Scanner Control via Organ Surface Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Medical imaging technologies face challenges in accurately determining the location of internal organs within patients, leading to unnecessary radiation exposure and time-consuming manual positioning processes due to variations in patient body shapes and sizes.
Innovation Solution
A system utilizing machine learning to predict the surface of internal organs based on body surface data collected by depth sensors, enabling precise control of medical imaging scanners to optimize scan positioning and reduce radiation exposure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual positioning is used to determine internal organ location, then positioning accuracy can be achieved, but time consumption and operational complexity increase
Solution Approach 1:
The patent replaces the manual mechanical positioning process with an automated optical sensing and machine learning system. Depth sensors capture body surface geometry, and machine learning algorithms automatically predict internal organ locations, eliminating the need for manual technician positioning while maintaining or improving accuracy.
Solution Approach 2:
The system creates a digital 3D model (copy) of the patient's body surface using depth sensors. This digital model is then processed by machine learning algorithms to infer the location of internal organs, replacing the need for direct manual measurement and positioning of actual organs.
2Object-affected harmful factors
If low-dose topogram images are used to determine organ location, then radiation exposure is reduced, but additional radiation is still required and positioning remains time-consuming
Solution Approach 1:
The patent extracts the body surface geometry information using non-ionizing depth sensors (such as structured light or time-of-flight cameras). This extraction method completely eliminates the need for ionizing radiation-based topogram images while providing sufficient data for organ location prediction.
Solution Approach 2:
The system introduces body surface geometry as an intermediary between external observation and internal organ location. Instead of using radiation-based imaging to directly view organs, the system uses safe optical sensors to capture surface data, which then serves as a mediator for inferring internal structures through machine learning.
3Ease of operation
If manual positioning by technicians is performed, then positioning can be adjusted, but operational complexity and cost increase
Solution Approach 1:
The system enables self-service automated positioning by having the machine learning algorithms automatically determine optimal scan positions based on predicted organ locations. The system independently performs tasks that previously required trained technicians, reducing operational complexity while maintaining positioning quality.
Solution Approach 2:
The system changes the operational parameters from manual visual assessment and physical adjustment to automated digital processing. By transforming the positioning task into a computational problem solved by machine learning, the system reduces the skill level required for operation while maintaining or improving positioning accuracy.
Data Source
AI summary
A method for controlling a scanner comprises: sensing an outer surface of a body of a subject to collect body surface data, using machine learning to predict a surface of an internal organ of the subject based on the body surface data, and controlling the scanner based on the predicted surface of the internal organ.