Image Motion Detection Using Classified Feature Regions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing motion detection methods for medical images during non-invasive treatments lack flexibility and accuracy due to the lack of rigid body assumptions, interference from imaging parameters and environmental changes, and difficulty in extracting target features from anatomical surface images with grayscale information.

Innovation Solution

An image-based motion detection method that classifies basic markings into categories, determines offset vectors, and uses clustering to correct deviations, with flexible threshold settings for improved accuracy and adaptability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If simple image comparison is used for motion detection, then the method is easy to implement, but the detection accuracy is insufficient due to lack of rigid body assumptions and interference from imaging parameter changes

Engineering Contradiction:
Improveease of implementationVSAvoiddetection accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent divides the image into multiple regions of interest (ROIs) and extracts features from each region separately. This segmentation allows the system to handle partial movements and distinguish between different anatomical structures, improving detection accuracy while maintaining implementation simplicity through modular processing

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different processing strategies to different regions based on their anatomical significance and movement characteristics. By assigning different weights and thresholds to different ROIs, the system adapts to local variations in tissue density and movement patterns, enhancing detection precision without requiring complex global models

Inventive Principle:
Principle #3Local quality

2Device complexity

If traditional motion detection algorithms are applied to medical images, then the processing is straightforward, but the target feature extraction is difficult due to grayscale information and mixed anatomical structures

Engineering Contradiction:
Improveprocessing complexityVSAvoidtarget feature extraction capability
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The patent extracts and isolates specific anatomical features from the grayscale medical images by defining regions of interest and selecting characteristic points within those regions. This extraction process concentrates the system's attention on movement-relevant features while filtering out irrelevant anatomical variations, effectively recovering target feature information from the grayscale data

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces a dimensional transformation by mapping 2D image coordinates to 3D anatomical space through the establishment of correspondence between reference and current images. This dimensional elevation enables the system to detect movements that would be invisible in single-plane grayscale images by leveraging spatial relationships across multiple dimensions

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Reliability

If fixed thresholds are used for motion detection, then the detection is consistent, but the adaptability to different scenarios and imaging conditions is insufficient

Engineering Contradiction:
Improvedetection consistencyVSAvoidadaptability to different scenarios
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic threshold adjustment where the motion detection thresholds are automatically adapted based on the specific imaging modality, anatomical region, and patient characteristics. The system adjusts sensitivity parameters in real-time based on the quality of feature extraction and the expected movement magnitude, maintaining both consistency and adaptability across different scenarios

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4202831B1Image-based motion detection method
Publication Date: 2025.07.02 SHANGHAI SHENDE MEDICAL TECH CO LTD
  • EP4202831B1 patent drawingFigure 1
  • EP4202831B1 patent drawingFigure 2~4

AI summary

Disclosed is an image-based motion detection method. The method specifically includes: acquiring a reference image of a detecting object, determining several first detecting points in the reference image, extracting basic markings centered on the first detecting points in the reference image and classifying all the basic markings into several categories; acquiring a detecting image of the detecting object; matching the basic markings in the detecting image, obtaining an offset vector of each basic marking, and determining whether the basic marking has moved according to a norm of the offset vector of the basic marking; determining whether the number of the basic markings that have moved in each category is greater than a third threshold, if yes, determining that the category has moved; and if no, determining that the category has not moved; and determining a moving state of the detecting object according to a moving state of each category. Compared with the prior art, the present disclosure has the advantages of good accuracy, flexibility and comprehensive information.