MRI Scanning Procedure Inference for Faster Protocol Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing MRI scanning procedure selection process is time-consuming and requires manual selection based on technician experience, especially when using mobile devices or without a Radiology Information System (RIS), leading to inefficiencies.
Innovation Solution
A method and apparatus that pre-acquire historical scanning data, establish a scanning procedure inference model, and infer a recommended procedure list based on the patient's request information, providing a list with probabilities for user selection, optionally pre-filling the highest probability option.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the technician manually selects the scanning procedure through the traditional multi-layer selection process (protocol tree map, area, examination, procedure), then the selection can be made based on technician experience and professional judgment, but the process is time-consuming and reduces productivity
Solution Approach 1:
The system performs preliminary actions by pre-acquiring historical scanning data and establishing an inference model before the actual scanning procedure selection. The model pre-processes and structures historical data with standardized field descriptions, so when a scanning request comes in, the system can quickly retrieve and recommend appropriate procedures without requiring manual navigation through multiple selection layers.
Solution Approach 2:
The system enables self-service by automatically inferring and generating scanning procedure recommendations based on the patient's scanning request information. The inference model autonomously processes the request, performs matching retrieval from historical data, and provides a ranked recommendation list without requiring the technician to manually navigate through protocol trees or make selections based on experience alone.
2Adaptability or versatility
If the technician uses mobile devices (e.g., touch tablets) for patient registration, then mobility and flexibility are improved, but the time to find and select procedures increases due to the complex selection interface
Solution Approach 1:
The system extracts the essential selection logic from the complex multi-layer interface and presents only the necessary information to the technician. Instead of requiring navigation through protocol trees, areas, examinations, and procedures, the system extracts the key matching parameters from the scanning request and directly presents a ranked list of recommended procedures, significantly reducing the time needed on mobile devices.
Solution Approach 2:
The system changes the parameters of the selection process by transforming the traditional hierarchical navigation interface into a recommendation-based interface. The inference model processes scanning request parameters, matches them against historical data with standardized field descriptions, and outputs procedure recommendations with recommendation probabilities, fundamentally changing how procedure selection is performed on mobile devices.
3Reliability
If the scanning procedure selection relies on technician experience rather than automated systems, then professional judgment is maintained, but the process requires manual intervention and reduces automation extent
Solution Approach 1:
The system implements feedback by using historical scanning data that includes actual scanning procedures performed in the past. The inference model learns from this historical feedback, continuously improving its recommendation accuracy by analyzing patterns in successful procedure selections. The system provides recommendation probabilities that reflect the confidence level based on historical matching, allowing technicians to make informed decisions while maintaining professional judgment.
Data Source
AI summary
A method and apparatus for determining a scanning procedure, including: pre-acquiring historical scanning data including scanning request information and scanning procedures, and establishing a scanning procedure inference model based on the historical scanning data; receiving scanning request information of a current patient, and inferring using the scanning procedure inference model based on the scanning request information to obtain a scanning procedure recommendation list including different recommendation probabilities; and providing the scanning procedure recommendation list to a user for selection.