Overview
PixelGuard login
PixelGuard login
PixelGuard job creation
PixelGuard job output
PixelGuard job audit
PixelGuard job report
PixelGuard is a state-of-the-art AI-enabled deidentification platform engineered to remove both overt and embedded patient identifiers from medical images without sacrificing diagnostic integrity. Ideal users include healthcare providers, clinical researchers, AI/ML developers, educators, and compliance teams, anyone who needs secure, auditable, and high-throughput image deidentification. PixelGuard ingests all common imaging formats, including DICOM, JPEG, PNG, NIfTI and outputs de-identified files in the same format. Through a combination of metadata scrubbing (with options for removal, swapping, or date-shifting), AI-driven detection of burned-in text for over 75 languages, and user-configurable redaction rules, PixelGuard ensures compliance with HIPAA, GDPR, and other privacy standards. Advanced algorithms handle decompression and recompression intelligently to preserve lossless image quality, and integration connectors allow seamless workflows with PACS, on-premises or cloud-based repositories.
Designed for high-volume and mission-critical environments, PixelGuard scales elastically to process millions of images via batch and asynchronous workflows, while offering real-time user review of flagged PHI to maintain oversight. Its crosswalk logging preserves a reversible mapping of original and de-identified IDs and dates, allowing controlled re-linkage when necessary. With a helpful and intuitive user interface and full Single Sign-On support. PixelGuard supports customization of deidentification settings and algorithm versions to meet any institutional policy or research protocol. Pre-built scripts and step-by-step instructions are provided to deploy the platform within the user's tenant using Infrastructure as Code. Additionally, comprehensive training and onboarding sessions are available to get your team up to speed quickly. Our standard pricing is outlined below; for enterprise or high-volume pricing and private offerings, please contact us at info@xtasis.com .
Highlights
- AI-Powered, Multiformat Deidentification: PixelGuard Leverages over 75 AI models and metadata scrubbing/masking to automatically detect and redact PHI (including burned-in text in multiple languages) across DICOM, JPEG, PNG, NIfTI, and more while preserving full diagnostic image quality. Supports auditable, asynchronous, high-volume jobs.
- Seamless SSO & Intuitive User Interface: PixelGuard integrates with your existing enterprise identity provider for Single Sign-On, and presents an easy-to-use web dashboard for real-time configuration, monitoring, and manual review of deidentification workflows.
- In-Tenant Deployment with Zero Data Egress: PixelGuard runs entirely within your organization's cloud tenant with no external data transfers required ensuring data sovereignty, simplifying compliance, and keeping all sensitive images behind your firewall.
Details
Unlock automation with AI agent solutions

Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/unit |
---|---|---|
1 medical image deidentified | one image has been deidentified using PixelGuard | $10.00 |
Vendor refund policy
We stand behind PixelGuard's performance. Refunds are issued only if you were charged for images that were not properly de-identified. To request a refund, email info@xtasis.com you're your subscriber AWS account ID, usage reported date, job details, number of affected files and evidence of de-identification failure. Once verified, eligible refunds will be processed within a reasonable time period. For inquiries or other assistance, contact our support team at info@xtasis.com .
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
AWS CloudFormation (via AWS CDK)
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Version: v1.0.0 Release Date: April 29, 2025 Update Classification: Initial Release
Overview: This is the first official release of the PixelGuard De-identification Platform on AWS Marketplace. It provides secure, scalable de-identification of medical images with AI-powered redaction and metadata scrubbing.
Key Features: Upload and process DICOM, JPEG formats AI detection of burned-in identifiers (supports 75+ languages) Configurable redaction rules (remove/swap/date-shift) HIPAA compliance support Integration with S3, Lambda, and Cognito-based user access Infrastructure deployed via CDK (IaC)
Known Limitations: TIFF format support is not available in this release (planned for future version)
Getting Started: Follow the deployment instructions in the README provided with the CDK repository. For configuration help or onboarding support, contact info@xtasis.com .
Additional details
Usage instructions
Usage Instructions:
Step 1: Generate an SSH Key Pair and Share the Public Key To access the PixelGuard repository, you must first generate an SSH key pair and send your public key to info@xtasis.com .
How to generate the key: For macOS/Linux:
- Open Terminal.
- Run: ssh-keygen -t rsa -b 4096 -C "your_email@example.com "
- Press Enter to accept the default file location.
- Optionally add a passphrase.
For Windows (Git Bash or WSL):
- Open Git Bash or WSL.
- Run: ssh-keygen -t rsa -b 4096 -C "your_email@example.com " Your public key will be saved to: ~/.ssh/id_rsa.pub
Copy and email the contents of this file to: info@xtasis.comÂ
Tip: Use this to copy the key to clipboard: macOS: cat ~/.ssh/id_rsa.pub | pbcopy Windows: cat ~/.ssh/id_rsa.pub | clip Linux: xclip -sel clip < ~/.ssh/id_rsa.pub (requires xclip)
Step 2: Clone the PixelGuard Git Repository Once access is granted:
git clone git@gitlab.com:xtasis/pixelguard.git
Step 3: Navigate into the Project and Checkout the v2.0 Branch
cd pixelguard
git fetch origin v1.0
git checkout v1.0
Step 4: Follow the Project README Inside the cloned folder, follow the instructions provided in the README.md file for setup and deployment.
Support
Vendor support
Reach out to us any time at info@xtasis.com . Our support specialists monitor this inbox around the clock and aim to respond to all inquiries within one business day. Our comprehensive FAQ is also available at https://xtasis.com/pixelguard_faq/ . It's updated regularly with answers to common questions, configuration tips, and troubleshooting steps. Pre-built scripts and step-by-step instructions are provided to deploy the platform within the user's tenant using Infrastructure as Code. Additionally, comprehensive training and onboarding sessions are available to get your team up to speed quickly. Our standard pricing is outlined here; for enterprise or high-volume pricing and private offerings, please contact us directly.
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.