HHS · no agency ID · record R0945

TB Case Browser Image Text Detection

Department of Health and Human Services · HHS/NIH

Overview

Development stage: DeployedSource: c) Deployed – The use case is being actively authorized or utilized to support the functions or mission of an agency.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: 2019-01 (month precision)Source: Jan-19
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Science
Operational functions: Document processing and extraction Derived by keyword rules; see methodology

Problem the AI is intended to solve

Without OCR technology, validation of text on images is manually intensive and, without proper controls, can create the risk of sensitive information coming into the system.

Expected benefits

Provides additional protection against PII/PHI ingress into the TB Portals imaging dataset in a far more automated process.

System outputs

User uploads a DICOM image, which is converted and passed to the AWS Rekognition service. Output is a JSON block with predictions on the location of text within an image.

Technology

AI classification: Computer visionSource: Computer Vision: AI that processes and interprets visual data (e.g., images and videos).
System name(s): NIAID TB Portals
Custom-developed code: Yes
Public source code: Not reported

Sourcing

How it was built: Contract and in-houseSource: c) Developed with both contracting and in-house resources
Vendor (as reported): Deloitte, Guidehouse, Research Data and Communication Technologies Corp.
Vendors (standardized): DeloitteGuidehouse

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: No
Privacy Impact Assessment: Not reported
Authorization to Operate: Yes
Demographic features: k) None of the above
Training and evaluation data: Existing TB Portals images with and without text are used to evaluate performance.
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported