Automated Medical Image Annotation Algorithm

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual annotation of medical images with markers for orientation and laterality is disruptive to the radiography workflow, prone to errors, and subject to hospital-specific guidelines.

Innovation Solution

A computer-implemented method for annotating medical images using an annotation algorithm that determines image coordinates, scaling, brightness, and orientation for post-acquisition annotations, ensuring accurate and automated placement and sizing of markers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual annotation using pre-acquisition markers is used, then annotation accuracy is improved, but workflow efficiency deteriorates and error probability increases

Engineering Contradiction:
Improveannotation accuracyVSAvoidworkflow efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the manual mechanical process of placing physical markers with an automated computational system. The annotation algorithm automatically determines marker positions, orientations, and sizes based on image analysis, eliminating the need for manual intervention while maintaining annotation accuracy.

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

Solution Approach 2:

The system enables self-service annotation where the medical image itself provides the information needed for accurate marker placement. The algorithm analyzes image features such as anatomy orientation and laterality indicators within the image to automatically determine appropriate annotation parameters without external manual input.

Inventive Principle:
Principle #25Self-service

2Adaptability or versatility

If manual annotation is used, then annotation can be customized according to hospital guidelines, but annotation precision and consistency deteriorate due to human error

Engineering Contradiction:
Improveannotation customizationVSAvoidannotation consistency
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system maintains adaptability by allowing configuration of annotation parameters such as marker size, position offsets, and placement rules to match different hospital guidelines. The algorithm adjusts these parameters automatically based on input images while ensuring consistent application of the chosen guidelines across all annotations.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If post-acquisition software markers are used, then workflow disruption is reduced, but annotation precision deteriorates due to manual placement errors

Engineering Contradiction:
Improveworkflow efficiencyVSAvoidmarker placement accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces the manual software-based marker placement process with an automated algorithm that computationally determines optimal marker positions. This substitution eliminates human placement errors while maintaining the workflow efficiency benefits of post-acquisition annotation.

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

Solution Approach 2:

The system creates an automated copy of the annotation process that replicates the intended marker placement without requiring manual execution. The algorithm generates annotation parameters based on image analysis, effectively copying the correct placement logic from image features to final annotation output.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4539057A1Annotating medical images
Publication Date: 2025.04.16 KONINKLIJKE PHILIPS NV
  • EP4539057A1 patent drawingFigure 1~2
  • EP4539057A1 patent drawingFigure 3
  • EP4539057A1 patent drawingFigure 4

AI summary

Manual marker placement in medical imaging is disruptive to the workflow and prone to error. There is therefore provided a computer-implemented method for annotating medical images. The method comprises: obtaining a medical image (300) to be annotated; applying an annotation algorithm to the medical image, wherein the annotation algorithm determines values of one or more parameters for a post-acquisition annotation (302) to be applied to the medical image and annotates the medical image by applying the post-acquisition annotation to the medical image using the determined values, wherein the one or more parameters comprise image coordinates for a position of the post-acquisition annotation in the medical image; and outputting the annotated medical image. The method improves the workflow by automating the marker placement.