining diagnostic accuracy.

Inventive Principle:

Principle #34Discarding and recovering

Data Source

PatentUS12276715B2Systems and methods for motion-artifact reduction in magnetic resonance imaging

Publication Date: 2025.04.15 GE PRECISION HEALTHCARE LLC

AI summary

Systems and methods are provided for reconstructing images from motion-affected k-space data. In one example, a method comprises obtaining k-space data of a spin echo magnetic resonance imaging (MRI) exam of a subject, the k-space data comprising a plurality of echo train lengths (ETLs), with each ETL comprising a subset of lines of the k-space data. The method further comprises identifying a subset of ETLs of the plurality of ETLs of the k-space data corresponding to a dominant pose of the subject, generating an undersampled version of the k-space data, the undersampled version including only the subset of ETLs, entering the undersampled version of the k-space data as input to a reconstruction model trained to output a reconstructed image based on the undersampled version of the k-space data, and displaying the reconstructed image on a display device and/or saving the reconstructed image in memory.