Anonymization Network for Specimen Label Masking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated diagnostic analysis systems face challenges in protecting patient information during specimen characterization, as images captured for analysis often include sensitive information from labels affixed to specimen containers.
Innovation Solution
The system employs an anonymization network to capture images of specimen containers, identify labels, and edit the images to mask sensitive information, ensuring patient privacy while allowing for specimen characterization and interferent determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If images of specimen containers are captured for specimen characterization, then specimen analysis accuracy is improved, but patient information privacy is compromised due to labels containing sensitive data
Solution Approach 1:
The patent extracts and removes the harmful element (patient information from labels) from the captured images while preserving the useful elements (specimen characteristics). The anonymization network specifically targets and removes text and barcodes from labels, allowing specimen analysis to proceed without privacy concerns.
Solution Approach 2:
The patent introduces an intermediary component (anonymization network) that acts as a mediator between image capture and specimen analysis. This intermediary processes the captured images to remove sensitive information before the images are used for characterization, thus resolving the conflict between obtaining accurate images and protecting privacy.
2Reliability
If label information is removed from images to protect privacy, then patient information security is improved, but specimen characterization capability may be degraded
Solution Approach 1:
The patent segments the image processing task into distinct functions: the anonymization network specifically targets and removes only the label portions containing text and barcodes, while leaving the specimen regions intact. This selective segmentation ensures that privacy protection does not compromise specimen characterization capabilities.
Solution Approach 2:
The patent applies different processing quality to different regions of the image: label regions are anonymized by removing text and barcodes, while specimen regions are preserved with full quality for accurate characterization. This local differentiation of processing quality resolves the contradiction between security and accuracy.
Data Source
AI summary
A method of characterizing a specimen and specimen container to be analyzed in an automated diagnostic analysis system. The method can provide a segmentation determination and/or an HILN determination (hemolysis, icterus, lipemia, or normal) of the specimen while protecting patient information. The method includes capturing an image of a specimen container via an image capture device, identifying a label affixed to the specimen container in the captured image via an anonymization network, and editing the captured image via the anonymization network to mask some or all information present in the label so that it is removed from the captured image. Quality check modules and systems configured to carry out the method are also described, as are other aspects.