3D Medical Image Anonymization via Skin Region Expansion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for anonymizing three-dimensional medical images struggle to effectively de-identify faces and body shapes, potentially leaving personal information exposed.

Innovation Solution

A method and apparatus for anonymizing three-dimensional medical images by determining a skin region, generating a human mask, expanding the skin region, generating an anonymization region by removing the human mask from the expanded skin region, and changing the brightness values of voxels in the anonymization region to a predefined or arbitrary value.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If existing anonymization methods are used, then processing speed is maintained, but de-identification effectiveness deteriorates

Engineering Contradiction:
Improvede-identification effectivenessVSAvoidprocessing speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent segments the anonymization process into distinct stages: skin region extraction, human mask generation, skin expansion region creation, and brightness value modification. This segmentation allows each component to specialize in specific tasks, improving overall effectiveness while maintaining efficiency through optimized processing stages.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by first extracting the skin region and generating the human mask before proceeding to expansion and anonymization. These preliminary steps prepare the data structure in advance, enabling faster and more effective de-identification in subsequent processing stages.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If skin region is expanded to ensure complete de-identification, then de-identification effectiveness is improved, but risk of removing internal organ information increases

Engineering Contradiction:
Improvede-identification effectivenessVSAvoidinternal organ information
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

The patent applies local quality by differentiating between the skin region (to be expanded and anonymized) and internal organ regions (to be preserved). The human mask specifically identifies internal structures that should exclude from expansion, ensuring that anonymization is applied locally only where appropriate while preserving critical internal information.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The human mask serves as an intermediary element between the skin region expansion and the internal organ preservation. It acts as a mediator that guides the expansion process, allowing the skin region to be expanded for de-identification while the mask prevents over-expansion into internal organ territories, thus protecting important information.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4105883B1Three-dimensional medical image anonymization method and apparatus
Publication Date: 2025.05.07 MEDICALIP CO LTD
  • EP4105883B1 patent drawingFigure 1
  • EP4105883B1 patent drawingFigure 2
  • EP4105883B1 patent drawingFigure 3

AI summary

A method and apparatus for anonymizing a three-dimensional medical image are provided. The apparatus determines a skin region of a three-dimensional medical image, generates a human mask based on a human tissue region of the three-dimensional medical image, the human tissue region including various organs, generates a skin expansion region in which the skin region of the three-dimensional medical image is expanded, generates an anonymization region obtained by removing a region corresponding to the human mask from the skin expansion region, and changes brightness values of voxels corresponding to the anonymization region in the three-dimensional medical image to a predefined value or an arbitrary value.