Image Matching Method for Medical Sequence Registration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for determining correspondence between image frames in medical image sequences, such as CT images, are inaccurate due to variations in patient positioning and organ distribution, leading to low accuracy in image matching.

Innovation Solution

An image matching method that involves acquiring and registering image sequences to establish a one-to-one correspondence between pixel points, using a registration matrix equation solved by the least square method to generate a mapping relationship between frames, and displaying matching frames based on this relationship.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a difference value is set artificially based on experience to determine correspondence between image frames, then the operation is simple and fast, but the accuracy of image frame correspondence is low

Engineering Contradiction:

Improvesimplicity of setting difference valueVSAvoidaccuracy of image frame correspondence

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent replaces the manual mechanical approach of setting difference values based on experience with an automated image registration system that uses computational algorithms (rigid/non-rigid registration, feature point matching) to automatically determine the correspondence between image frames, thereby substituting human judgment with systematic image processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms the static parameter approach (fixed difference value) into a dynamic parameter system where the correspondence relationship is determined by actual image content analysis through registration algorithms, allowing the mapping relationship to adapt to different imaging conditions and patient anatomies

Inventive Principle:

Principle #35Parameter changes

2Productivity

If manual difference value setting is used to match image frames, then the process is quick, but the reliability of diagnosis is reduced due to inaccurate correspondence

Engineering Contradiction:

Improvespeed of image frame matchingVSAvoidreliability of diagnosis

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent performs image registration and establishes the mapping relationship between image frames in advance, before the actual diagnostic comparison is needed. This preliminary processing creates a reliable correspondence foundation that can be quickly applied during subsequent diagnostic operations, separating the computationally intensive registration step from the diagnostic review process

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11954860B2Image matching method and device, and storage medium

Publication Date: 2024.04.09 INFERVISION MEDICAL TECH CO LTD

AI summary

Disclosed are an image matching method, an image matching device, and a storage medium. A first image sequence and a second image sequence are acquired, and thus a first object and a second object are reconstructed and generated based on the first image sequence and the second image sequence respectively. The registration of the first object and the second object are further performed, and a mapping relationship obtained according to a registration result may indicate a correspondence between image frames in the first image sequence and image frames in the second image sequence. Compared with setting a difference value artificially, obtaining the correspondence between image frames in the first image sequence and image frames in the second image sequence by using the image matching method improves the matching accuracy.