Automated Medical AI Training Data Generation Patent US12603176B2
Summary
USPTO granted patent US12603176B2 to SMART REPORTING GMBH covering a computer-implemented method, system, and computer program product for automatically generating medical training data to train AI algorithms supporting clinical reporting and documentation. The invention receives medical image data, generates or edits findings reports with machine-readable elements, automatically assigns semantic content to unique identifiers, and annotates image data by linking image elements to findings report identifiers for storage as AI training data.
What changed
USPTO granted patent US12603176B2 to SMART REPORTING GMBH for automated generation of medical training data for AI algorithms. The patent covers receiving medical image data, generating or editing findings reports with machine-readable elements, automatically assigning semantic content to unique identifiers, and annotating images by linking data elements to identifiers for storage as AI training data.
Medical device makers and healthcare technology companies developing AI-powered clinical documentation tools may benefit from reviewing this patent for freedom-to-operate considerations. The patent claims a method for creating annotated medical imaging datasets that could overlap with AI-based medical imaging analysis, diagnostic support, and clinical reporting systems.
Archived snapshot
Apr 19, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
Automated generation of medical training data for training AI-algorithms for supporting clinical reporting and documentation
Grant US12603176B2 Kind: B2 Apr 14, 2026
Assignee
SMART REPORTING GMBH
Inventors
Wieland Sommer, Sigrid Auweter
Abstract
A computer-implemented method, computer-system and computer-program product for generating medical training data for training artificial-intelligence (AI) algorithms for supporting clinical reporting and documentation are described. To generate the training data medical image data of a patient comprising medical image data elements are received and a medical findings report is generated, edited and/or received that summarizes individual medical findings. It comprises machine-readable findings-report elements the contents of which comprise semantic features. The contents of the findings report elements are automatically assigned to unique identifiers, wherein each identifier uniquely represents the medical semantic content of exactly one individual medical finding. The medical image data are annotated by linking one or more medical image data elements to the unique identifiers of one or more contents of the findings-report elements, and the annotated received medical image data are stored as training data for AI algorithms for supporting clinical reporting and documentation.
CPC Classifications
G16H 15/00 G16H 30/40 G16H 50/70 G16H 10/60 G16H 30/00
Filing Date
2020-08-14
Application No.
18021151
Claims
20
Related changes
Get daily alerts for USPTO Patent Grants - Health Informatics (G16H)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Grants - Health Informatics (G16H) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.