Automated Breast Density Assessment via Calibrated Mammography
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for assessing breast density in mammography lack standardization and automation, which hinders the use of breast density as a risk factor for breast cancer, particularly due to variations in image acquisition techniques and the inability to effectively calibrate for these differences.
Innovation Solution
The method involves calibrating digital mammography images to normalize for image acquisition technique variations, using statistical analysis to calculate measures such as pixel variations and central moments, and associating these with breast cancer risk, including the use of non-central and fractional order moments to derive risk metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If operator-assisted labeling method is used to measure breast density, then breast density can be assessed, but the method lacks standardization and automation
Solution Approach 1:
The patent replaces the manual operator-assisted labeling method with an automated computational system that uses calibration curves and image processing algorithms to calculate breast density metrics, eliminating human subjectivity and achieving both automation and standardization
Solution Approach 2:
The patent transforms breast density assessment by changing from qualitative operator labeling to quantitative automated calculation using calibrated pixel values and statistical parameters (mean, standard deviation, central moments) derived from digital mammography images
2Measurement precision
If calibration is applied to normalize image acquisition technique differences, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent performs calibration in advance by creating calibration curves from phantom images before actual breast imaging, storing these curves for later use in normalizing patient images and eliminating the need for complex real-time calibration during clinical imaging
Solution Approach 2:
The patent introduces calibration phantoms as intermediary objects with known properties that bridge the gap between image acquisition parameters and breast density measurement, allowing systematic correction of technique variations through phantom-based calibration curves
3Reliability
If spatial variation measures are calculated from calibrated images, then breast cancer risk assessment improves, but calculation complexity increases
Solution Approach 1:
The patent segments the breast tissue into different density regions (fatty, glandular, mixed) based on calibrated pixel intensity values, then calculates spatial variation metrics separately for each segment to improve risk assessment while managing computational complexity through region-based analysis
Data Source
AI summary
Breast density is a significant breast cancer risk factor measured from mammograms. Evidence suggests that the spatial variation in mammograms may also be associated with risk. The variation in calibrated mammograms as a breast cancer risk factor was investigated and its relationship with other measures of breast density was explored using full field digital mammography (FFDM) as described herein. A matched case-control analysis was used to assess a spatial variation breast density measure in calibrated FFDM images, normalized for the image acquisition technique variation. The findings indicate the variation measure is a viable automated method for assessing breast density. Insights gained by this work may be used to develop a standard for measuring breast density.