All Data Fast News is © Data Fast Solutions, unless where otherwise indicated • All Rights Reserved

Data Fast News


Keep up to date with Data Fast Solutions for your business.


Amazon RekognitionAmazon has recently announced that a new system has been developed allowing identifying protected health information (PHI) listed on medical images to be automatically removed which prevent patients from being identified.

Medical images generally contain a patient’s protected health information (PHI) listed on the image, including name, birth date, age, and possibly additional information. Before the images can be used for research, written permission must be obtained from the patient or all identifying data must be permanently removed. Removing PHI from images requires a manual check and alteration of the image which can be an expensive and time-consuming to complete.

The new system is Amazon’s Rekognition machine-learning service, which can detect and extract text from images. The text is then fed through Amazon Comprehend Medical to identify any PHI. In combination with Python code it is possible to quickly remove any PHI in the images. The system works on PNG, JPEG, and DICOM images.

Amazon claims the system allows healthcare organizations to de-identify large quantities of images quickly and inexpensively. Amazon also states that the system can be used to batch process thousands or millions of images. Also, once an image has been processed and the location of PHI has been identified, it is possible to associate a Lambda function to automatically remove PHI from any new images when they are uploaded to an Amazon S3 bucket.

Excerpts taken from HIPAA JOURNAL 2019

Created by RIO

This article is ©2019 Data Fast Solutions • All Rights Reserved

Comments are closed.