Adaptive Tumor Burden Estimation Using Organ-Specific Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining tumor burden in medical images are labor-intensive, time-consuming, and prone to false positives or negatives due to global thresholding and lack of organ/system-based segmentation and calculations.
Innovation Solution
A method and system that identify a first region of interest in a medical image, select a second region for tumor burden determination, define segmentation criteria, and calculate tumor burden using a processing unit with a tumor burden estimation module, which adapts to anatomical and physiological variations by using adaptive standardized uptake value thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic lesion detection uses a single standardized uptake value threshold for the whole medical image volume, then the detection process is simplified and faster, but false positives or false negatives occur due to variations in physiological uptake across different organs
Solution Approach 1:
The patent divides the medical image volume into multiple organ-specific regions of interest (ROIs) based on anatomical segmentation. Each organ ROI is processed with its own adaptive threshold, allowing precise lesion detection while maintaining automated processing. This resolves the contradiction by enabling both speed (through automation) and precision (through organ-specific thresholds).
Solution Approach 2:
The patent implements local quality by applying different standardized uptake value thresholds to different organs based on their specific physiological characteristics. For example, the brain, heart, and liver receive higher thresholds due to high glucose metabolism, while lungs receive lower thresholds. This local adaptation eliminates false positives/negatives while maintaining automated detection efficiency.
2Measurement precision
If manual exclusion of tumor hotspots is performed for regions with physiological uptake, then measurement precision is improved, but the process becomes labor-intensive and time consuming
Solution Approach 1:
The patent implements self-service by enabling the system to automatically perform the exclusion of physiological uptake regions through adaptive organ-specific thresholding. The automated system identifies and excludes false positives in organs with high physiological uptake without requiring manual physician intervention, thereby maintaining high measurement precision while eliminating the time-consuming manual process.
3Extent of automation
If current post processing applications are used for tumor burden estimation, then basic automated segmentation is available, but organ/system-based segmentation and calculations are not supported
Solution Approach 1:
The patent implements universality by creating a multi-functional system that performs both automated segmentation and organ-specific tumor burden calculations within a single integrated platform. The system can automatically segment tumors and simultaneously perform organ-specific analysis using adaptive thresholds, eliminating the need for separate manual processes and providing versatile functionality that adapts to different organ systems.
Data Source
AI summary
A method and system for determining system-based tumor burden is disclosed. In one aspect, the method includes obtaining the medical image from a source, through an interface. Additionally, the method includes identifying a first region of interest in the medical image. The method also includes selecting from the first region of interest a second region of interest whose tumor burden is to be determined. Furthermore, the method includes defining a segmentation criterion for the second region of interest. The method also includes determining the tumor burden for the second region of interest.