Ultrasonic Breast Imaging for Perilobular Stroma Differentiation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ultrasonic diagnostic apparatuses cannot accurately distinguish between perilobular stroma and edematous stroma in breast tissue, limiting the ability to assess cancer risk in the mammary gland region with precision.
Innovation Solution
An ultrasonic diagnostic apparatus equipped with a first category determination unit that utilizes machine learning to categorize glandular tissue components in the breast, including mammary ducts, lobules, and perilobular stroma, based on ultrasonic images, enabling detailed cancer risk assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional ultrasonic imaging is used to observe mammary gland tissue, then the entire mammary gland region can be visualized, but the perilobular stroma and edematous stroma cannot be distinguished from each other
Solution Approach 1:
The patent segments the mammary gland tissue into distinct components (perilobular stroma, edematous stroma, lobules, ducts) by analyzing specific ultrasonic features. The image processing unit divides the ultrasonic image into multiple regions corresponding to different tissue types, enabling precise identification and measurement of each component's area ratio.
Solution Approach 2:
The patent applies local quality analysis by examining specific local features of the ultrasonic image such as echo intensity distribution, texture patterns, and boundary characteristics in different regions. This allows differentiation between perilobular stroma and edematous stroma based on their distinct local ultrasonic properties.
2Measurement precision
If the entire mammary gland region is observed as a single unit, then the overall glandular tissue can be assessed, but the ratio of GTC region in the mammary gland region cannot be measured
Solution Approach 1:
The patent segments the mammary gland region into GTC (glandular tissue component) and non-GTC areas by analyzing ultrasonic features. The image processing unit identifies and separates different tissue components, calculates their respective areas, and determines the GTC ratio, enabling precise measurement without manually tracing each structure.
Solution Approach 2:
The system performs automated image processing and tissue classification without requiring manual intervention. The image processing unit automatically analyzes the ultrasonic image, identifies tissue boundaries, calculates area ratios, and generates diagnostic information, reducing the complexity burden on the operator.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables precise categorization of glandular tissue components, allowing for enhanced cancer risk evaluation by distinguishing between different tissue types within the mammary gland region.
Implementation Method 1
an ultrasonic beam is transmitted from the ultrasonic probe toward a subject, an ultrasonic echo from the subject is received by the ultrasonic probe
Implementation Method 2
a reception signal is electrically processed to generate the ultrasonic image
Data Source
AI summary
An ultrasonic diagnostic apparatus includes a first category determination unit (25) that determines, based on an ultrasonic image including a mammary gland region in a breast of a subject, a category of a glandular tissue component in the breast, and a category output unit (26) that outputs the category of the glandular tissue component determined by the first category determination unit (25).