Portable MRI ADC Image Correction via Function Fitting Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Portable mobile magnetic resonance imaging (MRI) systems with field strengths below 1.0T face challenges in generating accurate apparent diffusion coefficient (ADC) images due to the inability to use echo planar imaging sequences, leading to disparities with conventional fixed MRI systems, and current corrections rely heavily on subjective calibration methods resulting in low parameter accuracy.
Innovation Solution
A method involving the acquisition of ADC images using echo planar imaging sequences from portable mobile MRI systems, followed by inputting these images into a pre-constructed image correction model generated through function fitting based on magnetic resonance image sequences of different objects, allowing for the correction of grayscale values and improvement in image accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If portable mobile magnetic resonance imaging with field strength below 1.0T is used, then the device portability and flexibility are improved, but the image parameter accuracy deteriorates due to inability to use EPI sequences
Solution Approach 1:
The patent applies parameter changes by establishing a correction model that transforms the relationship between mobile MRI ADC values and fixed MRI ADC values through mathematical functions. The model uses parameters such as b-values, T1 relaxation times, and diffusion coefficients to create a mapping relationship that corrects the parameter accuracy of mobile MRI images to match fixed MRI standards.
2Device complexity
If manual calibration of cerebrospinal fluid grayscale values is used, then the correction process is simplified, but the parameter accuracy deteriorates due to subjective experience and large calibration differences
Solution Approach 1:
The patent introduces an intermediary correction model that acts as a mediator between mobile MRI and fixed MRI systems. This model uses T1-weighted images as an intermediary reference to establish anatomical structure correspondence, and employs diffusion-weighted image registration to create a mapping relationship that objectively corrects ADC values without relying on subjective manual calibration.
Solution Approach 2:
The patent implements feedback mechanisms by using the correction model to iteratively adjust and optimize the mapping between mobile and fixed MRI parameters. The model continuously refines the correction based on the comparison between corrected mobile MRI images and reference fixed MRI images, improving parameter accuracy through systematic feedback loops.
Data Source
AI summary
A method and a device for correcting magnetic resonance images are provided. The method includes: acquiring an ADC image to be corrected, which is generated by scanning a target object using an echo planar imaging sequence from a pulse sequence of a portable mobile magnetic resonance apparatus and converting; inputting the ADC image to be corrected into a pre-constructed image correction model to correct a grayscale value of tissue position of the ADC image to be corrected, where the pre-constructed image correction model is generated by function fitting based on magnetic resonance image sequences of different objects; and outputting a target image corresponding to the ADC image to be corrected. A storage medium and a terminal are also provided.