MRI Scan Planning Using 3D Scout Reconstruction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for generating scan plans in whole-body magnetic resonance imaging are time-consuming and labor-intensive, particularly in determining the start and end positions of scans and mid-axis lines, due to reliance on single slice images for scout scans, leading to inaccurate positioning of landmarks.
Innovation Solution
A magnetic resonance imaging support method that utilizes multi-planar reconstruction and object detection algorithms to generate scan plans based on three-dimensional scout images in axial, sagittal, and coronal planes, using neural networks to detect key positions such as head top, knee center, and spine, reducing computation by using only a fraction of whole-body slice images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single slice image is used as a scout image for generating scan plans, then the scan plan generation process is simpler and faster, but the positioning accuracy of landmarks becomes inaccurate leading to inappropriate scan plans
Solution Approach 1:
The patent transitions from using a single 2D slice image to using multiple 2D slice images at different positions that can be reconstructed into 3D volumetric data. This dimensional expansion allows landmarks to be positioned accurately in three-dimensional space rather than being constrained to a single plane, thereby improving positioning accuracy while the automated processing maintains efficiency.
Solution Approach 2:
The system performs preliminary processing of multiple slice images to generate 3D volumetric data and automatically detect landmarks before final scan plan generation. This preliminary action of pre-processing and landmark detection from multiple images ensures accurate positioning is established beforehand, making the subsequent scan plan generation more reliable without requiring manual intervention.
2Productivity
If manual specification of start position, end position, and mid-axis lines is performed based on whole-body scout images, then scan plan accuracy can be maximized, but the process becomes time consuming and labor intensive
Solution Approach 1:
The system enables self-service by implementing automated algorithms that independently perform landmark detection, start and end position determination, and mid-axis line calculation based on the 3D volumetric data from multiple slice images. This self-service automation eliminates the need for manual operator intervention in these time-consuming tasks while maintaining high accuracy in scan plan generation.
Solution Approach 2:
The patent replaces the mechanical manual process of visually inspecting images and manually marking landmarks with an automated computer vision system that uses image processing algorithms. This substitution of mechanical human operation with automated computational methods dramatically reduces the time required for scan plan generation while maintaining or improving accuracy.
3Measurement precision
If multiple slice images are processed to generate 3D volumetric data for accurate landmark detection, then positioning precision improves, but computational load increases
Solution Approach 1:
The system extracts only the essential information needed for scan plan generation from the multiple slice images, such as key landmark positions and anatomical features, rather than processing all image data in full detail. This extraction of critical information maintains positioning accuracy while significantly reducing the computational energy required compared to comprehensive processing of all image pixels and features.
Data Source
AI summary
A magnetic resonance imaging support method according to an embodiment includes an acquisition step, a multi-planar reconstruction step, a first determination step, and a second determination step. The acquisition step acquires, by performing a scout scan on a subject, a plurality of first slice images corresponding to different slice positions, the plurality of first slice images corresponding to either sagittal planes or coronal planes. The multi-planar reconstruction step generates a second slice image corresponding to the axial plane by performing multi-planar reconstruction based on the plurality of first slice images. The first determination step determines a position corresponding to a specific part of the subject based on the second slice image. The second determination step determines a range to be scanned in a main scan based on the plurality of first slice images at the position determined by the first determination step.