Catheter Pose Estimation from Echo Depth Maps in Medical Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for tracking objects of interest in medical imaging using magnetic sensor-enabled catheters are costly due to their invasive nature and disposability, leading to high costs.
Innovation Solution
An apparatus and method for object pose estimation in medical images using a processor and memory to generate echo depth maps, segment them, determine depth data, and create a 3D point cloud, utilizing a pose estimation model trained with 3D point clouds and pose datums.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If magnetic sensor-enabled catheters are used for tracking objects in medical imaging, then tracking precision is improved, but device cost increases and disposability is required
Solution Approach 1:
The patent replaces expensive magnetic sensors with a visual copying approach using 2D echocardiographic images. The system creates a visual representation (copy) of the catheter's position and orientation by detecting the catheter's acoustic signature in echo images, then processes this visual information to determine pose. This eliminates the need for expensive magnetic sensors while maintaining tracking precision.
Solution Approach 2:
The patent substitutes the magnetic field-based tracking system with an acoustic/optical system. Instead of using magnetic sensors that detect magnetic fields, the system uses echocardiographic imaging (acoustic waves) to visualize and track the catheter. This replacement eliminates the need for disposable magnetic sensor-enabled devices while achieving the same tracking function.
2Measurement precision
If disposable magnetic sensor catheters are used, then tracking accuracy is maintained, but surgical cost increases
Solution Approach 1:
The patent inverts the disposable concept: instead of making the catheter itself disposable with embedded magnetic sensors, the system uses a reusable echocardiographic imaging system. The catheter can be reused, while the imaging system provides continuous tracking, thereby reducing overall surgical costs while maintaining tracking accuracy.
Solution Approach 2:
The echocardiographic imaging system serves multiple functions: it provides both the primary imaging for cardiac procedures and simultaneously tracks the catheter position. This multi-functionality eliminates the need for separate expensive magnetic tracking systems, reducing surgical costs while maintaining tracking accuracy.
3Ease of operation
If magnetic sensors are embedded in catheters, then object tracking is enabled, but invasiveness and surgical risk increase
Solution Approach 1:
The patent introduces an intermediary approach: instead of directly embedding sensors in the catheter, the system uses the echocardiographic images as an intermediary to detect and track the catheter. The imaging system acts as a mediator that indirectly observes the catheter's position through its acoustic properties, eliminating the need for invasive sensor embedding.
Solution Approach 2:
The patent replaces the invasive mechanical embedding of magnetic sensors with a non-invasive acoustic imaging approach. The echocardiographic system uses sound waves to visualize and track the catheter externally, eliminating the need to modify the catheter with embedded sensors and thereby reducing surgical risks.
Data Source
AI summary
Apparatus and method for object pose estimation are disclosed. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to receive a plurality of sets of echo data, wherein the plurality of sets of echo data is configured for generation of a plurality of echo depth maps, segment the plurality of echo depth maps, determine a depth datum related to pixels of an object of interest as a function of the plurality of segmented echo depth maps, generate a three dimensional (3D) point cloud related to the object of interest as a function of the depth datum and generate a pose datum of the object of interest as a function of the 3D point cloud.