Multi-Reference Surgical Navigation for Intervertebral Motion Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical imaging technologies struggle to provide real-time, three-dimensional CT-quality images for surgical navigation, especially in minimally invasive procedures, due to challenges in reconstructing 3D volumes from limited 2D projections and aligning surgical instruments with patient anatomy, which is compounded by intervertebral motion and non-linear distortions in X-ray images.
Innovation Solution
A system combining optical and radiographic data to reconstruct 3D volumes from biplanar X-ray images using deep learning, with multiple independent reference markers on vertebrae for dynamic registration and motion compensation, and a registration transform to align instrument coordinates with patient and volume systems, correcting non-linear distortions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If fluoroscopy is used for real-time imaging, then real-time visual assistance is provided, but only two-dimensional views are obtained which are insufficient for complicated surgical procedures requiring three-dimensional anatomy
Solution Approach 1:
The patent transforms 2D fluoroscopic images into 3D anatomical representations by introducing a temporal dimension through sequential imaging and applying computational algorithms (MIP, SSR, neural networks) to reconstruct three-dimensional structures from two-dimensional projection data, enabling both real-time visualization and 3D surgical navigation
Solution Approach 2:
The patent replaces traditional mechanical CT scanning systems with a computational approach that uses software-based 3D reconstruction algorithms processing fluoroscopic images, achieving 3D visualization without the expensive and time-consuming hardware-based CT scanner
2Manufacturing precision
If computerized tomography is used for real-time three-dimensional anatomy generation, then three-dimensional CT quality images are obtained, but the cost and time required are prohibitive for real-time surgical navigation
Solution Approach 1:
The patent creates a virtual copy of the 3D anatomical structure by computationally reconstructing it from 2D fluoroscopic projections using algorithms that simulate CT-quality imaging without requiring the actual CT scanning process, providing 3D navigation data in real-time
Solution Approach 2:
The patent changes the imaging parameters from traditional CT scanning (rotating X-ray source around patient) to fluoroscopic parameters (fixed or C-arm X-ray source), and compensates through computational parameter adjustments in the reconstruction algorithms to maintain 3D accuracy
3Device complexity
If a single reference marker is used for surgical navigation, then the system is simple to implement, but accuracy deteriorates when the surgical instrument operates far from the reference marker, especially with intervertebral motion
Solution Approach 1:
The patent divides the single reference marker system into multiple distributed reference markers placed at different anatomical locations, allowing the navigation system to select the most appropriate reference marker based on the surgical instrument's current position, thereby maintaining accuracy across the entire surgical field
Solution Approach 2:
The patent implements a dynamic reference marker selection system that automatically chooses the optimal reference marker based on real-time instrument position and anatomical motion detection, adapting to intervertebral motion by selecting markers on stable vertebrae relative to the current surgical target
4Measurement precision
If multiple reference markers are used for enhanced navigation accuracy, then measurement precision is improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent implements a dynamic reference marker selection system that automatically chooses the most appropriate reference marker based on real-time instrument position and anatomical motion detection, adapting to intervertebral motion by selecting markers on stable vertebrae relative to the current surgical target
Solution Approach 2:
The patent uses feedback from the surgical instrument's position and detected anatomical motion to dynamically adjust which reference marker is active, creating a closed-loop system that maintains navigation accuracy by selecting the optimal reference frame based on current surgical conditions
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 accurate, real-time surgical navigation with high-resolution 3D reconstructions, reducing the need for additional imaging and enhancing navigation accuracy by dynamically adapting to intervertebral motion and correcting distortions.
Implementation Method 1
reconstructing 3D volumes from limited 2D projections
Implementation Method 2
reconstruct 3D volumes from biplanar X-ray images using deep learning
Implementation Method 3
combining optical and radiographic data
Implementation Method 4
a registration transform to align instrument coordinates with patient and volume systems
Implementation Method 5
correcting non-linear distortions
Data Source
AI summary
A system and method combines optical and radiographic data to enhance imaging capabilities. Specifically, the system combines visually obtained patient pose position information and radiographic image information to facilitate calibrated surgical navigation. Multiple distinct reference markers on a patient's body each have an associated independent coordinate system. By transforming an instrument's position into all these coordinate systems and using a dynamic selection algorithm to determine the most appropriate coordinate systems based on a predetermined criteria, the system maintains high navigation accuracy across multiple anatomical regions, e.g. vertebral levels. By calculating relative transformations between different reference markers, the process allows real-time detection and compensation for anatomical motion during a procedure.