Procedure Navigation With Hybrid Tracking and AI Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation systems for procedures, such as surgical and assembling procedures, face challenges in accurately tracking and illustrating the pose of instruments relative to a subject, particularly in obstructed views, and in efficiently segmenting anatomical structures for procedural planning.
Innovation Solution
A navigation system that combines electromagnetic and optical tracking with machine learning algorithms, specifically convolutional neural networks, to automatically segment anatomical features like vertebrae, and track instruments in real-time, enabling precise pose determination and procedural planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning algorithms are used to automatically segment anatomical structures, then segmentation efficiency and accuracy are improved, but computational complexity and processing time requirements increase
Solution Approach 1:
The system performs preliminary segmentation of anatomical structures using machine learning algorithms before the actual procedure. Pre-trained models process preprocessed image data to automatically identify and segment relevant anatomical regions, reducing real-time computational burden while maintaining high accuracy in anatomical structure identification
2Measurement precision
If electromagnetic and optical tracking systems are combined, then tracking accuracy in obstructed views is improved, but system complexity and cost increase
Solution Approach 1:
The system merges electromagnetic tracking and optical tracking systems to provide redundant and complementary tracking capabilities. The electromagnetic tracking provides robust tracking through obstructed views while optical tracking provides precise positional information, and the fusion of these systems enables accurate instrument pose determination in challenging environments where either system alone would fail
Solution Approach 2:
The system uses an intermediary processing layer that fuses data from both electromagnetic and optical tracking systems. This intermediary layer reconciles differences between the two tracking methods and produces a unified, accurate pose estimation that leverages the strengths of both tracking technologies while mitigating their individual weaknesses
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 tracking and illustration of instrument pose relative to anatomical structures, facilitating efficient and automated procedural planning and execution, even in obstructed views.
Implementation Method 1
The sensor coil may include a conductive material that is placed within an EM field where a current is induced in the sensor coil. The measured induced current may be used to identify or determine a position of the instrument or object.
Data Source
AI summary
Disclosed is a system to assist in a procedure. During the procedure an object may be moved relative to a subject, such as being positioned and/or placed within a subject. The system and related method may be used to assist in displaying and/or determining a pose of the object relative to a subject, such as rigid portions of a subject.