Dynamic Registration for Image Guided Surgery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image-guided medical procedures face challenges in accurately registering pre-operative or intra-operative images with real-time anatomical data, leading to suboptimal navigation and precision during minimally invasive procedures due to rigid matching limitations.
Innovation Solution
A method involving a computing system that accesses model points associated with a model space and measured points associated with a patient space, determining weights for matches between them to generate a registration, allowing for flexible and accurate alignment of anatomical structures, and updating registrations based on the distal end location and target anatomic location to account for deformation and movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If rigid matching is used between model points and measured points, then the registration process is simple and fast, but the accuracy and adaptability of the registration deteriorates when anatomical structures deform or move
Solution Approach 1:
The patent implements dynamic registration by continuously updating the transformation parameters between model space and patient space as the medical instrument moves through the anatomical structure. The system adapts the registration in real-time based on measured points collected during instrument insertion, allowing the registration to accommodate deformations and movements of soft tissues rather than relying on a static rigid transformation.
Solution Approach 2:
The system changes the registration parameters dynamically based on the distal end location of the medical instrument and the target anatomic location. By adjusting the transformation parameters according to the current instrument position and anatomical deformation, the system maintains high registration accuracy throughout the procedure without requiring a completely complex re-registration process.
2Adaptability or versatility
If rigid matching is used for registration, then the computational process is efficient, but the ability to account for anatomical deformation and movement deteriorates
Solution Approach 1:
The patent implements dynamic registration by continuously updating the transformation parameters between model space and patient space as the medical instrument moves through the anatomical structure. The system adapts the registration in real-time based on measured points collected during instrument insertion, allowing the registration to accommodate deformations and movements of soft tissues rather than relying on a static rigid transformation.
Solution Approach 2:
The system performs preliminary registration using initial model points and measured points before the procedure begins. This preliminary registration provides a baseline transformation that can be efficiently updated during the procedure, combining the speed of rigid matching with the adaptability to handle deformations as they occur.
3Measurement precision
If traditional registration methods are used, then the system is simple to implement, but the navigation precision during minimally invasive procedures deteriorates
Solution Approach 1:
The patent implements feedback by continuously comparing the location of the medical instrument's distal end with the target anatomic location during the procedure. The system uses measured points collected during instrument insertion to update the registration, creating a feedback loop that corrects for anatomical deformations and movements, thereby maintaining high navigation precision throughout the minimally invasive procedure.
Solution Approach 2:
The system performs preliminary registration using initial model points and measured points before the procedure begins. This preliminary registration provides a baseline transformation that can be efficiently updated during the procedure, combining the speed of rigid matching with the adaptability to handle deformations as they occur.
Data Source
AI summary
A system includes one or more processors configured to read instructions to cause the system to perform operations including accessing a set of model points of a model of an anatomic structure of a patient. The model points is associated with a model space. The operations further include collecting a set of measured points of the anatomic structure of the patient, the measured points being associated with a patient space, determining a set of matches between the set of model points and the set of measured points, determining a first plurality of weights for the set of matches, and registering the set of model points to the set of measured points based on the first plurality of weights to generate a first registration.