DTX Studio Assist

K252086

Nobel Biocare C/O Medicim NV · cleared 2025-11-17 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“DTX Studio Assist is a software development kit (SDK) that makes a selection of algorithms (including AI-based algorithms) available through a clean, well-documented API.”
AlgorithmAI-based algorithms, supervised machine learning algorithms
source quote (p.5)
“DTX Studio Assist is a software development kit (SDK) that makes a selection of algorithms (including AI-based algorithms) available through a clean, well-documented API. DTX Studio Assist and primary predicate device (DTX Studio Clinic 4.0 - K231898) share the following characteristics: - Supervised machine learning algorithms”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (4)

Standalone

n=1,530 images

endpoints: overall sensitivity of 88.8%; specificity of 96.6%; segmentation accuracy confirmed by a mean Dice score of 86.5%

Standalone

n=274 images

endpoints: sensitivity of 93.2% for ABL line segment matching; specificity of 88.6% for ABL line segment matching; average mean average error of 0.26 mm

Standalone

n=220 images

endpoints: overall average Dice score of 86.5%; overall average sensitivity of 89.0%; overall average specificity of 95.2%

Reader study (MRMC)

n=216 images

endpoints: significantly improved dentists' diagnostic detection and localization performance; statistically significant increase in the Area Under the Curve (AUC) in the aided arm compared to the unaided control arm

Reported performance (5 observations)

sensitivity93.2
source quote (p.7)
“The algorithm achieved a sensitivity of 93.2% and specificity of 88.6% for ABL line segment matching.”
specificity96.6
source quote (p.7)
“The algorithm achieved an overall sensitivity of 88.8% and specificity of 96.6%, with segmentation accuracy confirmed by a mean Dice score of 86.5%, closely matching inter-expert agreement”
diceas written: “mean Dice score”86.5
source quote (p.7)
“The algorithm achieved an overall sensitivity of 88.8% and specificity of 96.6%, with segmentation accuracy confirmed by a mean Dice score of 86.5%, closely matching inter-expert agreement”
diceas written: “overall average Dice score”86.5
source quote (p.8)
“The algorithm demonstrated strong performance, achieving an overall average Dice score of 86.5%, an overall average sensitivity of 89.0%, and an overall average specificity of 95.2%.”
aurocas written: “AUC increase”8.7CI p < 0.001
source quote (p.8)
“The analysis showed a highly significant AUC increase (p < 0.001) of 8.7% overall in the aided arm.”

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
-100%
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/K252086