AI-Rad Companion Organs RT

K221305

Siemens Medical Solutions USA, Inc · cleared 2022-10-14 · product code QKB · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.3)
“AI-Rad Companion Organs RT is a post-processing software intended to automatically contour DICOM CT imaging data using deep-learning-based algorithms.”
Algorithmdeep learning algorithm
source quote (p.3)
“AI-Rad Companion Organs RT is a post-processing software intended to automatically contour DICOM CT imaging data using deep-learning-based algorithms. AI-Rad Companion Organs RT VA40 and AI-Rad Companion Organs RT VA20 both use a deep learning algorithm to support their AI claims.”
Adaptive (vs locked)No
source quote (p.6)
“All models contained within AI-Rad Companion Organs RT VA40 and AI-Rad Companion Organs RT VA20 (K193562) are locked and cannot be modified by the user.”
PCCPNo
Cybersecurity addressedNo

Validation studies (2)

Retrospective clinical

n=113 patients

endpoints: Dice coefficients; absolute symmetric surface distance (ASSD); fail rate; lower 95th percentile confidence bound

Bench

sample size not stated

standards: ISO 62366-1: 2015-02, ISO 14971:2007

Reported performance (2 observations)

diceas written: “DICE score (median)”0.85CI [80.23,84.61]
source quote (p.13)
“The subject device achieved a median DICE score of 0.85 with a median ASSD of 0.93 in comparison to the predicate device achieving a median DICE score of 0.85 with a median ASSD of 0.94 for existing organs. AI-Rad Companion Organs RT VA40 DICE Median 0.85 95% CI (Bootstrap) [80.23,84.61]”
diceas written: “Dice [%] (Head and Neck lymph node class, Avg)”0.8132CI [80.32,82.12]
source quote (p.14)
“AI-Rad Companion Organs RT VA40 (Head and Neck lymph node class) Avg Dice [%] 81.32 95% CI Bootstrap [80.32,82.12]”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

0
recalls in product code, 24mo
0
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
0
drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K221305