Overview
This pipeline detects and flags PHI entities within both the metadata and visual content of DICOM files, supporting robust compliance monitoring and streamlined violation reporting.
Its primary purpose is to generate a comprehensive report detailing any PHI entities found - whether embedded in the image or present in metadata - within DICOM files that were previously subjected to de-identification.
A potential use case for this pipeline:
A healthcare organization receives large batches of DICOM files from third-party providers or external imaging centers. These files are expected to be de-identified according to HIPAA or other regulatory standards. However, due to inconsistencies in de-identification workflows, some files still contain Protected Health Information (PHI) - either embedded in image overlays, burned-in text, or DICOM metadata fields (e.g., patient name, institution, accession number).
The organization uses the PHI detection pipeline to automatically scan both the pixel data and metadata, flagging any detected PHI entities. The output is a compliance report that summarizes: which files contain PHI, the type of PHI (e.g., names, IDs, dates).
IMPORTANT USAGE INFORMATION:
After subscribing to this product and creating a SageMaker endpoint, billing occurs on an HOURLY BASIS for as long as the endpoint is running.
-Charges apply even if the endpoint is idle and not actively processing requests.
-To stop charges, you MUST DELETE the endpoint in your SageMaker console.
-Simply stopping requests will NOT stop billing.
This ensures you are only billed for the time you actively use the service.
Highlights
- The pipeline cross-references DICOM metadata entities with text detected in the corresponding DICOM images. If information such as patient names, physician names, or dates found in the metadata also appears in the image text, it will be automatically identified and de-identified - even if it was not part of the initial entity recognition list
- De-identified entities: NAME,AGE,CONTACT,LOCATION,PROFESSION,PERSON,DATE,ID,DOCTOR
Details
Unlock automation with AI agent solutions

Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m4.2xlarge Inference (Batch) Recommended | Model inference on the ml.m4.2xlarge instance type, batch mode | $47.52 |
ml.m4.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.m4.2xlarge instance type, real-time mode | $47.52 |
Vendor refund policy
No refunds are possible.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Version release notes
Spark-OCR==6.0.0 Spark-Healthcare==6.0.2 Spark-NLP==6.0.1
Additional details
Inputs
- Summary
Supported Dicom input format.
- Input MIME type
- application/octet-stream
Support
Vendor support
For any assistance, please reach out to support@johnsnowlabs.com .
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products




