Radiographic Couch Accessory Position Verification Using Instance Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inconsistent or inappropriate use of accessories with radiographic imaging apparatus couches leads to suboptimal patient imaging outcomes, affecting image quality and radiation dose.
Innovation Solution
A computer-implemented method using an instance segmentation model, such as Mask R-CNN, to determine the type and position of couch accessories by processing imaging data, comparing actual positions with specified positions, and providing alerts for corrections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual monitoring of couch accessory positioning is used, then operational flexibility is maintained, but positioning accuracy and consistency deteriorate
Solution Approach 1:
The patent replaces manual mechanical monitoring with an automated computer vision system using imaging devices and processing circuits to detect and verify accessory positioning, eliminating human error while maintaining system simplicity
Solution Approach 2:
The system performs self-verification by automatically detecting accessory positions and comparing them against expected positions, enabling the system to monitor itself without external intervention
2Reliability
If couch accessories are not properly positioned, then setup speed is maintained, but image quality and radiation dose deteriorate
Solution Approach 1:
The system performs preliminary verification of accessory positioning before imaging begins, ensuring correct setup is achieved quickly without delaying the actual imaging process
Solution Approach 2:
The system provides real-time feedback on accessory positioning status, allowing operators to correct positioning issues immediately without repeating entire setup procedures
3Measurement precision
If automated accessory detection is implemented, then positioning accuracy improves, but false detection errors may increase
Solution Approach 1:
The patent introduces an intermediary verification layer where detected accessory information is cross-checked against expected positioning data before final confirmation, reducing false detections while maintaining high accuracy
Data Source
Figure 1~2
Figure 3a
Figure 3b
AI summary
In an embodiment, a method (100) is described. The method is a computer- implemented method. The method comprises receiving (102): imaging data of a region comprising a radiographic imaging apparatus couch; and an indication of a specified number, type and position of at least one couch accessory associated with use of the radiographic imaging apparatus couch by a subject. The method further comprises determining (104) a type and position of at least one target object in the region using an instance segmentation model for processing the imaging data. Determining the type of the at least one target object comprises determining whether or not the at least one target object is a type of couch accessory specified by the indication. The method further comprises comparing (106) the determined position of the at least one target object that is determined to be the type of couch accessory specified by the indication with the indicated specified position for the couch accessory. The method further comprises, in response to determining that the determined position of the at least one target object does not correspond to the indicated specified position for the couch accessory, indicating (108) that the couch accessory is incorrectly positioned.