Machine Learning MRI Protocol Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The manual selection of MRI imaging protocols is time-consuming and often results in non-ideal diagnostic information or unnecessary scans, especially in emergency situations, due to the complexity of adapting protocols to individual patient needs and clinical questions, which can lead to inefficiencies and reduced diagnostic quality.

Innovation Solution

A method utilizing a machine learning model to suggest optimal MRI imaging protocols based on prior knowledge of clinical questions, patient conditions, and physician preferences, trained on historical data and operator feedback to automate the selection process, reducing the need for operator intervention and improving diagnostic quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual selection of MRI imaging protocols is used, then flexibility in adapting to individual patient needs is improved, but time consumption and operational complexity increase significantly

Engineering Contradiction:

Improveadaptability to individual patient needsVSAvoidtime for protocol selection and tuning

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system enables self-service by allowing the imaging system to automatically select and configure appropriate imaging protocols based on patient data and clinical questions, eliminating the need for manual technologist intervention in protocol selection while maintaining adaptability to individual patient needs

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of technologist selection and adjustment is replaced by an automated computer-based system that uses machine learning models and algorithms to automatically select and configure imaging protocols, substituting human cognitive work with computational processes

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If manual adaptation of protocols is performed, then diagnostic quality can be optimized, but operator training requirements and operational difficulty increase

Engineering Contradiction:

Improvediagnostic qualityVSAvoidease of protocol selection

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system performs self-service by automatically optimizing protocol selection based on patient characteristics and clinical requirements, eliminating the need for operator expertise in manual protocol selection while maintaining high diagnostic quality through algorithmic optimization

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system incorporates feedback mechanisms that learn from historical imaging data and outcomes to continuously improve protocol selection, using feedback loops to refine the machine learning models and enhance diagnostic quality over time without increasing operational complexity

Inventive Principle:

Principle #23Feedback

3Manufacturing precision

If extensive protocol tuning is performed, then image quality is improved, but the number of necessary adjustments and system complexity increase

Engineering Contradiction:

Improveimage qualityVSAvoidprotocol configuration complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary action by pre-configuring and pre-optimizing imaging protocols based on patient data before the actual imaging process, automatically selecting the most appropriate protocol parameters in advance to ensure high image quality without requiring complex real-time adjustments

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system automatically adjusts imaging parameters based on patient-specific factors and clinical questions, dynamically changing protocol parameters such as sequence type, field of view, and contrast settings to optimize image quality while simplifying the overall configuration process through automated parameter selection

Inventive Principle:

Principle #35Parameter changes

4Productivity

If automated protocol selection is implemented, then time efficiency and productivity are improved, but the system requires advanced technology and initial setup complexity

Engineering Contradiction:

Improveexamination throughputVSAvoidsystem technology complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system achieves universality by designing a multi-functional automated protocol selection platform that handles various imaging scenarios, patient types, and clinical questions through a single integrated system, eliminating the need for multiple specialized systems while maintaining high productivity across diverse applications

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system performs preliminary setup and training of machine learning models using historical data before deployment, preparing the automated selection system in advance to ensure high productivity from the start while managing initial complexity through pre-processing and pre-training phases

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11574728B2Method for enabling magnetic resonance imaging of a subject

Publication Date: 2023.02.07 KONINKLIJKE PHILIPS NV

AI summary

The present disclosure relates to a medical imaging method for enabling magnetic resonance imaging of a subject (318) using a set of imaging parameters of imaging protocols, the method comprising: receiving information related to the subject; using a predefined machine learning model for suggesting at least one imaging protocol for the received information, wherein the imaging protocol comprises at least part of the set of imaging parameters and associated values; providing the imaging protocol.