Subpixel ROI Rendering for Accurate SUV Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for isolating regions of interest (ROI) in DICOM images are inefficient, leading to inaccuracies in determining the standard uptake value (SUV), which is crucial for medical imaging and diagnosis.
Innovation Solution
A method and system that identify pixels within a ROI by determining a sequential order for navigating coordinates, defining a set of points around the ROI, generating sub-pixel subregions, and calculating the combined area of these subregions to accurately determine the percentage of each pixel within the ROI.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to isolate regions of interest in DICOM images, then the process is simpler, but the accuracy in determining standard uptake value deteriorates
Solution Approach 1:
The patent divides each pixel into multiple sub-pixel regions based on the ROI boundary intersections. By segmenting pixels that are partially covered by the ROI into distinct sub-regions (internal, external, and boundary sub-pixels), the method achieves precise calculation of the percentage of each pixel within the ROI, thereby improving SUV measurement accuracy without requiring overly complex algorithms.
Solution Approach 2:
The patent introduces a new dimension of analysis by calculating sub-pixel level information within each pixel. Instead of treating pixels as uniform units, the method divides pixels into sub-regions and calculates the precise area proportion of ROI within each pixel, adding a sub-pixel dimension to the traditional pixel-based analysis and significantly improving measurement precision.
2Productivity
If traditional pixel isolation methods are used, then the computational process is faster, but the efficiency of ROI isolation deteriorates
Solution Approach 1:
The patent performs preliminary classification of pixels into three categories (fully internal, fully external, and partially covered) before conducting detailed calculations. By pre-identifying and separating pixels based on their relationship with the ROI boundary, the method avoids unnecessary computations for pixels that are completely outside the ROI, thereby improving overall processing efficiency and reducing computational time.
Solution Approach 2:
The patent applies different processing strategies to different types of pixels based on their local characteristics. Fully internal pixels receive simple inclusion marking, fully external pixels are quickly excluded, and only partially covered pixels undergo detailed sub-pixel analysis. This localized quality-based processing significantly improves computational efficiency by focusing resources only where precise measurement is necessary.
Data Source
AI summary
Computer-implemented method, systems, computer program products include a processor(s) that obtains input data comprising an image and image data: coordinates (points) defining a region of interest in the image. The processor(s) determines a non-duplicative sequential order for navigating the coordinates. The processor(s) defines a set of points bordering the region of interest: points in the image and points comprising intersection points between two coordinates with an edge of a pixel in the image. The processor(s) determines a combined area of sub pixel subregions in each pixel that includes points in the set of points by: identifying the points of the set, generating one or more sub pixel subregions, and utilizing the sub pixel subregions to determine the combined area of sub pixel subregions.