Local Tissue Function Assessment via Image Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional tumor therapy response assessment methods, such as RECIST criteria, are inadequate for novel therapies that do not immediately affect tumor size, and fail to account for local differences in blood supply and structural changes in tumor tissue, leading to inaccurate or delayed response evaluation.
Innovation Solution
A method for determining local tissue function by segmenting medical images to identify and analyze specific tissue regions, allowing for the assessment of function parameters like perfusion and texture analysis, enabling early and reliable evaluation of treatment response.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional RECIST criteria are used to assess tumor response, then tumor size measurement is simple and straightforward, but the assessment is inaccurate for novel therapies that do not immediately affect tumor size
Solution Approach 1:
The patent changes the assessment parameters from simple linear dimensions (RECIST LAD/SAD) to functional parameters including blood volume, perfusion, and texture metrics. This allows accurate assessment of novel therapies that affect tumor function before size change, resolving the contradiction between measurement precision and therapy type adaptability
Solution Approach 2:
The patent segments the tumor into multiple regions of interest (ROIs) and analyzes functional parameters in each region separately. This segmentation enables detection of local treatment responses that may be masked in overall tumor size measurements, improving assessment accuracy for heterogeneous tumor responses
2Measurement precision
If blood volume is evaluated for the entire lesion, then the measurement process is simple, but local differences in blood supply are not detected
Solution Approach 1:
The patent automatically segments the lesion into multiple ROIs based on intensity thresholds and spatial distribution. This segmentation enables local blood supply detection without requiring manual region definition, resolving the contradiction between measurement precision and process complexity
Solution Approach 2:
The system performs automatic ROI selection and analysis without user intervention. The algorithm independently identifies regions of interest and computes functional parameters, eliminating the need for manual region definition while maintaining local detection capability
3Reliability
If manual definition of regions of interest is used, then local differences in blood volume can be identified, but the method is heavily user dependent and poorly reproducible
Solution Approach 1:
The system performs automatic ROI selection based on image intensity characteristics and spatial distribution. This self-service approach eliminates user dependency while maintaining the ability to identify local differences, resolving the contradiction between reliability and ease of operation
Solution Approach 2:
The patent uses texture analysis to create reproducible representations of tissue structure that can be compared across different time points and patients. This copying approach standardizes the analysis process, improving reproducibility without requiring manual intervention
4Measurement precision
If texture analysis methods are used to create perfusion maps, then structural properties can be evaluated, but the methods react very sensitively to processing chain changes and cannot enable comparison of initial and control measurements
Solution Approach 1:
The patent transforms texture data into standardized functional parameters (blood volume, perfusion) that are less sensitive to processing variations. This parameter transformation maintains structural property evaluation capability while improving measurement comparability across different processing conditions
Solution Approach 2:
The patent performs preliminary normalization and standardization of image data before analysis. This preliminary action ensures that measurements are comparable across different time points and processing conditions, resolving the reliability issue while maintaining structural evaluation capability
Data Source
AI summary
A method for determining a local tissue function of tissue in a body region of interest of an examination object is disclosed. In an embodiment, the method includes segmentation of an outer contour of the tissue using at least one medical image recording representing the body region of interest of the examination object comprising the tissue; subdivision of the segmented tissue into at least two tissue regions; and ascertaining a function parameter relating to the tissue function for each of the at least two tissue regions. Embodiments also relate to a corresponding computing unit for determining a tissue function of tissue, a corresponding medical imaging system, a computer program and a computer-readable data carrier.