Real-Time Cardiac Ultrasound Guidance Through Image Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The reliability of cardiac ultrasound measurements depends heavily on the skill level of medical staff, leading to variability in results and challenges in emergency situations due to time constraints.

Innovation Solution

A guideline providing system based on an artificial neural network is developed to segment cardiac ultrasound images, providing probe guidance and measurement values, and classifying cross-sectional views to enhance accuracy and reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual measurement and interpretation by medical staff is used, then measurement values can be obtained, but reliability and consistency vary greatly depending on skill level

Engineering Contradiction:

Improvemeasurement reliabilityVSAvoidmeasurement consistency

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent replaces the manual mechanical process of measurement by medical staff with an automated image processing system using artificial neural networks. The system automatically segments cardiac ultrasound images, identifies anatomical structures, and calculates measurement values, eliminating human skill-level variability and providing consistent, reliable measurements regardless of operator expertise.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service measurement by automatically performing image analysis and measurement calculation without requiring manual interpretation. The artificial neural network autonomously processes cardiac ultrasound images, segments relevant structures, and generates measurement values, allowing the system to serve itself rather than relying on external human expertise.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If comprehensive manual analysis is performed to ensure accuracy, then measurement quality improves, but examination time increases significantly

Engineering Contradiction:

Improvemeasurement accuracyVSAvoidexamination time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system implements continuous automated image processing where cardiac ultrasound images are immediately analyzed as they are acquired. The artificial neural network continuously segments images and calculates measurements in real-time, eliminating interruptions and maintaining continuous useful action throughout the examination process, thereby reducing total examination time while preserving measurement accuracy.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system performs preliminary segmentation and identification of anatomical structures automatically before final measurement calculation. By pre-processing images to identify relevant cardiac structures and boundaries in advance, the system prepares measurement data beforehand, enabling rapid final measurement determination without time-consuming manual analysis during the examination.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If multiple imaging modes are switched to obtain measurement values, then comprehensive measurement data is obtained, but operational complexity and time consumption increase

Engineering Contradiction:

Improvemeasurement coverageVSAvoidoperational simplicity

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system implements a universal image processing framework that can handle multiple cardiac ultrasound imaging modes (2D, M-mode, Doppler) through a single artificial neural network architecture. The system automatically adapts to different imaging modes and extracts measurement data from any mode without requiring separate processing pipelines, providing comprehensive measurement coverage while maintaining operational simplicity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system merges the functionality of multiple imaging modes into a unified automated measurement process. Instead of requiring separate manual analysis for each imaging mode, the artificial neural network integrates processing of different modalities, combining their strengths to provide comprehensive measurement data through a single streamlined operation that simplifies the user workflow.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentEP4620405A1Method for providing guideline for cardiac ultrasound image and device for providing guideline for cardiac ultrasound image using the same

Publication Date: 2025.09.24 ONTACT HEALTH CO LTD

Figure 1A
Figure 1B
Figure 2A

AI summary

The present disclosure provides a method for providing a guideline for a cardiac ultrasound image implemented by a processor, in which the method includes receiving a cardiac ultrasound image of a captured subject and determining probe guidance based on the received cardiac ultrasound image by using a prediction model trained to determine probe guidance according to movement of an ultrasound probe by inputting the cardiac ultrasound image. Moreover, the present disclosure provides a device using the method.