AutoContour (Model RADAC V4)

K242729

Radformation, Inc. · cleared 2024-12-09 · product code QKB · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.6)

“As with AutoContour Model RADAC V3, the AutoContour Model RADAC V4 device is software that uses DICOM-compliant image data (CT or MR) as input to: (1) automatically contour various structures of interest for radiation therapy treatment planning using machine learning based contouring.”

Algorithmmachine learning based contouring, deep-learning based structure models, CNN architecture

source quote (p.6)

“automatically contour various structures of interest for radiation therapy treatment planning using machine learning based contouring. The deep-learning based structure models are trained using imaging datasets consisting of anatomical organs of the head and neck, thorax, abdomen and pelvis for adult male and female patients, (2) allow the user to review and modify the resulting contours, and (3) generate DICOM-compliant structure set data the can be imported into a radiation therapy treatment planning system.”

Adaptive (vs locked)No

PCCPNo

Cybersecurity addressedNo

Validation studies (1)

Retrospective clinical

n=54 images

endpoints: Mean Dice Similarity Coefficient (DSC); Qualitative clinical appropriateness rating (1-5)

standards: NRG/RTOG guidelines

Reported performance (6 observations)

diceas written: “Mean DSC (Large CT Structures)”0.92CI +/-0.06

source quote (p.19)

“For CT Structure models large, medium and small structures resulted in a mean DSC of 0.92+/-0.06, 0.85+/-0.09, and 0.81+/-0.12 respectively.”

diceas written: “Mean DSC (Medium CT Structures)”0.85CI +/-0.09

source quote (p.19)

“For CT Structure models large, medium and small structures resulted in a mean DSC of 0.92+/-0.06, 0.85+/-0.09, and 0.81+/-0.12 respectively.”

diceas written: “Mean DSC (Small CT Structures)”0.81CI +/-0.12

source quote (p.19)

“For CT Structure models large, medium and small structures resulted in a mean DSC of 0.92+/-0.06, 0.85+/-0.09, and 0.81+/-0.12 respectively.”

diceas written: “Mean DSC (Large MR Structures)”0.96CI +/-0.03

source quote (p.27)

“For MR Structure models, a mean training DSC of 0.96+/-0.03 was found for large models, 0.84+/-0.07 for medium models, 0.74+/- 0.09 for small models.”

diceas written: “Mean DSC (Medium MR Structures)”0.84CI +/-0.07

source quote (p.27)

“For MR Structure models, a mean training DSC of 0.96+/-0.03 was found for large models, 0.84+/-0.07 for medium models, 0.74+/- 0.09 for small models.”

diceas written: “Mean DSC (Small MR Structures)”0.74CI +/-0.09

source quote (p.27)

“For MR Structure models, a mean training DSC of 0.96+/-0.03 was found for large models, 0.84+/-0.07 for medium models, 0.74+/- 0.09 for small models.”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

drift signals on this device

re_clearance
The FDA AI/ML device list shows a newer 510(k) K260509 (decision 2026-03-19) from Radformation, Inc. for a matching device line ("AutoContour (RADAC V5)") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K260509

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).