AI-Rad Companion Organs RT

K221305

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

FDA 510(k) summary for AI-Rad Companion Organs RT (K221305)

Constat organizes this clearance into predicate context, validation evidence, reported performance, postmarket signals, and reimbursement links. Each extracted claim stays tied to the public FDA source; missing fields remain explicitly unstated.

Validation studies
2
Cited predicates
2
Performance observations
2
Product code
QKB
Official FDA 510(k) database record ↗FDA 510(k) source PDF ↗

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
2
drift signals on this device
  • predicate_cohort_contagion

    K221305 shares predicate K213976 with K243762 (Synapse 3D Base Tools (V7.0)), whose product code QIH recorded 1 recall event(s) in the trailing 24 months.

    first seen 2026-08-26 · predicate:K213976 sibling:K243762

  • predicate_cohort_contagion

    K221305 shares predicate K193562 with K232045 (MeVis Liver Suite), whose product code JAK recorded 75 recall event(s) in the trailing 24 months.

    first seen 2026-07-15 · predicate:K193562 sibling:K232045

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 2026-08-26.

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.

Related FDA clearances

More AI/ML devices under product code QKB

These are recent clearances in the same FDA product-code category. Shared classification does not by itself make a device an appropriate predicate.

Contour ProtégéAI+

K253270

Mim Software, Inc.

cleared 2026-03-27

AutoContour (RADAC V5)

K260509

Radformation, Inc.

cleared 2026-03-19

Seg Pro V3 (RT-300)

K251306

Ever Fortune.Ai, Co., Ltd.

cleared 2026-01-28

AccuContour 4.0

K251351

Manteia Technologies Co., Ltd.

cleared 2026-01-23

ARTAssistant

K250780

Manteia Technologies Co., Ltd.

cleared 2025-12-05

TAIMedImg DeepMets

K250427

Taiwan Medical Imaging Co., Ltd.

cleared 2025-05-28

MR Contour DL

K242925

GE HealthCare

cleared 2025-04-01

AI-Rad Companion Organs RT

K242745

Siemens Healthcare GmbH

cleared 2025-03-27

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