Dynamic Chest Image Waveform Analysis for Diagnosis Assistance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for pulmonary diagnosis using dynamic images struggle to efficiently acquire both physiological and morphological data, making it difficult for physicians to grasp pathological conditions, particularly under dynamic conditions, and do not adequately utilize respiratory and vascular dynamics for diagnosis.

Innovation Solution

A diagnosis assistance program that analyzes images by extracting waveforms and frequencies from dynamic images, using AI to learn and match these patterns, enabling visualization of respiratory and vascular dynamics through waveform and frequency analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If conventional methods are used to capture dynamic chest images, then image data can be obtained, but it is difficult to efficiently acquire both physiological data and morphological data

Engineering Contradiction:
Improveamount of diagnostic dataVSAvoidefficiency of data acquisition
Core Design Contradiction:
Quantity of substanceVSProductivity

Solution Approach 1:

The patent combines multiple diagnostic functions into a single dynamic image capture system. By simultaneously extracting morphological information (lung field regions, anatomical structures) and physiological information (respiratory waveforms, cardiovascular dynamics) from the same dynamic image sequence, the system eliminates the need for separate imaging procedures and achieves efficient multi-parameter diagnosis

Inventive Principle:
Principle #5Merging (Combining)

2Loss of information

If maximum inter-frame difference values are displayed for each pixel, then dynamic changes are visualized, but physicians cannot easily grasp pathological conditions

Engineering Contradiction:
Improveinformation about dynamic changesVSAvoidease of pathological assessment
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent extracts specific diagnostic information from the complex dynamic image data by identifying and isolating key features: respiratory waveforms are extracted from periodic image signal variations, cardiovascular dynamics are separated from bulk motion, and morphological changes are distinguished from physiological movements. This extraction process transforms raw pixel data into clinically interpretable parameters

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies different analysis methods to different regions of the image: lung field regions are analyzed for respiratory mechanics, pulmonary hilum regions are examined for cardiovascular dynamics, and specific anatomical structures are tracked for morphological changes. This region-specific analysis enhances the clinical interpretability of dynamic changes

Inventive Principle:
Principle #3Local quality

3Reliability

If respiration and blood pressure are measured after the subject is placed in a resting state, then measurement can be performed, but measurement is limited to this condition and dynamic conditions cannot be assessed

Engineering Contradiction:
Improvemeasurement stabilityVSAvoidmeasurement condition flexibility
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent transitions from static resting-state measurement to dynamic real-time assessment. By continuously analyzing dynamic image sequences, the system captures respiratory and cardiovascular parameters during natural breathing and movement, enabling evaluation under physiologically relevant dynamic conditions while maintaining measurement reliability through real-time signal processing

Inventive Principle:
Principle #15Dynamics

4Measurement precision

If feature amounts indicating movement of divided small regions are displayed, then regional analysis is provided, but this is still not sufficient for grasping pathological conditions

Engineering Contradiction:
Improveregional movement measurementVSAvoidinformation about pathological conditions
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent integrates multiple types of diagnostic information into a comprehensive analysis framework: morphological data from image structure, physiological data from waveform analysis, functional data from respiratory and cardiovascular dynamics, and regional data from divided small region tracking. This composite approach combines diverse information sources to provide sufficient pathological assessment

Inventive Principle:
Principle #40Composite materials

Data Source

PatentEP4696240A1Diagnosis assistance program and diagnosis assistance system
Publication Date: 2026.02.18 RADWISP PTE LTD
  • EP4696240A1 patent drawingFigure 1A
  • EP4696240A1 patent drawingFigure 1B
  • EP4696240A1 patent drawingFigure 1C~1D

AI summary

[Problem] To analyze a dynamic image of a living body and display an analysis result. [Solution] A diagnosis assistance program for analyzing an image of a living body and displaying an analysis result, the diagnosis assistance program causing a computer to execute a process of acquiring a plurality of frame images, a process of acquiring a periodic image signal changing at a fixed period from the plurality of frame images, a process of extracting the waveform of all or a part of the periodic image signal, and a process of collating the extracted waveform with a model waveform acquired in advance and detecting a correlation therebetween. Further included is a process of complementing discrete periodic image signals to form a continuous waveform. Further, the correlation is detected based on at least one of the phase, the amplitude, or the frequency of the waveform of all or a part of the periodic image signal.