Optical Sensor Coordinate Calibration Using Patient-Table Keypoints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current calibration methods for optical sensor systems in medical imaging require large phantoms that are cumbersome to store and use, leading to potential errors and reduced precision, and necessitate field service personnel, complicating the installation and calibration process.
Innovation Solution
A method using a keypoint detection module to calibrate the optical sensor system's coordinate system with the medical imaging system by detecting keypoint elements on the patient table, eliminating the need for additional phantoms and enabling remote, automated calibration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a large calibration phantom is used to cover the field of view, then calibration precision is improved, but storage and handling become difficult
Solution Approach 1:
The calibration target is extracted from a separate physical phantom and integrated directly into the patient table structure. Keypoint elements are embedded in the table itself, eliminating the need for a separate large phantom while maintaining calibration precision across the entire field of view.
Solution Approach 2:
The calibration function is merged with the patient table by integrating keypoint elements directly into the table structure. This combination allows the table to serve dual purposes: patient support and calibration reference, eliminating the need for separate phantom storage and handling.
2Measurement precision
If a large calibration phantom is used, then calibration precision is improved, but storage space requirements increase
Solution Approach 1:
The calibration functionality is extracted from a separate large phantom and integrated into the patient table. This eliminates the need for additional storage space for a separate phantom while maintaining the precision required for full field of view calibration.
Solution Approach 2:
The patient table is given multiple functions: it serves as both the patient support structure and the calibration reference. The keypoint elements embedded in the table provide calibration functionality without requiring additional dedicated calibration equipment or storage space.
3Ease of manufacture
If individual parts of the calibration phantom are connected using adhesives, then assembly is enabled, but misalignments and errors occur
Solution Approach 1:
The calibration elements are merged into the patient table as an integrated structure rather than separate parts requiring assembly. This eliminates the need for adhesives and potential misalignments while maintaining ease of manufacture through modular table design.
4Measurement precision
If field service personnel are required for calibration, then proper calibration can be ensured, but installation complexity and time increase
Solution Approach 1:
The system enables self-service calibration by automatically detecting the keypoint elements on the patient table and computing transformation parameters without requiring field service personnel. The computing device performs the calibration autonomously, reducing installation complexity while maintaining precision.
Solution Approach 2:
The keypoint detection module uses advanced image processing and pattern recognition algorithms to rapidly and accurately identify calibration elements, accelerating the calibration process and eliminating the need for manual intervention by service personnel.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
Disclosed herein is a method for calibrating a first coordinate system of a field of view of an optical sensor system (140). The calibrating comprises a registering of the first coordinate system with a second coordinate system of a medical imaging system (100) using a keypoint detection module (412). The keypoint detection module (412) is configured for detecting as output keypoint elements (122) of a patient table (120) of the medical imaging system (100) within optical sensor data (414) in response to receiving the optical sensor data (414). The method comprises determining three-dimensional coordinates values descriptive of positions of detected keypoint elements (122) within the first coordinate system and receiving three-dimensional coordinates values descriptive of the positions of the detected keypoint elements (122) within the second coordinate system. One or more transformation parameters (420) are determined for a transformation from the first coordinate system to the second coordinate system.