Imaging Biomarker for Lesion Detectability in Mammography
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mammography accuracy is reduced for women with dense breasts due to reduced lesion contrast and distracting tissue texture, making it harder to detect lesions, and current methods lack a quantitative measure for the difficulty of interpreting mammographic images.
Innovation Solution
A method is developed to generate an imaging biomarker that estimates the detectability of lesions in mammographic images by computing a task-based measure of signal-to-noise ratio over small regions-of-interest, using image properties and physical models to predict detection rates and indicate lesion conspicuity, which can inform clinicians about the suitability of the image for detecting lesions or the need for alternative screening methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If mammography is used for screening dense breasts, then breast cancer screening is performed, but lesion detectability is reduced due to reduced contrast and distracting tissue texture
Solution Approach 1:
The patent introduces an imaging biomarker as an intermediary measure that quantifies the difficulty of detecting lesions in mammographic images. This biomarker serves as a mediator between the mammography process and the final detection outcome, providing objective information about image interpretability without requiring direct lesion detection. The biomarker is computed from image properties and physical models to estimate detectability, thereby resolving the contradiction by adding an intermediate assessment layer.
2Measurement precision
If quantitative breast density measurement is added to mammographic examination, then breast cancer risk assessment accuracy is improved, but a quantitative measure of interpretation difficulty is still lacking
Solution Approach 1:
The patent segments the overall mammographic assessment into distinct components: breast density quantification and lesion detectability measurement. By separating these functions, the patent enables independent optimization of each aspect. The imaging biomarker specifically addresses the interpretation difficulty aspect that was previously missing, while preserving the benefits of density quantification for risk assessment.
3Ease of operation
If BIRADS density scoring is used, then basic indication of detection difficulty is provided, but the measure is qualitative and lacks precision
Solution Approach 1:
The patent transforms the qualitative BIRADS density scoring system into a quantitative framework by computing an imaging biomarker based on objective image properties and physical models. This parameter change converts subjective categorical assessments into precise numerical measurements of lesion detectability, thereby improving measurement precision while maintaining operational feasibility through automated computation.
Data Source
AI summary
Systems and methods for generating imaging biomarkers that indicate detectability or conspicuity of lesions that may be present in mammographic images are provided. In general, a task-based measure of a signal-to-noise ratio (“SNR”) measurement of a detection task is computed over a number of small regions-of-interest (“ROIs”) in an image, and the computed parameter is used to predict what detection rates should be if a lesion was present in the image. As such, the computed parameter can be used to define an imaging biomarker that is a “masking measure” that indicates the degree of conspicuity of lesions that may be present in a given a mammographic image.