Acorn 3D Software (AC-SEG-4009); Acorn 3DP Model (AC-101-XX)

K252103

Mighty Oak Medical · cleared 2025-12-02 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
“Acorn 3D Software is a modular image processing software intended for use as an interface for visualization of medical images, segmentation, treatment planning, and production of an output file. The Acorn 3D Segmentation module contains both machine learning based auto segmentation as well as semi-automatic and manual segmentation tools. Acorn 3DP Model is an additively manufactured physical replica of the virtual 3D model generated in Acorn 3D Segmentation.”
Algorithmmachine learning algorithm, convolutional neural network called U-Net
source quote (p.13)
“Acorn 3D utilizes a machine learning algorithm to assist in the segmentation of regions of interest, with a primary focus on segmenting vertebrae from the spine in DICOM images. The algorithm produces segmentations using a convolutional neural network called U-Net, which is trained on qualified ground truth data.”
Adaptive (vs locked)No
source quote (p.12)
“In accordance with the PCCP, all algorithm modifications will be trained, tuned, and locked prior to release of the software.”
PCCPYes
source quote (p.12)
“Mighty Oak Medical will make future algorithm improvements under a Predetermined Change Control Plan (PCCP; cleared as part of K234009 – no changes made to the PCCP as part of K252103).”
Cybersecurity addressedFDA source did not state this

Validation studies (3)

Retrospective clinical

n=71 cases

endpoints: DICE similarity coefficient (DSC)

Retrospective clinical

n=40 cases

endpoints: DICE similarity coefficient (DSC)

Bench

sample size not stated

endpoints: Median TRE (mm); 3rd Quartile TRE (mm)

Reported performance (3 observations)

diceas written: “Mean DSC (Vertebral, In-House)”0.9331
source quote (p.13)
“Model: Vertebral (T1-T12, L1-L5), Testing Dataset: In-House (Mighty Oak Medical), Mean DSC: 0.9331”
diceas written: “Mean DSC (Vertebral, VERSE '20)”0.94451
source quote (p.13)
“Model: Vertebral (T1-T12, L1-L5), Testing Dataset: VERSE '20, Mean DSC: 0.94451”
diceas written: “Mean DSC (Sacral, In-House)”0.9663
source quote (p.13)
“Model: Sacral, Testing Dataset: In-House (Mighty Oak Medical), Mean DSC: 0.96630”

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
3
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/K252103