Non-invasive Patient-Image Registration via Blood Vessel Pattern Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current patient-image registration methods in minimally and non-invasive surgeries are invasive, imprecise, or affected by soft tissue changes, especially when using fiducial markers or 2D sectional images, which limits their applicability in microsurgical operations.
Innovation Solution
A system and method for non-invasive registration using a near-infrared 3D camera to extract blood vessel images and patterns, which are then matched with pre-operative 3D medical images to align the patient's position without fiducial markers, utilizing feature points from blood vessel patterns to minimize errors and skin deformation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fiducial markers are attached to patient's bone for registration, then registration precision is improved, but patient burden increases due to invasive procedure and scar
Solution Approach 1:
The patent extracts the registration function from invasive fiducial markers and implements it through non-invasive blood vessel pattern recognition. The system captures images of blood vessels on the patient's skin surface and uses pattern matching to achieve registration without any physical markers or invasive procedures, thereby eliminating patient burden while maintaining precision
Solution Approach 2:
The patent introduces blood vessel patterns as an intermediary between the patient's anatomy and the registration system. Instead of directly attaching markers to bone, the system uses the naturally occurring blood vessel patterns on the skin surface as a mediator to establish coordinate transformation, achieving both non-invasiveness and precision
2Object-affected harmful factors
If non-invasive fiducial markers are attached on patient's skin for registration, then patient burden is reduced, but registration precision deteriorates making it inapplicable to microsurgical operation
Solution Approach 1:
The patent replaces the mechanical attachment of fiducial markers with an optical imaging system that captures blood vessel patterns. Instead of mechanically fixing markers to the skin, the system uses near-infrared or optical imaging to detect and analyze the natural blood vessel patterns, achieving high precision without mechanical intervention
Solution Approach 2:
The patent changes the registration approach from marker-based coordinate matching to blood vessel pattern recognition. By analyzing the geometric parameters and topological features of blood vessel patterns, the system achieves precise registration without requiring physical markers, thus maintaining both non-invasiveness and precision
3Device complexity
If 2D sectional images or 3D scan models are used for markerless registration, then fiducial markers are eliminated, but registration accuracy deteriorates due to soft tissue transformation or skin surface shape change
Solution Approach 1:
The patent transitions from 2D sectional images to 3D surface imaging of blood vessel patterns. By capturing the three-dimensional geometry and topography of blood vessels on the skin surface, the system creates a more robust registration reference that is less susceptible to soft tissue deformation, thereby maintaining accuracy while remaining markerless
Solution Approach 2:
Instead of deforming the medical images to match the patient's current state, the patent inverts the approach by using the patient's blood vessel patterns as the reference and transforming the pre-operative medical images to match the observed patterns. This inverse transformation approach compensates for soft tissue changes and maintains registration accuracy
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables precise, non-invasive registration of patients with 3D medical images, reducing errors and being applicable to various surgical areas by using blood vessel patterns as feature points, thus improving surgical navigation and accuracy.
Implementation Method 1
a near infrared 3D camera which extracts a 3D blood vessel image of a patient's registration target area
Data Source
AI summary
A system for non-invasive registration between a patient and a three-dimensional (3D) medical image includes a near infrared 3D camera 110 which extracts a 3D blood vessel image I2 of a patients registration target area during surgical operation; a camera position tracer 120 which traces a position of the near infrared 3D camera 110 and calculates a real world coordinate system of the 3D blood vessel image I2; a controller 130 which extracts a first blood vessel pattern from a 3D medical image I1 of the registration target area, extracts a second blood vessel pattern from the 3D blood vessel image I2, and performs position registration between the patient and the 3D medical image I1 through the extracted first and second blood vessel patterns; and a display 140 which displays a registration result calculated by the controller 130.