Sold by: John Snow Labs
Deployed on AWS
Free Trial
This pipeline deidentifies SVS files, which comes from Microscopes and other sources.
It removes all Protected Healthcare Information (PHI) from input SVS pixel-data and metadata Tags.
It uses a combination of SOTA Deep Learning based NLP & OCR pipeline, as well as binary processing.
Overview
This pipeline can be used to mask PHI information in SVS files. It removes PHI from metadata tags and pixel data of the input file. You can remove any metadata tags via custom parameters like ImageDescription.ScanScope ID, ImageDescription.Time Zone, ImageDescription.ScannerType.
Masked entities include AGE, BIOID, CITY, COUNTRY, DATE, DEVICE, DOCTOR, EMAIL, FAX, HEALTHPLAN, HOSPITAL, IDNUM, LOCATION, MEDICALRECORD, ORGANIZATION, PATIENT, PHONE, PROFESSION, STATE, STREET, URL, USERNAME, ZIP, ACCOUNT, LICENSE, VIN, SSN, DLN, PLATE, and IPADDR.
The output is a SVS document, similar to the one at the input, but with black bounding boxes on top of the targeted entities and PHI removed from metadata tags.
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
- Comprehensive, multi-layered approach to de-identifying SVS files - combining advanced deep learning based NLP, OCR, and binary processing to accurately detect and mask Protected Health Information (PHI) across both pixel data and metadata.
- By targeting a wide range of entity type - from patient names and medical IDs to geographic locations and digital identifiers - the solution ensures compliance with privacy regulations while preserving the integrity and usability of the original SVS file.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 15 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.4xlarge Inference (Batch) Recommended | Model inference on the ml.m5.4xlarge instance type, batch mode | $95.04 |
ml.m5.4xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.4xlarge instance type, real-time mode | $95.04 |
ml.m5.xlarge Inference (Batch) | Model inference on the ml.m5.xlarge instance type, batch mode | $95.04 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $95.04 |
ml.m6i.xlarge Inference (Real-Time) | Model inference on the ml.m6i.xlarge instance type, real-time mode | $95.04 |
ml.m5.2xlarge Inference (Real-Time) | Model inference on the ml.m5.2xlarge instance type, real-time mode | $95.04 |
Dimensions summary
You pay by the hour for the compute instance that runs the de-identification model. Pricing splits into two processing modes. Batch mode covers three instance sizes, from ml.m5.xlarge up to ml.m5.4xlarge, for processing groups of SVS image files at once. Real-time mode covers ml.m6i.xlarge, ml.m5.2xlarge, and ml.m5.4xlarge for on-demand requests. Within each mode, larger instance sizes offer more compute capacity. Your cost scales with the mode you choose, the instance size, and the number of host hours you run.
Top-of-mind questions for buyers
One host hour is one hour that a single compute instance runs the de-identification model. You pay for each hour the instance is active, times the number of instances you run. The rate depends on the instance size and processing mode you select.
Batch mode meters host hours while processing groups of SVS files together in one run. Real-time mode meters host hours for a running instance that handles requests on demand. Batch suits scheduled bulk jobs. Real-time suits continuous, request-driven processing where the instance stays available.
Charges accrue only while the instance runs and accumulates host hours. A fully stopped instance stops accruing software charges. In real-time mode, an instance kept running to accept requests keeps billing even during idle periods, so you should shut it down when not needed.
nlp.johnsnowlabs.com
Helpful?
Vendor refund policy
No refunds are possible.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
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.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
This endpoint deidentifies SVS files, which comes from Microscopes and other sources. It removes all Protected Healthcare Information (PHI) from input SVS pixel-data and metadata Tags. It uses a combination of SOTA Deep Learning based NLP & OCR pipeline, as well as binary processing.
johnsnowlabs_version: 6.0.2
Spark-OCR==6.0.0 Spark-Healthcare==6.0.2 Spark-NLP==6.0.1
Additional details
Inputs
- Summary
Supported PDF input format. PDF can be digital and scanned or mixed.
- Input MIME type
- application/octet-stream
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/svs_deid/inputs/real-time
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/svs_deid/inputs/batch
Resources
Vendor resources
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
CancerVision is a cutting-edge 2-in-1 whole-genome cancer assay offering both somatic (40x) and paired germline (20x) coverage, with ultra-deep targeting (500x) of 600+ clinically relevant cancer genes. It delivers >99% sensitivity and PPV, with robust detection of complex variants including SVs, CNVs, and mutations in non-coding regions. CancerVision also provides key biomarker insights such as TMB, MSI, HRD, mutational signatures, and germline variants. This CAP/CLIA-validated assay offers a fast 2-week turnaround and supports advanced custom analyses, including ecDNA, tumor ploidy, and transposable element detection, at whole-genome resolution. Designed for precision oncology, CancerVision is your comprehensive genomic solution for cancer diagnostics and research.
Medical data processing to management is available through the MeDIAuto service:- MeDIAuto enables doctors and experts to quickly, accurately, and easily process training data so that AI can be trained to identify various cancer cells, thereby improving the performance of AI models.
1) Annotation processing: Detailed annotation processing is possible in the viewer in the WSI (supports all formats of large cancer image files) cloud
2) Meta information: Clinical meta information management by WSI is possible through the definition of meta attributes by clinical type
3) Statistics: You can check the data processing status by institution and project through various visualization tools
4) Dashboard: Check the status of various cancer images through the number of data collection, clinical information input, and annotation status by institution and project.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.