Tissue Region Segmentation for Staining Heterogeneity Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for measuring cell nuclei in tissue samples from immuno-histochemistry images require users to manually specify measurement regions, leading to extra effort and difficulty in observing staining heterogeneity within cancerous regions, as measurement values are aggregated over the entire tissue region.
Innovation Solution
An image measurement apparatus and method that recognizes tissue regions, extracts images of fixed size and magnification, generates masks to remove non-measurement objects, merges adjacent unmasked regions to form object regions, and computes information on measurement objects within these regions, allowing for detailed measurement and display of staining intensity and positive ratios for each region.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the entire tissue region is specified as a measurement object, then the measurement process is simplified, but it becomes difficult to observe staining heterogeneity in each cancerous region as individual values
Solution Approach 1:
The patent segments the tissue region into multiple object regions (cancerous regions) based on staining characteristics. The measurement system divides the entire tissue region into distinct segments, each representing a separate cancerous region, allowing individual analysis of staining heterogeneity while maintaining automated processing
Solution Approach 2:
The patent applies local quality by computing measurement values (staining intensity, positive/negative results) separately for each object region rather than aggregating over the entire tissue region. This allows each cancerous region to have its own specific measurement values, preserving local staining heterogeneity information
2Measurement precision
If a user manually specifies a measurement object region, then measurement precision is improved, but user effort and time consumption increase
Solution Approach 1:
The measurement system performs self-service by automatically identifying and segmenting object regions (cancerous regions) from the tissue region without requiring manual user specification. The system uses staining characteristics to autonomously define measurement regions, eliminating user effort while maintaining measurement precision
Solution Approach 2:
The patent performs preliminary action by pre-processing the tissue image to identify and segment object regions before the actual measurement process. This preliminary segmentation is done automatically based on staining patterns, preparing the measurement regions in advance without requiring user intervention during the measurement phase
Data Source
AI summary
A partial image extracting unit extracts images of a predetermined size and constant magnification from a tissue region. A mask generating unit generates a mask for removing a region not intended for measurement from the tissue region for each extracted image. A complete mask generating unit generates a temporary complete mask in which the masks generated for each of the images are integrated together, and generates a complete mask in which close portions among unmasked portions in the temporary complete mask are unified into one or more target regions. A measuring unit measures information pertaining to an object to be measured included in the image, and this information is measured for each of the images extracted by the partial image extracting unit. A region information calculating unit calculates, for each target region, information pertaining to the object to be measured from the measured information and from the complete mask.