MRI Organ Segmentation by Localized Slice-Region Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for segmenting the positions and sizes of abdominal organs in magnetic resonance imaging (MRI) are time-consuming and lack consistency and accuracy, making automated scan planning challenging, especially for asymmetric structures like those in the abdomen.
Innovation Solution
An image segmentation apparatus for MRI that includes an obtaining unit for localizer images, a temporary localization unit for identifying segments containing organs, and a segmentation unit for performing image segmentation processes on these segments, enabling prompt and accurate segmentation and localization of organs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional techniques are used for segmenting abdominal organs, then the segmentation can be performed, but the process takes a long period of time
Solution Approach 1:
The patent divides the abdominal region into multiple segments along the layer direction (e.g., upper abdomen, middle abdomen, lower abdomen) and processes each segment independently. This segmentation strategy reduces the computational complexity and processing time compared to analyzing the entire abdomen at once, while maintaining segmentation accuracy for each regional organ.
Solution Approach 2:
The patent performs preliminary localization to identify which segments contain organs before performing the full segmentation process. By pre-determining the relevant segments through localization algorithms, the system avoids unnecessary processing of empty segments, thereby reducing overall processing time while maintaining completeness of organ detection.
2Extent of automation
If manual scan planning is performed by technologists, then the scan can be customized, but the process takes time and lacks consistency
Solution Approach 1:
The system performs self-service through automated localization and segmentation processes that run without manual intervention. The automated algorithms independently identify organ positions, determine scan parameters, and generate scan planning protocols, eliminating the need for technologist expertise and ensuring consistent, reproducible results across different patients and operators.
Solution Approach 2:
The patent automatically determines scan parameters such as field of view, slice thickness, and positioning based on the segmented organ information. By changing from manual parameter selection to automated parameter derivation from segmentation results, the system achieves both speed and consistency in scan planning while adapting to individual patient anatomy.
3Measurement precision
If the lower edge of the rib is used to determine liver position, then the localization can be simplified, but the accuracy of liver position expression is poor
Solution Approach 1:
The patent extracts and focuses on the actual organ boundaries (liver edges) rather than using surrogate anatomical landmarks (rib edges). By directly segmenting and localizing the organ of interest, the system achieves accurate position measurement without relying on indirect proxies that introduce measurement errors.
Solution Approach 2:
The patent replaces manual or simplified geometric localization methods with automated image processing and segmentation algorithms. This substitution enables precise detection of organ boundaries through computational methods, achieving high measurement precision while maintaining algorithmic efficiency.
4Measurement precision
If comprehensive organ information is collected for multi-organ scan planning, then the scan planning becomes more accurate, but the processing time increases
Solution Approach 1:
The patent segments the abdominal region into multiple layers and processes organ information collection systematically across these segments. By organizing the comprehensive data collection into a structured segmented approach, the system maintains accuracy in capturing complete organ information while improving processing efficiency through systematic iteration.
Solution Approach 2:
The patent implements continuous processing where localization and segmentation operations run seamlessly through all segments without interruption. The system maintains continuous scanning and processing of organ information across all abdominal layers, ensuring complete data collection while minimizing idle time and maximizing processing throughput.
Data Source
AI summary
An image segmentation apparatus for magnetic resonance imaging according to an embodiment includes processing circuitry. The processing circuitry is configured to obtain a localizer image of an organ, the localizer image being three-dimensional or being in a plurality of layers and two-dimensional. The processing circuitry is configured to temporarily localize, on a basis of the localizer image, a segment in which the organ is present in terms of the layer direction of a plurality of slices included in the localizer image. The processing circuitry is configured to obtain a segmentation result of the organ, by performing an image segmentation process on the localizer image positioned inside the segment in which the organ is present.