Medical Image Segmentation via Registration and Preliminary Action
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical image recording techniques require manual and error-prone segmentation of target volumes, leading to unreliable and labor-intensive data extraction, especially when comparing rest and stress images for perfusion and viability assessments.
Innovation Solution
A method involving the recording of a first image with high contrast for target volume segmentation, which is then registered and applied to subsequent images, allowing for precise localization and segmentation of the target volume in subsequent images without the need for repeated manual segmentation, thereby enhancing reliability and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual segmentation is performed on each image record to ensure precise target volume localization, then measurement precision is improved, but productivity deteriorates due to labor-intensive repeated segmentation
Solution Approach 1:
The patent performs segmentation on a first image record with high anatomical contrast before processing second image records. This preliminary segmentation result is then transferred to the second image records through registration, eliminating the need for repeated manual segmentation while maintaining precision.
Solution Approach 2:
The segmentation mask created from the first image record serves multiple purposes: it localizes the target volume for analysis in the second image records and enables extraction of physiological parameters across different imaging sequences without requiring separate segmentation for each.
2Measurement precision
If image records are optimized for contrast agent visualization to improve information quality, then measurement precision is improved, but manufacturing precision deteriorates due to poor anatomical boundary contrast
Solution Approach 1:
The patent separates the imaging process into two distinct image records: one optimized for anatomical boundary visualization (first image record) and another optimized for contrast agent visualization (second image record). This segmentation of imaging functions allows each record to be optimized for its specific purpose without compromise.
Solution Approach 2:
The first image record with high anatomical contrast acts as an intermediary that provides the segmentation mask. This mask is then applied to the second image record through registration, serving as a bridge that transfers precise anatomical localization to the perfusion-weighted images without requiring them to have both anatomical and functional contrast simultaneously.
3Reliability
If multiple image records are recorded for comprehensive examination, then reliability is improved, but device complexity increases due to multiple segmentation requirements
Solution Approach 1:
The patent performs a single preliminary segmentation on the first image record that serves all subsequent analysis of multiple second image records. This eliminates the need for separate segmentation processes for each image record, reducing operational complexity while maintaining comprehensive examination capability.
Data Source
AI summary
Disclosed is a method for determining and displaying at least one piece of information on a target volume, especially in a human body, the information being obtained from an image record. At least one embodiment of the method includes: a first and at least one second image record of a target zone encompassing the target volume are recorded, the first image record having a higher contrast regarding the boundaries of the target volume, and the first and the second image record being registered together; the target volume is segmented in the first image record; target volume image data.