Medical Image Metadata Standardization via Trained Function Feedback

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Incorrect or incomplete metadata attributes associated with medical images can hinder comparison and processing, leading to issues in querying specific medical images and providing accurate information for diagnostic applications.

Innovation Solution

A method and system that unify metadata attributes by receiving medical images and associated metadata, applying a trained function to determine image-based attribute values, and combining these with provisional values to provide final, standardized attribute values.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If metadata attributes are filled in manually or automatically without verification, then the filling process is simple and quick, but the accuracy and standardization of attribute values deteriorate

Engineering Contradiction:

Improvemetadata filling efficiencyVSAvoidattribute value accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system extracts attribute values from the medical image itself and uses this extracted information as feedback to verify and correct the provisional attribute values. This closed-loop feedback mechanism ensures that the final attribute values accurately reflect the actual image content while maintaining efficient processing.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The medical image itself serves as the source of truth for verifying metadata attributes. By extracting attributes directly from the image data, the system enables the image to self-verify its own metadata, eliminating the need for manual verification and ensuring accuracy without reducing productivity.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If attribute values are not standardized, then manual filling is more flexible, but the ability to query and compare medical images deteriorates

Engineering Contradiction:

Improvemanual filling flexibilityVSAvoidimage querying capability

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system transforms provisional attribute values into standardized final attribute values by extracting and comparing key parameters from the medical image. This parameter-based standardization enables consistent querying and comparison across different images while preserving the flexibility of the initial filling process.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If automated functions are used to determine attribute values, then processing speed increases, but the complexity of the system increases

Engineering Contradiction:

Improveattribute determination speedVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system replaces manual verification mechanisms with automated image analysis functions. By using computational algorithms to extract and verify attribute values directly from the image data, the system achieves high processing speed without requiring complex manual intervention procedures.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12322091B2Method for providing at least one metadata attribute associated with a medical image

Publication Date: 2025.06.03 SIEMENS HEALTHINEERS AG

AI summary

A computer-implemented method is for providing at least one first metadata attribute associated with a medical image. The method includes receiving the medical image and the at least one first metadata attribute. Therein the at least one first metadata attribute includes an attribute tag and a provisional attribute value. Furthermore, the method includes applying a first trained function to the medical image to determine an image-based attribute value. Furthermore, the method includes determining a final attribute value based on the provisional attribute value and the image-based attribute value. Furthermore, the method includes providing the at least one first metadata attribute. Therein the at least one first metadata attribute includes the attribute tag and the final attribute value.