Instrument Registration Using Point Cloud Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Minimally invasive medical procedures face challenges in accurately registering medical instruments with anatomical images due to anatomical motion, which distorts images and agitates instrument position data, making it difficult to isolate and segment the catheter and instrument position effectively.
Innovation Solution
A system that uses shape sensors to record shape data and generate sensor point clouds, which are then registered with image point clouds using point matching techniques like the iterative closest point method, allowing for robust registration of the instrument frame of reference to the image frame of reference despite anatomical motion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional image registration methods are used, then the registration process is simple, but the registration accuracy deteriorates due to anatomical motion distorting images and agitating instrument position data
Solution Approach 1:
The patent creates a virtual model (copy) of the anatomical structure from pre-operative imaging data and registers the instrument to this virtual model rather than directly to distorted intra-operative images. This copying approach preserves the geometric accuracy of the anatomical structure while avoiding the distortion problems of real-time imaging, thereby maintaining high registration accuracy without requiring complex real-time image processing
Solution Approach 2:
The patent performs image acquisition and 3D model construction before the surgical procedure begins. By preparing the virtual anatomical model in advance when no anatomical motion is present, the system establishes an accurate reference framework that can guide the instrument throughout the procedure without requiring complex real-time registration adjustments
2Productivity
If real-time image capture is performed, then navigation guidance is provided continuously, but image quality deteriorates due to anatomical motion causing distortion
Solution Approach 1:
Instead of relying on distorted real-time images, the system uses a pre-acquired 3D virtual model that copies the anatomical structure's geometry. This virtual model serves as a stable reference that can be continuously referenced during the procedure without being affected by anatomical motion, thus maintaining both real-time navigation capability and image quality
Solution Approach 2:
The patent transitions from 2D fluoroscopic images to a 3D virtual model representation of the anatomy. This dimensional change allows the system to avoid the planar distortion issues inherent in 2D real-time imaging while maintaining comprehensive anatomical visualization for navigation guidance throughout the procedure
3Measurement precision
If shape sensor data is collected continuously, then instrument position tracking is improved, but data reliability deteriorates due to anatomical motion agitating the position data
Solution Approach 1:
The patent introduces a virtual anatomical model as an intermediary reference framework. The instrument's shape sensor data is registered to this stable virtual model rather than being interpreted against moving anatomical structures. This intermediary reference provides a stable coordinate system that maintains data reliability while enabling precise instrument position tracking relative to the anatomy
Solution Approach 2:
The system establishes the virtual anatomical model and instrument registration in advance before anatomical motion begins. By performing the registration when the anatomy is stationary, the system creates a stable reference relationship that remains valid throughout the procedure, ensuring both tracking accuracy and data reliability without requiring continuous re-registration
Data Source
AI summary
A system may comprise a processor and a memory having computer readable instructions stored thereon. The computer readable instructions, when executed by the processor, may cause the system to record shape data from a shape sensor for an instrument during an image capture period and generate a sensor point cloud from the recorded shape data. The computer readable instructions, when executed by the processor, may also cause the system to receive image data from an imaging system during the image capture period, generate an image point cloud for the instrument from the image data, and register the sensor point cloud to the image point cloud.