Photogrammetry for Intraoperative Orthopedic Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current orthopedic joint replacement surgeries face challenges in accurately aligning and sizing orthopedic elements and endoprosthetic implants due to limited visualization of the operative area, especially in minimally invasive procedures.
Innovation Solution
The use of a deep learning network to identify orthopedic elements and components of endoprosthetic implants, and to map these elements to spatial data from two-dimensional input images taken from different transverse positions, allowing for accurate calculation of their positions in three-dimensional space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If minimally invasive surgical procedures are used, then patient trauma and recovery time are reduced, but the surgeon's visual field is severely limited
Solution Approach 1:
The patent creates a virtual 3D copy of the patient's anatomy using photogrammetry and image registration techniques. Multiple 2D images taken during surgery are registered and reconstructed into a 3D model that replicates the patient's bone structure, allowing the surgeon to visualize and measure anatomical structures without direct line-of-sight
Solution Approach 2:
The patent transitions from 2D images to 3D visualization by registering multiple 2D images taken from different angles and reconstructing them into a three-dimensional model. This dimensional transformation allows the surgeon to view anatomical structures in 3D space while working through a minimally invasive portal incision
2Ease of operation
If external indicia and positioning guides are used, then alignment estimation is possible, but accuracy is compromised due to soft tissue movement and patient repositioning
Solution Approach 1:
The patent replaces mechanical positioning guides and external indicia with a computational image registration system. Instead of relying on physical guides that move with soft tissue, the system uses image matching algorithms to track anatomical landmarks through soft tissue deformation and patient repositioning, substituting mechanical measurement with optical-digital measurement
Solution Approach 2:
The patent introduces image registration as an intermediary between the physical anatomical structures and the surgical instrumentation. The registration process creates a virtual reference frame that mediates the relationship between the moving soft tissues and the fixed surgical guides, allowing accurate alignment estimation despite tissue movement
3Object-affected harmful factors
If traditional 2D imaging is used, then radiation exposure is reduced, but three-dimensional spatial information is lost
Solution Approach 1:
The patent merges multiple 2D images taken from different angles into a unified 3D spatial model through image registration. By combining information from multiple 2D projections, the system reconstructs three-dimensional anatomical structures without requiring a single 3D imaging modality that would increase radiation exposure
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 enables precise alignment and sizing of orthopedic elements and endoprosthetic implants, reducing the risk of misalignment and improving the accuracy and longevity of the implants, while also reducing the need for excessive radiation.
Implementation Method 1
Systems and methods of using photogrammetry for intraoperatively aligning surgical elements
Data Source
AI summary
Systems and methods for ascertaining a position of an orthopedic element in space comprising: capturing a first and second images of an orthopedic element in different reference frames using a radiographic imaging technique, detecting spatial data defining anatomical landmarks on or in the orthopedic element using a deep learning network, applying a mask to the orthopedic element defined by an anatomical landmark, projecting the spatial data from the first image and the second image to define volume data, applying the deep learning network to the volume data to generate a reconstructed three-dimensional model of the orthopedic element; and mapping the three-dimensional model of the orthopedic element to the spatial data to determine the position of the three-dimensional model of the orthopedic element in three-dimensional space.