Elasticity Image Classification for Objective Disorder Progression Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The existing ultrasonic diagnostic apparatuses rely on visual estimation of elasticity images for disorder progression, leading to variability among examiners, necessitating an objective method for classifying and estimating the progress state of disorders based on elasticity image information.

Innovation Solution

An ultrasonic diagnostic apparatus equipped with an elasticity image analyzing unit that automatically processes RF signal frame data to calculate distortion and elasticity modulus, and an image classifying unit using multivariate analysis to objectively classify and estimate the disorder progression by analyzing histogram data, statistical processing, and region complexity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If visual estimation of elasticity images is used for disorder progression, then diagnostic flexibility is maintained, but estimation variability among examiners increases

Engineering Contradiction:
Improveestimation consistencyVSAvoidautomated classification
Core Design Contradiction:
Measurement precisionVSExtent of automation

Solution Approach 1:

The patent replaces the manual visual estimation process with an automated image analysis system that uses computer algorithms to objectively evaluate elasticity images. The system automatically extracts features from elasticity images, classifies them into disorder progression stages, and generates diagnostic results without relying on examiner subjectivity, thereby substituting the mechanical visual assessment process with an automated computational system.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The image analysis system performs self-assessment by automatically analyzing elasticity images and determining disorder progression stages without requiring manual intervention. The system uses pre-programmed algorithms to extract image features, compare them against reference data, and generate diagnostic classifications autonomously, enabling the diagnostic process to serve itself without external examiner input.

Inventive Principle:
Principle #25Self-service

2Reliability

If automated image analysis is implemented, then estimation objectivity is improved, but system complexity increases

Engineering Contradiction:
Improvediagnostic objectivityVSAvoidanalysis system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent divides the complex diagnostic system into distinct functional modules: an image acquisition module that captures elasticity images, an image processing module that extracts features from the images, a classification module that compares features against reference data, and a result generation module that outputs diagnostic stages. This segmentation allows each module to perform a specific function independently, managing overall system complexity through modular design.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system manages complexity by transforming the diagnostic problem into parameter-based analysis. Instead of requiring complex pattern recognition, the system extracts quantitative parameters from elasticity images (such as stiffness values, texture features, and structural characteristics) and compares these parameters against reference ranges for different disorder stages, simplifying the analysis through parameterization.

Inventive Principle:
Principle #35Parameter changes

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 objective estimation of disorder progression, reducing variability among examiners and providing accurate classification of elasticity images, thereby improving diagnostic consistency.

Implementation Method 1

cross-sectional scanning means for repetitively obtaining tomogram data in the object containing a motional tissue at a predetermined period by using a reflection echo signal from the ultrasonic wave receiving means

Methodology Applied
Scientific EffectUltrasonic wave reflection: Reflection

Implementation Method 2

displacement measuring unit that measures displacement of each point in the object by using a correlation calculation of ultrasonic wave reception signals of two frames which are adjacent to each other in time series

Methodology Applied
Scientific EffectCorrelation calculation:

Implementation Method 3

elasticity data calculating unit that calculates distortion and/or elasticity modulus of each point on the image from the RF signal frame data

Methodology Applied
Scientific EffectElasticity measurement: Elasticity

Implementation Method 4

elasticity modulus data of the biomedical tissue represented by Young's modulus or the like are imaged from the stress distribution caused by the external force and the distortion data

Methodology Applied
Scientific EffectStress-strain relationship: Hooke's Law

Data Source

PatentEP2263545B1ultrasonograph
Publication Date: 2016.12.14 HITACHI LTD
  • EP2263545B1 patent drawingFigure 1
  • EP2263545B1 patent drawingFigure 2
  • EP2263545B1 patent drawingFigure 3

AI summary

There is provided an ultrasonic diagnostic apparatus that can classify an elasticity image by using elasticity data of the elasticity image and image information and objectively estimate a progress state of a disorder. The ultrasonic diagnostic apparatus has an elasticity information calculator for calculating elasticity data of a biomedical tissue by using RF signal frame data from the inside of an object which is received by ultrasonic wave transmitting/receiving means, an elasticity image constructing unit for generating an elasticity image on the basis of a distortion amount and/or an elasticity modulus calculated by an elasticity information calculator, an elasticity image estimating unit 11 for generating estimation data for estimating the characteristic of a biomedical tissue on the basis of an elasticity image, and an image classifying unit 12 for classifying an elasticity image by using at least one of estimation data generated by the elasticity image estimating unit 11. A classification result of the classifying unit 12 is displayed on a display unit through a switching and displaying unit 14.