ClearPoint Maestro Brain Model

K213645

ClearPoint Neuro, Inc. · cleared 2022-08-08 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.3)

“ClearPoint Maestro™ Brain Model is intended for automatic labeling, visualization, volumetric and shape quantification of segmentable brain structures from a set of MR images. This software is intended to automate the process of identifying, labelling, and quantifying the volume and shape of brain structures visible in MRI images.”

AlgorithmMachine learning derived outputs are the volumes of the gray and white matter in the cerebellum and the left and right cerebral hemispheres: Cerebellum GM, Cerebellum WM, L Cortical GM, and R Cortical GM, L Cortical WM, R Cortical WM.

source quote (p.6)

“Machine learning derived outputs are the volumes of the gray and white matter in the cerebellum and the left and right cerebral hemispheres: Cerebellum GM, Cerebellum WM, L Cortical GM, and R Cortical GM, L Cortical WM, R Cortical WM. The training data was created by the three technical experts at Philips Research Hamburg. Validation was performed in 101 subjects from the validation dataset, which was completely independent from the training data created by Philips. All machine learning derived outputs met the acceptance criteria. Their Dice coefficient was greater than 70% and their mean relative volume difference was less than 0.3 in both the full population and in all subgroups.”

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=101 patients

endpoints: segmentation accuracy success was defined as Dice coefficient >0.7; relative volume difference <0.3 between the device output and manually labeled data; reproducibility success criteria were defined as absolute volume differences <15% between segmentation performed on two repeated scans

Reported performance (1 observation)

diceas written: “Dice coefficient”0.7

source quote (p.5)

“The means of computed Dice coefficients for 21 segmented brain structures in 101 subjects from the validation dataset were significantly greater than 70%, meeting the acceptance criteria.”

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) K243657 (decision 2025-01-24) from ClearPoint Neuro, Inc. for a matching device line ("ClearPoint System (Software Version 3.0)") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K243657
re_clearance
The FDA AI/ML device list shows a newer 510(k) K233243 (decision 2023-11-27) from ClearPoint Neuro Inc. for a matching device line ("ClearPoint System (Software Version 2.2)") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K233243

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).