Image Scanning With Motion-Cycle Gating
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Magnetic resonance (MR) scanning of movable subjects often results in inaccurate images due to discrepancies between the default and actual motion cycles, leading to resource waste and reduced efficiency, as re-scanning is required to meet image quality standards.
Innovation Solution
A system and method that utilize a scanning device to acquire image data, determine a subject's motion state and physiological signals, and calibrate scan gating information to optimize image capture based on a trained machine learning model, enabling precise image acquisition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a default motion cycle is used for scanning trigger, then the scanning process is simple and fast, but the image quality deteriorates when there is significant difference between default and actual motion cycles
Solution Approach 1:
The system performs preliminary action by acquiring image data and determining motion states before the actual scanning process. A trained machine learning model analyzes the image data to identify the subject's actual motion cycle characteristics in advance, allowing the system to pre-calculate accurate scan gating information that matches the subject's real motion pattern, thereby avoiding the need for re-scanning.
Solution Approach 2:
The system implements feedback by using the determined motion state and physiological signals to continuously optimize the scan gating information. The machine learning model processes the image data and physiological signals to provide feedback on the actual motion cycle, which is then used to adjust and refine the scanning trigger timing, ensuring accurate image capture while maintaining scanning efficiency.
2Manufacturing precision
If re-scanning is performed to meet image quality requirements, then image quality improves, but resource waste increases and work efficiency decreases
Solution Approach 1:
The system performs preliminary analysis of motion states and physiological signals before scanning to pre-determine accurate scan gating information. This preliminary action ensures that the first scanning attempt captures images at the correct motion phase, eliminating the need for re-scanning and avoiding resource waste while maintaining high work efficiency.
Solution Approach 2:
The system applies parameter changes by dynamically adjusting the scan gating information based on the determined motion state and physiological signals. The machine learning model optimizes scanning parameters such as trigger timing and gating thresholds to match the subject's actual motion characteristics, ensuring high image quality is achieved in a single scan without requiring re-scanning.
3Device complexity
If scan gating information is determined without considering actual motion state, then the scanning process is simple, but the scanning trigger accuracy deteriorates
Solution Approach 1:
The system replaces the traditional mechanical or fixed-timing scanning trigger mechanism with an intelligent system based on machine learning and physiological signal analysis. The trained model automatically determines scan gating information by analyzing image data and physiological signals, substituting complex computational processing for simple fixed timing, thereby achieving high trigger accuracy while keeping the overall process streamlined.
Solution Approach 2:
The system implements self-service by enabling the scanning system to automatically determine its own optimal trigger timing through analysis of the subject's motion state and physiological signals. The machine learning model processes the acquired data and autonomously generates accurate scan gating information without requiring manual intervention or complex external calibration, improving trigger accuracy while maintaining process simplicity.
Data Source
AI summary
Embodiments of the present disclosure provide a method and a system for image scanning. The method may include: obtaining image data of a subject, the image data being acquired by a scanning device scanning the subject during a time period; determining, based on the image data, a motion state of the subject in a motion cycle; obtaining a physiological signal of the subject in the motion cycle; determining, based on the motion state of the subject and the physiological signal of the subject, scan gating information of the subject; and determining, based on the scan gating information, target image data of the subject.