Fluoroscopic 3D Target Marking with Multi-Angle Image Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical imaging technologies, such as standard fluoroscopy, struggle to accurately identify and mark small soft-tissue targets in real-time fluoroscopic three-dimensional reconstructions due to the challenges of deformation during procedures and the limitations of two-dimensional projections, necessitating costly and cumbersome CT or cone-beam CT scans.
Innovation Solution
A system and method for facilitating the identification and marking of targets in fluoroscopic three-dimensional reconstructions by receiving initial and final user selections at multiple angles, utilizing two-dimensional fluoroscopic images and potentially CT or MRI scans, to enhance accuracy and navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If standard fluoroscopy is used for real-time imaging, then real-time navigation capability is improved, but target identification accuracy deteriorates due to difficulty resolving small soft-tissue objects
Solution Approach 1:
The system merges standard fluoroscopy imaging with CT scan data to create a composite navigation system. The fluoroscopy provides real-time imaging capability while the CT data provides detailed anatomical structure information, combining the strengths of both modalities to achieve both real-time navigation and accurate target identification.
Solution Approach 2:
The system introduces an intermediary processing layer that registers fluoroscopic images with pre-acquired CT data. This intermediary registration process aligns the real-time fluoroscopy images with the high-resolution CT anatomical structures, enabling accurate target identification in the fluoroscopic view through the mediator of image registration.
2Measurement precision
If CT or cone-beam CT scans are used for 3D reconstruction, then target visualization accuracy is improved, but device complexity and cost worsen
Solution Approach 1:
The system creates a virtual 3D copy of the anatomical structures from pre-acquired CT scan data. Instead of requiring complex cone-beam CT hardware during the procedure, the system uses software-based 3D reconstruction and rendering of the CT data, allowing accurate target visualization without the complexity of dedicated 3D imaging equipment in the operating room.
Solution Approach 2:
The system performs the complex 3D imaging action in advance by acquiring CT scans before the procedure. This preliminary acquisition of detailed anatomical data eliminates the need for complex real-time 3D imaging equipment during the procedure, reducing device complexity while maintaining accurate target visualization capability.
3Ease of manufacture
If previously acquired CT data is used for navigation, then navigation planning is improved, but navigation accuracy deteriorates due to deformation during procedure
Solution Approach 1:
The system implements feedback by continuously comparing pre-acquired CT data with real-time fluoroscopic images during the procedure. This feedback mechanism detects deformations and anatomical changes, allowing the system to adjust the navigation plan accordingly and maintain accuracy despite tissue deformation, breathing, or patient movement.
Solution Approach 2:
The system transitions from static pre-operative CT data to dynamic real-time navigation by integrating fluoroscopic imaging throughout the procedure. This dynamic approach allows the navigation system to adapt to changing anatomical conditions, accommodating breathing, heartbeats, and tissue deformation while maintaining navigation accuracy.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
A method and system for facilitating identification and marking of a target in a displayed Fluoroscopic Three-Dimensional Reconstruction (F3DR) of a body region of a patient. The system includes a display and a storage device storing instructions for receiving an initial selection of the target in the F3DR, fining the F3DR based on the initial selection of the target, displaying the fined F3DR on the display, and receiving a final selection of the target in the fined F3DR via a user selection. The system further includes at least one hardware processor configured to execute said instructions. The method and instructions may also include receiving a selection of a medical device in two two dimensional fluoroscopic images, where the medical device is located in an area of the target, and initially fining the F3DR based on the selection of the medical device.