Medical Image Registration with Physiological Motion Compensation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The accuracy of image registration between preoperative and real-time medical images during surgery is compromised by factors such as image artifacts, particularly due to physiological motion of the patient, which is exacerbated by the need for continuous contrast agent injections.

Innovation Solution

A method for image registration that involves obtaining initial and target registration relationships by determining the motion state of blood vessels based on physiological features, using centerlines and projection data, and applying weights to improve accuracy, reducing the reliance on contrast agents.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If continuous contrast agent injections are performed to achieve real-time tracking of blood vessels, then the visibility and tracking accuracy of blood vessels is improved, but the adverse effects on the patient and image quality deteriorate due to artifacts and physiological motion

Engineering Contradiction:
Improvetracking accuracyVSAvoidadverse effects on patient
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system performs preoperative imaging to obtain three-dimensional blood vessel models before surgery. These pre-acquired images are stored and later registered with real-time intraoperative images, eliminating the need for continuous contrast agent injection during surgery while maintaining tracking accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a digital copy of the blood vessel anatomy through preoperative imaging. This virtual model is then overlaid and registered with real-time fluoroscopic images, allowing the surgical team to track blood vessels without repeatedly injecting contrast agents into the patient.

Inventive Principle:
Principle #26Copying

2Productivity

If preoperative images are superimposed on real-time images for guidance, then real-time tracking capability is improved, but registration accuracy deteriorates due to physiological motion and image artifacts

Engineering Contradiction:
Improvereal-time tracking capabilityVSAvoidregistration accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system dynamically adjusts the registration process by detecting physiological motion (respiratory and cardiac cycles) and applying real-time motion compensation. The registration parameters are continuously updated based on detected motion states, maintaining alignment accuracy despite patient movement during surgery.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms where physiological signals (such as ECG or respiratory monitoring) are used to detect motion states. This feedback information is then fed into the registration algorithm to compensate for motion artifacts and improve the accuracy of overlaying preoperative and real-time images.

Inventive Principle:
Principle #23Feedback

3Measurement precision

If motion compensation based on physiological features is implemented, then registration accuracy is improved, but system complexity increases due to additional processing requirements

Engineering Contradiction:
Improveregistration accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the physiological motion into distinct components (respiratory motion and cardiac motion) and processes each separately. By dividing the motion compensation task into manageable segments corresponding to different physiological cycles, the system achieves accurate registration without overwhelming computational complexity.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4579595A1Systems, devices, and methods for image registration
Publication Date: 2025.07.02 SHANGHAI UNITED IMAGING HEALTHCARE
  • EP4579595A1 patent drawingFigure 1~2
  • EP4579595A1 patent drawingFigure 3~4
  • EP4579595A1 patent drawingFigure 5~7

AI summary

The present disclosure provides systems, devices, and methods for image registration. The methods include obtaining a first medical image and a second medical image of a target subject, the first medical image indicating blood vessels of the target subject, the second medical image indicating an interventional tool in the target subject; determining an initial registration relationship between the first medical image and the second medical image; determining, based on a first physiological feature of the target subject at an acquisition time of the second medical image, a first motion state of the blood vessels at the acquisition time; and determining a target registration relationship between the first medical image and the second medical image based on the initial registration relationship and the first motion state of the blood vessels.