Endoluminal 3D Reconstruction for Accurate Object Characterization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional imaging techniques, such as fluoroscopy and endoscopic imaging, provide inaccurate two-dimensional representations of objects within a subject's body, leading to discrepancies between preoperative and intraoperative size estimations, which can complicate medical procedures like ureteroscopy.
Innovation Solution
A system that uses an imaging device at the distal end of an endoscope to capture images, reconstructs the object in three-dimensional space, and determines its properties like size and shape in real-time by generating 3D reconstructions based on image and pose data, incorporating techniques like photometric tracking and electromagnetic sensing to track the device's trajectory.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional external imaging techniques like fluoroscopy are used, then imaging can be performed, but accurate size and shape estimation of objects within the body cannot be obtained
Solution Approach 1:
The patent transitions from two-dimensional imaging (fluoroscopy, endoscopic images) to three-dimensional reconstruction by capturing images at multiple viewpoints and generating 3D models. This dimensional change enables accurate measurement of size and shape properties that cannot be obtained from 2D projections alone.
Solution Approach 2:
The system creates a virtual 3D copy or replica of the object within the body by reconstructing it from multiple 2D images. This digital twin allows for accurate measurement and characterization without physically manipulating the original object, enabling precise size and shape estimation.
2Ease of operation
If endoscopic imaging techniques are used to capture images within the lumen, then internal objects can be visualized, but the images are occluded, shadowed, or difficult to measure
Solution Approach 1:
The system overcomes the limitations of 2D endoscopic images by reconstructing 3D models from multiple viewpoints. This transforms the measurement problem from analyzing difficult 2D projections to measuring accurate 3D representations, resolving the contradiction between accessing internal structures and obtaining measurable images.
Solution Approach 2:
The 3D reconstruction acts as an intermediary that bridges the gap between the raw 2D endoscopic images and the required accurate measurements. This intermediate representation eliminates occlusions and shadowing effects present in the original 2D images while maintaining the ability to access internal structures.
3Loss of time
If preoperative characterization is performed, then treatment planning can be established, but discrepancies arise between preoperative and intraoperative characterization
Solution Approach 1:
The system performs 3D reconstruction and accurate characterization during the endoscopic procedure itself, providing real-time or near-real-time measurements. This eliminates the need for separate preoperative and intraoperative characterizations, ensuring consistency while reducing overall preparation time.
Solution Approach 2:
The system provides real-time feedback on object characteristics during the procedure, allowing immediate verification and adjustment of treatment plans. This feedback mechanism ensures characterization consistency between preoperative planning and intraoperative execution, eliminating discrepancies.
4Measurement precision
If 3D reconstruction is performed using multiple images and pose data, then accurate size and shape estimation can be achieved, but the system complexity increases
Solution Approach 1:
The system uses a single imaging device that performs multiple functions: capturing images, tracking pose information, and enabling 3D reconstruction. This multi-functionality reduces the need for separate specialized devices while achieving accurate measurement, thereby managing system complexity.
Solution Approach 2:
The imaging system performs self-characterization by automatically extracting pose data and generating 3D reconstructions without requiring external measurement devices or manual intervention. This self-service capability simplifies the overall system architecture while maintaining high measurement precision.
Data Source
AI summary
The present disclosure provides for determination of object characteristics/properties based at least in part on images captured from within a subject. The object characteristics/properties can include, without limitations, size, weight, and/or shape of the object. An object depicted in the images may be identified and may be reconstructed in three-dimensional (3D) space as a volumetric representation (e.g., a 3D reconstruction of the object). The object characteristics/properties may be estimated based at least in part on the volumetric representation. In some embodiments, a scale associated with the volumetric representation may be determined and applied to the volumetric representation.