Subject-Specific Magnetic Susceptibility Map Generation for MR Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to provide a fast and detailed subject-specific magnetic susceptibility distribution map, leading to partial compensation of demagnetization fields and significant image degradation, especially in MR imaging sequences sensitive to off-resonances.
Innovation Solution
A computer-implemented method using a trained artificial neural network to segment MR images into bone, air, and soft tissue types, assigning predetermined susceptibility values to generate a subject-specific magnetic susceptibility map, which is then used to estimate the demagnetization field and improve MR image quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional shimming systems are used to compensate for demagnetization fields, then the magnetic field homogeneity is improved to some extent, but the compensation is only partial and cannot dynamically adapt to subject motion
Solution Approach 1:
The patent implements dynamic adaptation by continuously tracking subject motion and updating the susceptibility map in real-time. The system uses motion detection algorithms to monitor changes in subject position and orientation during the MRI scan, and dynamically adjusts the demagnetization field compensation accordingly. This allows the system to adapt to subject motion that occurs during the imaging process, maintaining magnetic field homogeneity without requiring manual re-shimming.
Solution Approach 2:
The patent employs feedback mechanisms by measuring the actual magnetic field deviations during the MRI scan and comparing them with the predicted demagnetization fields from the susceptibility map. The system uses this feedback information to refine and update the susceptibility map, improving the accuracy of demagnetization field compensation iteratively throughout the imaging process.
2Measurement precision
If detailed subject-specific susceptibility maps are generated, then the accuracy of demagnetization field compensation is improved, but the computational time and complexity increase
Solution Approach 1:
The patent segments the complex task of generating a detailed susceptibility map into multiple simpler steps. First, it uses fast imaging sequences to acquire initial anatomical information. Then, it applies automated segmentation algorithms to identify and classify different tissue types (bone, air, soft tissue) based on their characteristic signal patterns. Finally, it assigns predetermined susceptibility values to each tissue category. This segmentation approach maintains high accuracy while significantly reducing computational complexity compared to generating fully subject-specific maps from scratch.
Solution Approach 2:
The patent performs preliminary actions by pre-calculating and storing susceptibility values for common tissue types (bone, air, soft tissue) before the actual imaging process. These pre-determined values are then directly assigned during image processing, avoiding the need for time-consuming real-time calculation of susceptibility distributions. This preliminary preparation significantly accelerates the overall processing time while maintaining measurement precision.
3Manufacturing precision
If MR imaging sequences sensitive to off-resonances are used, then the image contrast and detail are improved, but the impact of demagnetization field distortions increases
Solution Approach 1:
The patent applies preliminary anti-action by calculating and compensating for demagnetization field distortions before acquiring the MR images. The system generates a susceptibility map that predicts the demagnetization field distribution, and uses this information to pre-correct the imaging parameters and reconstruction algorithms. This preliminary compensation prevents distortions from degrading image quality rather than attempting to correct them after they occur, maintaining high contrast and detail in sensitive sequences like gradient-echo EPI.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
The invention relates to a method for generating a subject-specific map (20) of a tissue property, in particular the magnetic susceptibility, of a region of interest within a subject, the method comprising the steps of receiving an MR image (2) of the region of interest; feeding the MR image (2) as input into at least one trained neural network (4, 6), wherein the output of the neural network (4, 6) is an output image (8, 10) having improved contrast between bone and air; segmenting (12) the output image (8, 10) into air and at least two types of tissue, namely at least bone and at least one type of soft tissue, to obtain a segmented image; and assigning (14) pre-determined values (16) for the tissue property to each category of tissue and air in the segmented image to obtain the subject-specific map (20) of the tissue property.