Scan Protocol Mapping via Keyword Scoring Algorithm

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current scan protocols lack standardization across different countries and institutions, making it difficult to compare and establish national or international registries, particularly in radiology, where manual mapping of protocols is cumbersome and time-consuming.

Innovation Solution

A method for mapping user-created scan protocols to standardized protocols using a keyword scoring algorithm, which extracts textual parameters, generates a combined dataset, determines keyword scores, and selects the most relevant standardized protocol from a database like RadLex playbook, facilitating harmonization and consistency across institutions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual mapping of scan protocols is performed, then mapping accuracy can be maintained, but time consumption and labor costs increase significantly

Engineering Contradiction:
Improvemapping accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent introduces an automated mapping system that acts as an intermediary between scan protocols and standardized protocols. This system uses natural language processing and keyword scoring algorithms to automatically extract meaningful parameters from protocol names and descriptions, generating mapping suggestions that reduce manual work while maintaining accuracy through radiologist review.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual mechanical process of protocol mapping with an automated computational system. The system uses text analysis algorithms, keyword scoring, and database matching to automatically generate mapping recommendations, substituting human manual effort with automated information processing while maintaining quality through hybrid human-machine verification.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If standardized scan protocols are implemented across institutions, then comparability and registry establishment improve, but implementation complexity and standardization requirements increase

Engineering Contradiction:
ImprovecomparabilityVSAvoidstandardization complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal mapping system that can handle multiple types of scan protocols from different institutions and modalities. The system uses a standardized protocol database (RadLex) that serves as a common reference framework, allowing diverse local protocols to be mapped to universal standards, enabling cross-institutional comparability without requiring each institution to develop their own standards.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent transforms protocol information from unstandardized local formats to standardized formats by changing key parameters such as protocol naming conventions, anatomical region classifications, and modality descriptors. The system identifies and standardizes these critical parameters while preserving essential local variations, reducing implementation complexity through focused parameter standardization rather than complete protocol replacement.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If automated mapping systems are used, then time efficiency improves, but mapping precision and reliability may deteriorate

Engineering Contradiction:
Improvemapping efficiencyVSAvoidmapping reliability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent implements a feedback mechanism where automated mapping suggestions are presented to radiologists for review and confirmation. The system learns from radiologist corrections and feedback, continuously improving its mapping accuracy. This hybrid approach maintains high productivity through automation while ensuring reliability through human expertise validation, creating a self-improving system that combines the speed of automation with the judgment of specialists.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20240194327A1Computer-implemented method for mapping a scan protocol for scanning a patient to a standardized scan protocol
Publication Date: 2024.06.13 SIEMENS HEALTHINEERS AG
  • US20240194327A1 patent drawing
  • US20240194327A1 patent drawing

AI summary

A computer-implemented method comprises receiving a scan protocol, wherein the scan protocol comprises protocol information pertaining to a set of imaging parameters for imaging a patient; extracting at least one textual protocol parameter from the received scan protocol; generating a combined dataset based on the extracted textual protocol parameters; determining at least one keyword score, the determining the at least one keyword score includes applying a keyword scoring algorithm to the combined dataset to determine the at least one keyword score; determining a selected standardized scan protocol based on the at least one keyword score, the determining the selected standardized scan protocol includes selecting the selected standardized scan protocol out of a plurality of standardized scan protocols; mapping the scan protocol to the selected standardized scan protocol; and providing the mapping of the scan protocol to the selected standardized scan protocol.