Breast Density Measurement Using Segmentation and Dispersion Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for measuring breast density from digital mammograms are subjective and inaccurate, relying on radiologist visual examination or calibration data from X-ray imaging devices, which can be unreliable due to factors like device age and calibration status.
Innovation Solution
A system and method for obtaining breast density measurements and classifications through breast segmentation, thickness correction, and computation of density ratios and dispersion values from digital mammographic images, independent of X-ray imaging device calibration data, using techniques like breast segmentation, pectoral muscle segmentation, and multi-scale texture analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods using radiologist visual examination or device calibration data are used, then the measurement process is simple and quick, but the measurement precision and reliability are poor due to subjectivity and device variability
Solution Approach 1:
The patent applies segmentation by dividing the breast tissue into distinct regions based on density characteristics. The system segments the mammographic image to identify and separate dense tissue from fatty tissue, enabling quantitative analysis of breast density without relying on subjective visual examination or device calibration data.
Solution Approach 2:
The patent replaces the mechanical/subjective assessment method (radiologist visual examination) with an automated computational method. The system uses image processing algorithms and computational geometry to objectively measure breast density, eliminating human subjectivity and device calibration dependencies.
2Reliability
If device calibration data is used for breast density measurement, then the measurement can be obtained quickly, but the reliability deteriorates due to factors like device age and calibration status
Solution Approach 1:
The system performs self-service by extracting all necessary measurement information directly from the mammographic image itself, without requiring external calibration data or device parameters. The image processing algorithm independently determines breast density based on tissue density ratios and dispersion characteristics, making the measurement reliable and device-independent.
3Measurement precision
If subjective visual examination by radiologists is used, then the measurement process is straightforward, but the measurement precision is poor due to subjectivity and variability
Solution Approach 1:
The patent replaces the manual visual examination process with an automated computer-based system. The algorithm automatically analyzes mammographic images, calculates density ratios, and determines breast density classifications without human intervention, thereby eliminating subjectivity and improving precision while maintaining ease of operation through automated processing.
Data Source
AI summary
Breast density measurements are used to perform Breast Imaging Reporting and Data System (BI-RADS) classification during breast cancer screenings. The accuracy of breast density measurements can be improved by quantitatively processing digital mammographic images. For example, breast segmentation may be performed on a mammographic image to isolate the breast tissue from the background and pectoralis tissue, while a breast thickness adjustment may be performed to compensate for decreased tissue thickness near the skin line of the breast. In some instances, BI-RADS density categorization may consider the degree to which dense tissue is dispersed throughout the breast. A breast density dispersion parameter can also be obtained using quantitative techniques, thereby providing objective BI-RADS classifications that are less susceptible to human error.