Turbo Spin Echo MRI Artifact Removal Using Neural Reconstruction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional Turbo Spin Echo (TSE) magnetic resonance imaging protocols suffer from imperfect rephasing of spins due to refocusing pulses, leading to a combination of free induction decay and spin echo signals that result in image artifacts, which degrade image quality.

Innovation Solution

A method involving a neural network configured to filter free induction decay artifacts from TSE images by combining initial MR images with artifact images, using training data to enhance image quality, particularly in protocols with refocusing pulses less than 180° to reduce specific absorption rate (SAR).

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Object-affected harmful factors

If refocusing pulses with flip angles less than 180° are used to reduce specific absorption rate (SAR), then safety and comfort are improved, but free induction decay artifacts increase

Engineering Contradiction:

Improvespecific absorption rate (SAR)VSAvoidfree induction decay artifacts

Core Design Contradiction:

Object-affected harmful factorsVSObject-generated harmful factors

Solution Approach 1:

The patent applies this principle by using the neural network to convert the harmful free induction decay artifacts into useful information. The network learns to identify and separate artifact signals from genuine anatomical signals, effectively transforming the harmful artifacts into a tool for their own removal and improvement of image quality

Inventive Principle:

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

Solution Approach 2:

The neural network acts as an intermediary between the raw MRI data and the final image. It processes the mixed signals containing both genuine anatomical information and free induction decay artifacts, separating them through learned patterns and producing a clean artifact-free image

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If conventional TSE imaging protocols are used, then imaging speed is improved, but image quality deteriorates due to artifacts

Engineering Contradiction:

Improveimaging speedVSAvoidimage quality

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The patent replaces traditional mechanical signal processing methods with an intelligent neural network system. Instead of using conventional filtering or reconstruction techniques, the system employs a trained neural network that automatically learns and applies complex artifact removal patterns, achieving superior image quality while maintaining fast imaging speeds

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4653904A1Removal of free induction decay artifacts in turbo spin echo MRI images

Publication Date: 2025.11.26 KONINKLIJKE PHILIPS NV

Figure 1
Figure 2
Figure 3

AI summary

Disclosed herein is a method of imaging at least a part of a subject (318). The method comprises receiving (200) k-space data (122) acquired according to a fast spin echo magnetic resonance imaging protocol. The method further comprises reconstructing (202) an initial magnetic resonance image (124) from the k-space data. The method further comprises receiving (204) a free induction decay artifact image (128) in response to inputting the initial magnetic resonance image into an image processing neural network (126). The image processing neural network is configured for filtering free induction decay artifacts from fast spin echo magnetic resonance images. The method further comprises generating (206) a clinical magnetic resonance image (130), through a combination of at least a portion of the free induction decay artifact image and the initial magnetic resonance image. The method further comprises providing (208) the clinical magnetic resonance image.