Radiology reporting standard

PI-RADS

PI-RADS v2.1 is the scoring system for prostate MRI that assigns each lesion a category from 1 (clinically significant cancer highly unlikely) to 5 (highly likely), using diffusion-weighted imaging as the dominant sequence in the peripheral zone and T2-weighted imaging in the transition zone.

PI-RADS through RadVector API PI-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 PI-RADS is

Full name: Prostate Imaging Reporting and Data System
Edition RadVector applies: PI-RADS v2.1 (2019)
Published by: ACR, ESUR and AdMeTech Foundation PI-RADS Steering Committee
Applies to: Multiparametric or biparametric prostate MRI.
Modality: Prostate MRI

Official source: ACR PI-RADS

PI-RADS categories

1: Very low: clinically significant cancer highly unlikely.
2: Low: clinically significant cancer unlikely.
3: Intermediate: equivocal.
4: High: clinically significant cancer likely.
5: Very high: clinically significant cancer highly likely.

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

How RadVector applies it

PI-RADS, applied the same way every time.

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

Applies the zone rules: DWI-dominant in the peripheral zone (a DWI 3 resolved by DCE), T2-dominant in the transition zone; a score-4 lesion of 1.5 cm or more, or with extraprostatic extension, becomes 5.
On a biparametric exam with no contrast, applies the pack's stated rule for an unavailable DCE and records it.
Computes gland volume and PSA density from the dictated dimensions and PSA, reported beside the category and stated as not part of it.
Ignores a template's category legend and reports the highest stated category for the index lesion.

Radiologists and imaging centers

RadVector Reporting supplies the PI-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 PI-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 PI-RADS implementation across reporting, QA and other AI systems' results, with an audit trail of which pack version graded each report.

Talk to us

PI-RADS questions

Does RadVector calculate PSA density?

Yes. When the report or worksheet gives the prostate's three dimensions (or a stated volume) and a total PSA, RadVector computes gland volume and PSA density and shows them beside the PI-RADS category. PSA density is reported as supporting information and is not part of the PI-RADS category.

Is RadVector's PI-RADS pack validated?

Not yet. The PI-RADS v2.1 pack is a draft under validation, so RadVector answers as advisory and marks the result not usable for output. Validated packs today are Fleischner 2017, BI-RADS and DEXA.

Other reporting standards

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