Fluoroscopic Pose Estimation Using Markers for 3D Target Reconstruction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for pose estimation in medical imaging, particularly using fluoroscopic devices, are inadequate for real-time, accurate, and robust three-dimensional reconstruction of small soft-tissue objects, requiring costly and radiation-exposing CT scans or expensive Cone-beam CT machines, and standard fluoroscopic images struggle to resolve small soft-tissue targets.
Innovation Solution
A system and method utilizing a structure of markers positioned between the patient and a fluoroscopic imaging device, estimating the device's pose by detecting the most probable projection of the markers, and constructing fluoroscopic-based three-dimensional volumetric data to facilitate navigation of medical devices to targets, using a computing device to display and correct the location of the device relative to the target.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If CT scans or Cone-beam CT machines are used for three-dimensional reconstruction, then measurement precision and reliability are improved, but cost and radiation exposure increase
Solution Approach 1:
A structure of markers is introduced as an intermediary object between the fluoroscopic imaging device and the patient. These markers serve as reference points that enable pose estimation and three-dimensional reconstruction using standard fluoroscopy, thereby avoiding the need for CT scans while maintaining measurement precision.
Solution Approach 2:
The system creates a three-dimensional model by combining multiple two-dimensional fluoroscopic images taken from different poses. By estimating the pose of the imaging device for each image and integrating this information, a virtual three-dimensional representation is constructed without requiring actual three-dimensional scanning, thus reducing radiation exposure.
2Object-affected harmful factors
If standard fluoroscopic imaging is used, then cost and radiation exposure are reduced, but measurement precision and ability to resolve small soft-tissue targets deteriorate
Solution Approach 1:
Markers are placed on or near the patient as intermediary reference objects. These markers provide high-contrast, easily detectable features that enable accurate pose estimation of the fluoroscopic device. The known positions of these markers allow the system to calculate imaging geometry and reconstruct three-dimensional information from standard fluoroscopic images, thereby improving measurement precision without increasing radiation exposure.
3Measurement precision
If real-time imaging is used for accurate target location, then measurement precision is improved, but loss of time and processing complexity increase
Solution Approach 1:
The system performs preliminary pose estimation for each fluoroscopic image as it is captured, rather than waiting for the entire imaging sequence to complete. By estimating the device pose for each image in real-time and accumulating this information, the system provides current target location accuracy without significant time delay.
Solution Approach 2:
The system uses the marker structure and pose estimation algorithm to automatically generate three-dimensional information from standard fluoroscopic images without requiring additional specialized equipment or complex post-processing. The method is self-contained and can be implemented using the existing fluoroscopic system capabilities.
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 fast, accurate, and robust three-dimensional reconstruction of medical targets, reducing radiation exposure and costs by using standard fluoroscopic imaging, allowing safe and precise navigation of medical devices.
Implementation Method 1
two-dimensional fluoroscopic images acquired via a fluoroscopic imaging device
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A system and method for constructing fluoroscopic-based three-dimensional volumetric data of a target area within a patient from two-dimensional fluoroscopic images acquired via a fluoroscopic imaging device.