Motion Correction Confidence Score for Nuclear Imaging

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional nuclear imaging systems face inefficiencies due to resource-intensive motion correction processes, which may not always improve image quality, leading to wasted time and resources, especially when patient movement is minimal or high-quality images are not required.

Innovation Solution

The system estimates the effectiveness of motion correction by calculating motion coefficients based on time-based and motion-based frames of event data, providing a confidence score to determine if motion correction will enhance image quality, allowing selective application of correction only when necessary.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If motion correction is applied to all acquired event data, then image quality may be improved, but resource consumption and processing time increase significantly

Engineering Contradiction:

Improveimage qualityVSAvoidprocessing efficiency

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The system performs a preliminary assessment of motion coefficients and calculates a confidence score before executing motion correction. This preliminary action determines whether motion correction is actually needed, avoiding unnecessary processing and resource consumption while maintaining image quality when correction is beneficial

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system changes the parameter being measured from raw event data to motion coefficients derived from comparing time-based frames with motion-based frames. By monitoring these coefficient changes and calculating confidence scores, the system dynamically determines when motion correction parameters should be applied, optimizing the balance between image quality and processing efficiency

Inventive Principle:

Principle #35Parameter changes

2Manufacturing precision

If motion correction is applied to all acquired event data, then image quality may be improved, but processing time increases significantly

Engineering Contradiction:

Improveimage qualityVSAvoidprocessing time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Instead of applying motion correction universally, the system applies partial correction only when the confidence score indicates motion is present. This selective application reduces processing time while maintaining image quality for cases where correction is actually needed

Inventive Principle:

Principle #16Partial or excessive action

3Manufacturing precision

If motion correction is applied without assessment, then image quality may be improved, but resources are wasted when motion is minimal

Engineering Contradiction:

Improveimage qualityVSAvoidresource consumption

Core Design Contradiction:

Manufacturing precisionVSLoss of energy

Solution Approach 1:

The system calculates motion coefficients by comparing time-based frames with motion-based frames and uses this feedback to determine whether motion correction should be applied. The confidence score provides feedback on the likelihood of improvement, enabling the system to avoid wasting resources when motion is minimal while ensuring correction is applied when beneficial

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system autonomously assesses its own data to determine whether motion correction is needed, using internal motion coefficients and confidence scores to make the decision. This self-service approach eliminates the need for external assessment and ensures resources are only consumed when the system itself determines correction will be beneficial

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS11250575B2Determination of confidence score for motion correction

Publication Date: 2022.02.15 SIEMENS MEDICAL SOLUTIONS USA INC

AI summary

A system and method include acquisition of a plurality of event data associated with an object, each of the plurality of event data associated with a position and a time, assigning of each event data to one of a plurality of time-based frames based on a time associated with the event data, each of the plurality of time-based frames associated with a respective time period, assigning of each event data to one of a plurality of motion-based frames based on a time associated with the event data, each of the plurality of motion-based frames associated with a respective time period associated with a respective motion state, determination of a confidence score based on the plurality of time-based frames of event data and on the plurality of motion-based frames of event data, and presentation of the confidence score and a control selectable to initiate motion-correction of the event data.