Contour ProtégéAI

K213976

MIM Software Inc. · cleared 2022-02-03 · product code QKB · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
Contour ProtégéAI is an accessory to MIM software that automatically creates contours on medical images through the use of machine-learning algorithms.
Algorithmmachine-learning algorithms, neural network models
source quote (p.5)
Contour ProtégéAI is an accessory to MIM software that automatically creates contours on medical images through the use of machine-learning algorithms. A total of 4061 CT images from 31 clinical sites across multiple continents was gathered for the training of the final neural network models. Changes within this submission include new CT 3.0.0 neural network models with additional contours.
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (1)

Retrospective clinical

n=739 images · 12 site(s)

endpoints: Dice coefficient; non-inferiority/equivalence

Reported performance (62 observations)

diceas written: “Dice coefficient0.78CI 0.68
source quote (p.12)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.94CI 0.86
source quote (p.12)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.83CI 0.76
source quote (p.12)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.83CI 0.74
source quote (p.12)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.75CI 0.68
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.28CI 0.15
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.42CI 0.29
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.37CI 0.27
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.41CI 0.31
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.96CI 0.95
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.76CI 0.68
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.81CI 0.76
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.83CI 0.77
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.62CI 0.54
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.64CI 0.52
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.72CI 0.64
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.81CI 0.73
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.41CI 0.30
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.46CI 0.34
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.5CI 0.33
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.56CI 0.47
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.82CI 0.77
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.78CI 0.71
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.9CI 0.86
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.93CI 0.91
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.95CI 0.93
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.94CI 0.91
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.68CI 0.53
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.39CI 0.24
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.38CI 0.23
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.78CI 0.71
source quote (p.13)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.76CI 0.69
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.57CI 0.44
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.71CI 0.65
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.89CI 0.86
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.91CI 0.87
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.91CI 0.85
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.91CI 0.83
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.89CI 0.80
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.57CI 0.44
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.52CI 0.41
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.65CI 0.56
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.57CI 0.43
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.93CI 0.87
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.8CI 0.77
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.95CI 0.93
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.95CI 0.94
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.5CI 0.38
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.37CI 0.25
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.52CI 0.44
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.54CI 0.47
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.81CI 0.74
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.78CI 0.72
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.65CI 0.56
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.56CI 0.43
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.82CI 0.74
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.76CI 0.67
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.7CI 0.60
source quote (p.14)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.82CI 0.78
source quote (p.15)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.91CI 0.80
source quote (p.15)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.79CI 0.69
source quote (p.15)
Results over the validation set compared to the reference device are presented here:
diceas written: “Dice coefficient0.73CI 0.67
source quote (p.15)
Results over the validation set compared to the reference device are presented here:

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
4
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K253270 (decision 2026-03-27) from Mim Software, Inc. for a matching device line ("Contour ProtégéAI+") — a new clearance for the same line is a change event. The newer clearance's parsed summary mentions a PCCP.

    first seen 2026-07-08 · k_number:K253270

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K250035 (decision 2025-02-03) from MIM Software Inc. for a matching device line ("Contour ProtégéAI+") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K250035

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K231765 (decision 2023-11-08) from MIM Software Inc. for a matching device line ("Contour ProtégéAI") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K231765

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K223774 (decision 2023-04-06) from MIM Software Inc. for a matching device line ("Contour ProtégéAI") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K223774

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). 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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K213976