DTX Studio Clinic 3.0

K221921

Nobel Biocare AB · cleared 2023-03-28 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“DTX Studio Clinic features an AI-powered Focus Area Detection algorithm which analyzes intraoral radiographs for potential dental findings or image artifacts.”
AlgorithmAI-powered Focus Area Detection algorithm; Supervised machine learning
source quote (p.5)
“DTX Studio Clinic features an AI-powered Focus Area Detection algorithm which analyzes intraoral radiographs for potential dental findings or image artifacts.”
Adaptive (vs locked)No
PCCPNo
Cybersecurity addressedFDA source did not state this

Validation studies (2)

Standalone

n=452 images

endpoints: overall sensitivity; sensitivity per dental finding type; overall precision; localization accuracy (IoU); Dice score

standards: 21 CFR § 820, ISO 13485:2016, IEC 62304:2006+A1:2015, ISO 14971:2019

Reader study (MRMC)

n=216 images

endpoints: AUC increase; AUC difference per dental finding; specificity; sensitivity

standards: 21 CFR § 820, ISO 13485:2016, IEC 62304:2006+A1:2015, ISO 14971:2019

Reported performance (21 observations)

sensitivity0.79CI [0.74, 0.84]
source quote (p.10)
“The standalone overall sensitivity was found to be 0.79 (with 95% CI [0.74, 0.84])”
ppvas written: “Overall precision”0.45CI [0.40, 0.50]
source quote (p.10)
“Overall precision was found to be 0.45 (with 95% CI [0.40, 0.50]).”
iouas written: “Mean IoU (Caries)”58.6CI [56.2, 60.9]
source quote (p.10)
“58.6 [56.2, 60.9]”
diceas written: “Mean Dice (Caries)”71.9CI [69.9, 74.0]
source quote (p.10)
“71.9 [69.9, 74.0]”
iouas written: “Mean IoU (Periapical Radiolucency)”48.9CI [44.9, 52.9]
source quote (p.10)
“48.9 [44.9, 52.9]”
diceas written: “Mean Dice (Periapical Radiolucency)”63.7CI [59.9, 67.5]
source quote (p.10)
“63.7 [59.9, 67.5]”
sensitivityas written: “Sensitivity (Root Canal Filling Deficiency)”0.95CI [0.91, 0.99]
source quote (p.11)
“0.95 [0.91, 0.99]”
iouas written: “Mean IoU (Root Canal Filling Deficiency)”51.9CI [49.3, 54.6]
source quote (p.11)
“51.9 [49.3, 54.6]”
diceas written: “Mean Dice (Root Canal Filling Deficiency)”66.9CI [64.3, 69.4]
source quote (p.11)
“66.9 [64.3, 69.4]”
sensitivityas written: “Sensitivity (Discrepancy at Restoration Margin)”0.82CI [0.77, 0.87]
source quote (p.11)
“0.82 [0.77, 0.87]”
iouas written: “Mean IoU (Discrepancy at Restoration Margin)”48.4CI [46.0, 50.7]
source quote (p.11)
“48.4 [46.0, 50.7]”
diceas written: “Mean Dice (Discrepancy at Restoration Margin)”63.5CI [61.3, 65.8]
source quote (p.11)
“63.5 [61.3, 65.8]”
sensitivityas written: “Sensitivity (Bone Loss)”0.78CI [0.75, 0.81]
source quote (p.11)
“0.78 [0.75, 0.81]”
iouas written: “Mean IoU (Bone Loss)”44.8CI [43.4, 46.3]
source quote (p.11)
“44.8 [43.4, 46.3]”
diceas written: “Mean Dice (Bone Loss)”60.1CI [58.7, 61.6]
source quote (p.11)
“60.1 [58.7, 61.6]”
sensitivityas written: “Sensitivity (Calculus)”0.8CI [0.76, 0.84]
source quote (p.11)
“0.80 [0.76, 0.84]”
iouas written: “Mean IoU (Calculus)”55.5CI [53.7, 57.3]
source quote (p.11)
“55.5 [53.7, 57.3]”
diceas written: “Mean Dice (Calculus)”70.1CI [68.4, 71.7]
source quote (p.11)
“70.1 [68.4, 71.7]”
aurocas written: “Overall AUC increase”8.7CI [6.5, 10.9]
source quote (p.11)
“overall increase for all dental finding types together of 8.7% (CI [6.5, 10.9]).”
sensitivityas written: “Overall Sensitivity improvement”22.4CI [20.1, 24.7]
source quote (p.12)
“overall by 22.4% (with CI [20.1, 24.7])”
specificityas written: “Overall Specificity decrease”8.7CI [6.6, 10.7]
source quote (p.12)
“overall by 8.7 % with CI [6.6, 10.7]”

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
1
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K231898 (decision 2023-12-08) from Nobel Biocare AB for a matching device line ("DTX Studio Clinic (4.0)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K231898

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/K221921