Machine-Learning B0/B1 Shim Settings for Faster MRI Preparation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing magnetic resonance imaging systems require time-consuming and error-prone manual processes for determining B0-shim and B1-shim settings, which prolong the preparation time for MR imaging.
Innovation Solution
Implementing a machine-learning module to determine B0-shim and B1-shim settings from actual load parameters, eliminating the need for extensive MR data acquisition and reducing the preparation time by using actual load parameters such as patient features and RF coil information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If manual processes are used to determine B0-shim and B1-shim settings, then accuracy of shim settings can be maintained, but preparation time for MR imaging is prolonged
Solution Approach 1:
The patent replaces manual mechanical adjustment processes with an automated machine learning system. The ML module automatically determines B0-shim and B1-shim settings based on input parameters, eliminating the need for manual trial-and-error adjustment by operators. This substitution of manual mechanical operations with automated computational processing directly reduces preparation time while maintaining accuracy.
Solution Approach 2:
The system enables self-service by allowing the machine learning module to autonomously determine optimal shim settings without requiring manual intervention. The module takes input parameters (such as subject anatomy data or preliminary scan data) and automatically computes the appropriate shim settings, making the system self-sufficient in the shim determination process and eliminating time-consuming manual operations.
2Measurement precision
If extensive MR data acquisition is performed to determine accurate shim settings, then precision of shim determination is improved, but preparation time increases
Solution Approach 1:
The patent applies partial action by using a machine learning module that requires only limited input data (such as basic anatomical parameters or preliminary low-resolution scans) rather than extensive MR data acquisition. The ML algorithm processes this partial information to determine accurate shim settings, achieving high precision without the need for comprehensive data collection, thereby reducing preparation time while maintaining accuracy.
Solution Approach 2:
The system performs preliminary action by using pre-trained machine learning models that have already learned optimal shim determination patterns from extensive training data. During actual MR examinations, the pre-trained model quickly processes minimal input data to provide accurate shim settings, eliminating the need to perform extensive data acquisition and processing during the examination preparation phase.
3Productivity
If machine learning module is implemented to determine shim settings, then preparation time is reduced, but system complexity increases
Solution Approach 1:
The patent applies universality by designing the machine learning module to handle multiple functions within a single integrated system. The ML module determines both B0-shim and B1-shim settings, processes different types of input data (anatomical data, preliminary scans), and adapts to various examination protocols. This multi-functionality consolidates what would otherwise require separate systems into one unified module, reducing overall system complexity while maintaining high productivity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Accurately determines shim settings without extensive MR data acquisition, significantly reducing the preparation time and operator effort, thereby enhancing the efficiency of the MR examination workflow.
Implementation Method 1
a main magnet for applying a uniform static magnetic field (B0)
Implementation Method 2
an active shim system to apply shim magnetic fields to correct for inhomogeneities of the static magnetic field
Implementation Method 3
a radio frequency (RF) transmit system configured to emit an RF B1+-field
Data Source
AI summary
A magnetic resonance examination system comprising a main magnet for applying a uniform static magnetic field. An active shim system applies shim magnetic fields to correct for inhomogeneities of the static magnetic field. A shim driver system activates the active shim system on the basis of B0-shim settings. A trained machine-learning module is trained to return the B0-shim settings from one or more actual load parameters. The magnetic resonance examination system may further comprise an RF transmit system with RF antenna elements and an RF driver system to activate the RF antenna elements for applying a (B1) radio frequency field having a predetermined spatial distribution. An RF shim system to control the RF driver system to apply shim radio frequency fields to correct for deviation of the radio frequency field's spatial distribution from the predetermined spatial distribution on the basis of RF-shim settings. A trained machine-learning module trained to return the RF-shim settings from one or more actual load parameters.