Medical Image Segmentation Using Coordinate and Gray-Level Distance Range Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer vision technologies for image processing, particularly in medical imaging, face significant resource consumption and long processing times due to the need to calculate path distances from each pixel to foreground and background points, which is inefficient and time-consuming.
Innovation Solution
The method involves generating segmented medical images using a first and second segmentation model, determining foreground and background points, and calculating image distances to create range images, which are then used to refine the segmentation process, reducing the need to traverse all possible paths and thereby minimizing resource consumption and processing time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If path distances of all possible paths from each pixel to foreground or background point are calculated, then geodesic distance can be obtained, but resource consumption increases and processing time becomes long
Solution Approach 1:
The patent extracts and calculates only the essential distance components (coordinate distance and gray-level distance) rather than computing all possible path distances. By taking out the critical distance measurements and using them to generate foreground point range images and background point range images, the method obtains geodesic distance information without the computational burden of exhaustive path calculation.
Solution Approach 2:
The patent changes the approach from calculating path distances to calculating image distances based on coordinate distances and gray-level distances. This parameter transformation allows the system to derive geodesic distance information through a different computational pathway that is more efficient, using the formula: image distance = sqrt((coordinate distance)² + (gray-level distance)²).
2Measurement precision
If path distances of all possible paths from each pixel to foreground or background point are calculated, then geodesic distance can be obtained, but resource consumption increases
Solution Approach 1:
The patent extracts and calculates only the essential distance components (coordinate distance and gray-level distance) rather than computing all possible path distances. By taking out the critical distance measurements and using them to generate foreground point range images and background point range images, the method obtains geodesic distance information without the computational burden of exhaustive path calculation.
Solution Approach 2:
The patent changes the approach from calculating path distances to calculating image distances based on coordinate distances and gray-level distances. This parameter transformation allows the system to derive geodesic distance information through a different computational pathway that is more efficient, using the formula: image distance = sqrt((coordinate distance)² + (gray-level distance)²).
3Device complexity
If segmentation is performed without using range images, then processing is simpler, but segmentation accuracy decreases
Solution Approach 1:
The patent performs preliminary actions by generating foreground point range images and background point range images before the final segmentation step. These range images are created in advance and stored, then used as input features for the second segmentation model. This preliminary preparation of distance information enhances segmentation accuracy without significantly increasing overall processing complexity.
Solution Approach 2:
The patent introduces foreground point range images and background point range images as intermediary elements that mediate between the original image and the final segmentation result. These range images serve as additional feature inputs that provide distance information to the segmentation model, improving accuracy while maintaining a manageable processing framework.
Data Source
AI summary
An medical image processing method comprises generating a first segmented medical image in accordance with a first segmentation model and based on an original medical image that comprises a plurality of pixels. The method also comprises determining a foreground point and a background point according to the initial target region of the first segmented image. The method further comprises: for each pixel of the plurality of pixels of the original image, determining a first image distance between the respective pixel and the foreground point and a second image distance between the respective pixel and the background point. The method further comprises obtaining a foreground point range image and a background point range image corresponding to the original image, and generating a second segmented image in accordance with a second segmentation model based on the original image, the foreground point range image, and the background point range image.