Adaptive Medical Imaging Interface Using Learning Network

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Medical imaging systems require frequent and time-consuming adjustments of user interfaces by practitioners, such as radiologists or cardiologists, which increases costs and computational resources.

Innovation Solution

A learning network is used to monitor user actions and medical content data to develop a model that adapts the user interface configuration, predicting user commands and caching relevant data to streamline imaging viewing and reduce the need for manual adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual adjustments of user interface are performed frequently by practitioners, then the user interface can be customized to individual needs, but time consumption and computational resources increase

Engineering Contradiction:

Improveuser interface customizationVSAvoidtime for manual adjustments

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system performs self-adjustment by automatically detecting user interactions and adapting the interface configuration without requiring manual intervention. The learning network monitors user actions and autonomously modifies interface parameters to optimize the viewing experience, eliminating the need for practitioners to manually adjust settings.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback mechanisms where user interactions are continuously monitored and fed back into the learning network. This feedback loop enables the system to learn from practitioner behavior patterns and automatically adjust the user interface configuration, replacing manual adjustments with automated adaptive responses.

Inventive Principle:

Principle #23Feedback

2Ease of operation

If manual adjustments of user interface are performed frequently, then interface customization is achieved, but computational resources are consumed

Engineering Contradiction:

Improveuser interface customizationVSAvoidcomputational resources

Core Design Contradiction:

Ease of operationVSUse of energy by stationary object

Solution Approach 1:

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical adjustments with automated computational processes. Instead of practitioners manually configuring interface parameters, the system uses machine learning algorithms to automatically detect patterns and adjust settings, substituting human computational effort with automated intelligent systems.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If user interface is adjusted frequently, then it adapts to different imaging tasks, but workflow efficiency decreases

Engineering Contradiction:

Improveinterface adaptation to imaging tasksVSAvoidworkflow efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system performs preliminary learning during initial use sessions to establish baseline user preferences and imaging task patterns. This preliminary action enables the interface to be pre-configured for optimal performance in subsequent tasks, reducing the need for frequent adjustments and improving workflow efficiency.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The user interface transitions from a static configuration to a dynamic adaptive system. The learning network continuously monitors user interactions and automatically adjusts interface parameters in real-time, enabling the interface to adapt to different imaging tasks without requiring manual reconfiguration, thus maintaining workflow efficiency.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11461596B2Methods and apparatus to adapt medical imaging interfaces based on learning

Publication Date: 2022.10.04 GE PRECISION HEALTHCARE LLC

AI summary

Methods and apparatus to adapt medical imaging interfaces based on learning are disclosed. An example apparatus includes a use monitor to monitor, in a first session, user actions and medical content data pertaining to operation of a clinical image display, a learning device including a processor to implement a learning network to develop a model for a subsequent session based on the user actions in relationship to a context of the medical content data. The model developed by defining contextual patterns of the user actions based on the context and the medical content data. The learning device is to update, prior to or during a second session subsequent the first session, a user interface based on the model.