Single-Camera Medical Device Pose Estimation Under Occlusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical device tracking methods, such as stereo-based optical tracking and electromagnetic tracking, are costly and prone to occlusion errors, especially when using markers or general object tracking in medical environments with complex shapes and occlusions.
Innovation Solution
A single camera-based system for medical device pose estimation that uses a color depth camera to detect and track medical devices like ultrasound transducers without markers, employing image processing and machine learning to segment and match features against templates, while accounting for occlusions by modeling the occluding objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If stereo-based optical tracking with markers is used, then tracking precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts and removes the markers from the tracking system, using only the medical device itself as the tracking target. The system processes images to directly identify and track the medical device without requiring additional marker components, thereby simplifying the device while maintaining tracking capability
Solution Approach 2:
The patent makes the medical device itself serve dual functions: both its medical function and its tracking function. The device body is used for both treatment/diagnosis and for pose estimation, eliminating the need for separate marker components and achieving multi-functionality
2Measurement precision
If markers are added to the medical device, then tracking precision is improved, but cost increases
Solution Approach 1:
The patent removes the marker component entirely from the system, using only the medical device body for tracking. This extraction eliminates the cost of markers while maintaining tracking precision through advanced image processing algorithms
Solution Approach 2:
The medical device serves its own tracking needs without requiring external markers. The device body itself provides the visual features necessary for pose estimation, making the system self-sufficient and eliminating additional manufacturing costs
3Device complexity
If general object tracking is used, then device complexity is reduced, but measurement precision deteriorates due to occlusion
Solution Approach 1:
The patent performs preliminary segmentation of the medical device from the background and occluding objects before pose estimation. By pre-processing the image to isolate the device, the system maintains high tracking precision even when the device is partially occluded during the procedure
Solution Approach 2:
The patent introduces image processing algorithms as an intermediary between the camera and the tracking system. These algorithms process the raw images to extract and identify device features, serving as a mediator that enables accurate tracking despite occlusions and complex backgrounds
4Device complexity
If a single camera is used, then device complexity and cost are reduced, but tracking reliability deteriorates due to occlusion
Solution Approach 1:
The system performs preliminary segmentation and identification of the medical device from the single camera image before pose estimation. This pre-processing step ensures that even with occlusion, the device can be reliably identified and tracked
Solution Approach 2:
The patent replaces the mechanical/stereo camera system with a single camera combined with advanced image processing algorithms. The computational methods substitute for the physical redundancy of multiple cameras, maintaining tracking reliability while reducing hardware complexity
Data Source
AI summary
The pose of medical device in use, where the device may be occluded, is estimated using a single camera. Multiple cameras and/or a marker are not needed. The medical device is detected in the camera image during use to determine the pose. Various further approaches may be used to deal with occlusion. Comparison with a template for that type of medical device may be used to deal with occlusion. Modeling the occlusion, such as the hand, may be used to deal with occlusion.