Radiology reporting standard

O-RADS

O-RADS US is the American College of Radiology risk-stratification and management system for ovarian and adnexal lesions on ultrasound, assigning a score from 0 to 5 that estimates the risk of malignancy and guides management.

O-RADS through RadVector API O-RADS in RadVector Reporting

Draft · advisoryDraft criteria pack under validation; RadVector answers as advisory and marks the result not usable for output.

At a glance

What O-RADS is

Full name: Ovarian-Adnexal Reporting and Data System (Ultrasound)
Edition RadVector applies: O-RADS US v2022
Published by: American College of Radiology (ACR) O-RADS Committee
Applies to: Ovarian and adnexal lesions on ultrasound.
Modality: Pelvic ultrasound

Official source: ACR O-RADS

O-RADS categories

0: Incomplete evaluation.
1: Normal premenopausal ovary.
2: Almost certainly benign.
3: Low risk of malignancy.
4: Intermediate risk of malignancy.
5: High risk of malignancy.

A short summary in our own words. Use the official O-RADS documents for the complete criteria.

How RadVector applies it

O-RADS, applied the same way every time.

The same deterministic engine grades O-RADS inside RadVector Reporting and through RadVector API, and a test keeps the two answers identical.

Reads lesion type, wall, locularity, solid components, papillary projections and color score from the radiologist's words, by lesion.
When a feature that would change the score is not documented, enumerates the scores it could reach and names the feature instead of guessing.
Features reported by exception (solid component, papillary projections, ascites) take a stated pack default, and the answer says so.

Radiologists and imaging centers

RadVector Reporting supplies the O-RADS category and recommendation to the report draft from the radiologist's own findings, cites the guidance applied, and keeps a per-report governance record. The radiologist signs.

radcloud.net

Software teams and AI companies

RadVector API returns the O-RADS verdict with pack version, validation status and a trace id, as JSON or FHIR R4, with a sandbox key and synthetic fixtures to start.

Developer guide

Hospitals and enterprise imaging

One versioned O-RADS implementation across reporting, QA and other AI systems' results, with an audit trail of which pack version graded each report.

Talk to us

O-RADS questions

How does RadVector handle an incompletely described adnexal lesion?

RadVector lists every O-RADS score the lesion could reach given the features the report leaves out and names those features, rather than assigning a single score it cannot support. The O-RADS pack is a draft under validation, so the result is advisory.

Does RadVector read ultrasound images to assign O-RADS?

No. RadVector grades the findings the radiologist describes, or findings another system reports as FHIR or DICOM SR. It does not detect lesions in images.

Other reporting standards

RadVector is clinical decision support for qualified professionals, not a diagnostic device; the radiologist makes the final determination.