Ultrasonic Attenuation Map Analysis for Tumor Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cancer diagnostic tools, including mammography and ultrasound imaging, often result in a high percentage of benign biopsies, highlighting the need for improved methods to differentiate between malignant and benign tumors in breast tissue.
Innovation Solution
A computerized method and system that classify suspicious regions of interest in ultrasonic attenuation images by generating an attenuation map and analyzing specific attenuation features, such as dimensions, attenuation values, and homogeneity, to distinguish between benign and malignant tumors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If mammography and ultrasound imaging are used for cancer diagnosis, then detection capability is improved, but the percentage of benign biopsies increases
Solution Approach 1:
The patent applies parameter changes by computing multiple breast image features including shape parameters (estimated as depicting a possible tumor), texture parameters (of the suspicious region), and acoustic parameters (of the suspicious region). These multi-parameter analyses enable more accurate differentiation between malignant and benign tumors, thereby reducing unnecessary biopsies while maintaining high detection accuracy
Solution Approach 2:
The patent segments the analysis into distinct feature categories: shape features, texture features, and acoustic features. This segmentation allows the CAD system to independently evaluate different characteristics of suspicious regions and combine them for comprehensive classification, improving diagnostic reliability
2Measurement precision
If more breast image features are computed to distinguish malignant and benign tumors, then classification accuracy is improved, but system complexity increases
Solution Approach 1:
The CAD system implements universality by using a single integrated computerized system that performs multiple functions: detecting suspicious regions, computing shape features, computing texture features, computing acoustic parameters, and classifying tumors. This multi-functional approach consolidates complexity into one system rather than requiring separate devices for each analysis type
Data Source
AI summary
A computerized method of classifying at least one suspicious region of interest (ROI) in an ultrasonic attenuation image mapping tissue of a patient. The method comprises receiving an US image of an tissue, identifying a suspicious region of interest (ROI) in the US image, generating an attenuation map of the suspicious ROI, measuring, according to an analysis of the attenuation map, at least one attenuation feature of at least one of the suspicious ROI and at least one sub region in the suspicious ROI, and classifying the suspicious ROI according to the at least one attenuation feature.