Shape Sensing Device Control Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Minimally invasive surgery relies heavily on ionizing radiation for image-guided navigation, which poses health hazards due to radiation dosage costs for both patients and healthcare providers, and existing shape sensing technologies integrated with interventional devices require continuous X-ray imaging to monitor device shape changes.
Innovation Solution
A system utilizing shape sensing technologies like Rayleigh scattering or Fiber Bragg gratings in optical fibers integrated with interventional devices to measure shape changes without ionizing radiation, allowing for navigation and control of devices within the body using machine learning models trained on shape measurement data, enabling prediction of anatomical locations and procedure phases without image data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ionizing radiation is used for image-guided navigation, then navigation accuracy is improved, but radiation dosage cost increases
Solution Approach 1:
The patent extracts the shape measurement function from the imaging system by integrating shape sensing capabilities directly into the interventional device. This allows shape and position information to be obtained without relying on external ionizing radiation imaging, thereby reducing radiation dosage while maintaining navigation accuracy
Solution Approach 2:
The patent replaces the mechanical/optical imaging system (X-ray imaging) with a sensing system based on physical principles (Rayleigh scattering, Fiber Bragg gratings) that can measure device shape and position without ionizing radiation, thus eliminating the harmful radiation effect while preserving measurement capability
2Measurement precision
If continuous X-ray imaging is used to monitor device shape changes, then shape measurement accuracy is improved, but radiation dosage cost increases
Solution Approach 1:
The patent extracts shape measurement capability from the X-ray imaging system by integrating shape sensing elements (optical fibers with Rayleigh scattering or Fiber Bragg gratings) directly into the interventional device, enabling continuous shape monitoring without ionizing radiation
Solution Approach 2:
The patent introduces optical fibers with specific physical properties (Rayleigh scattering characteristics or Fiber Bragg grating responses) as intermediary elements that translate device shape changes into measurable optical signals, enabling accurate shape measurement without direct X-ray exposure
3Object-affected harmful factors
If shape sensing with optical fibers is used, then radiation dosage cost is reduced, but navigation control capability may be insufficient
Solution Approach 1:
The patent implements feedback control by using the shape measurement data from optical fibers to provide real-time information about device position and configuration, which is then fed back to the control system to enable precise navigation and adjustment of the interventional device without radiation exposure
Solution Approach 2:
The patent performs preliminary actions by training machine learning models offline using synthetic shape measurement data, enabling the system to make accurate predictions and control decisions during actual procedures without requiring extensive real-time data collection or complex processing
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
This approach reduces reliance on ionizing radiation, enhances navigation efficiency, and allows for precise control of interventional devices within the body by predicting anatomical locations and procedure phases based on shape measurements, thereby minimizing radiation exposure and improving procedural accuracy.
Implementation Method 1
Shape sensing could be based on Rayleigh scattering (enhanced and regular) or Fiber Bragg implementations of one or more shape sensing fibers
Implementation Method 2
Such optical shape sensing elements may include Fiber Bragg gratings, whose optical properties change with strain or shape or temperature
Data Source
AI summary
Computer implemented system (C-SYS) and related methods for controlling one or more devices in a procedure performed in relation to a patient. A shape sensing system is used to acquire shape measurement data. A predictor logic (PL) predicts based on this shape measurements an anatomical location, procedure type, or phase of such a procedure. The System may support navigation of a device in the patient. No imagery need to be acquired during the procedure for navigation. The predictor logic (PL) may be based on a machine learning model. Systems (TS, TDS) and methods for training such as model and for generating training data are also described herein.