Radiographic Posture Analysis Using Exposure Field-Based Body Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In radiographic imaging, determining the suitability of the imaging posture of an object becomes unstable when multiple individuals appear in the optical image, especially in varying lighting conditions, leading to potential misidentification of the object and incorrect imaging.
Innovation Solution
An information processing apparatus that utilizes a trained machine learning model to analyze optical images, identify human body parts, and determine the suitability of the imaging posture by comparing the detected human body parts with imaging order information, ensuring accurate alignment and orientation of the object within the radiation exposure field.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple persons appear in the optical image during radiographic imaging, then the imaging support can cover more scenarios (e.g., technician supporting patient), but the object recognition stability deteriorates leading to misidentification
Solution Approach 1:
The patent extracts and isolates the target object from the optical image by analyzing the radiation exposure field information. The processing unit identifies which detected human body part corresponds to the object by comparing its position with the radiation exposure field, effectively separating the target object from other persons (e.g., technicians) in the image. This resolves the contradiction by maintaining versatility in handling multiple persons while ensuring reliable object identification through field-based extraction.
Solution Approach 2:
The patent introduces the radiation exposure field as an intermediary element to bridge the optical image and the actual target object. By using the radiation exposure field information (obtained from imaging order information) as a reference, the system can accurately identify which human body part in the optical image corresponds to the object, even when multiple persons are present. This intermediary mechanism maintains both versatility and reliability.
2Adaptability or versatility
If the contrast between background and object decreases in varying lighting conditions, then the imaging can adapt to different lighting environments, but the object detection precision deteriorates
Solution Approach 1:
The radiation exposure field acts as an intermediary reference that is independent of lighting conditions. By comparing the position of detected human body parts with the radiation exposure field information, the system can accurately identify the target object regardless of background contrast variations. This resolves the contradiction by maintaining lighting adaptability while ensuring detection precision through field-based verification.
3Difficulty of detecting and measuring
If a person other than the object is recognized as the object, then the detection system is sensitive to all human bodies, but the imaging accuracy deteriorates due to incorrect identification
Solution Approach 1:
The patent extracts the correct target object from among multiple detected human bodies by using radiation exposure field information as a selection criterion. The processing unit compares the position of each detected human body part with the radiation exposure field to identify which one is the actual object. This resolves the contradiction by maintaining high detection sensitivity (detecting all human bodies) while ensuring imaging accuracy (selecting only the correct object).
Solution Approach 2:
The system uses radiation exposure field information as feedback to verify and correct object identification. By continuously comparing detected human body positions with the expected radiation exposure field, the system can identify and correct misidentifications, ensuring that the final object recognition is accurate even when multiple persons are present.
Data Source
AI summary
An information processing apparatus according to an embodiment of the present disclosure includes at least one memory storing instructions; and at least one processor that, upon execution of the instructions, is configured to operate as: an acquisition unit configured to acquire imaging order information and an optical image related to radiographic imaging, an identification unit configured to identify a radiation exposure field using the imaging order information and the optical image, a detection unit configured to detect a human body part in the optical image, and an analysis unit configured to, when a plurality of human body parts is detected in the optical image, analyze a human body part closest to the radiation exposure field using the optical image.