Transpara Density 1.0.0

K232096

Screenpoint Medical B.V. · cleared 2023-12-11 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.9)
“Transpara Density is a software-only device.”
Algorithmdeep learning artificial intelligence algorithms
source quote (p.3)
“Transpara Density utilises deep learning artificial intelligence algorithms to automatically determine volumetric breast density (VBD), breast volume, and an ACR BI-RADS 5th Edition breast density category to aid health care professionals in the assessment of breast tissue composition.”
Adaptive (vs locked)FDA source did not state this
PCCPNo
Cybersecurity addressedNo

Validation studies (6)

Standalone

n=5,468 cases

endpoints: Pearson correlation between VBD computed with Transpara Density and the physics model; Pearson correlation coefficient for breast volume

Standalone

n=190 cases

endpoints: Pearson correlation coefficient between VBD and breast MRI

Standalone

n=10,804 cases

endpoints: Pearson correlation coefficient between CC and MLO views; mean absolute deviation between CC and MLO views

Standalone

n=10,804 cases

endpoints: Pearson correlation coefficient between right and left breast VBD; mean absolute deviation between right and left breast VBD

Standalone

n=433 cases

endpoints: Pearson correlation coefficient between VBD on FFDM and DBT; mean absolute deviation between VBD on FFDM and DBT; quadratically weighted kappa for DG values for DM and DBT

Reader study (MRMC)

n=800 patients

endpoints: Overall accuracy for four breast density categories; Cohen's weighted kappa for four breast density categories; Overall accuracy for dense vs non-dense assessment; Cohen's weighted kappa for dense vs non-dense assessment; Sensitivity for dense vs. non-dense classification; Specificity for dense vs. non-dense classification

Reported performance (7 observations)

sensitivity87.3CI 95% CI: 83.6% - 90.3%
source quote (p.11)
“For dense vs. non-dense classification, Transpara Density has a sensitivity of 87.3% [95% CI: 83.6% - 90.3%]”
specificity90.4CI 95% CI: 87.2% - 92.9%
source quote (p.11)
“and a specificity of 90.4% [95% CI: 87.2% - 92.9%].”
agreement_kappaas written: “Quadratically weighted kappa for DG values for DM and DBT”0.81CI 95% CI: 0.787 - 0.835
source quote (p.11)
“There was a high agreement in the four category DG values for DM and DBT with a quadratically weighted kappa of 0.810 [95% CI: 0.787 - 0.835].”
accuracyas written: “Overall accuracy for four breast density categories”70.8CI 95% CI: 67.6% - 73.9%
source quote (p.11)
“Overall the accuracy was 70.8% [95% CI: 67.6% - 73.9%]”
agreement_kappaas written: “Cohen's weighted kappa for four breast density categories”0.74CI 95% CI: 0.70 - 0.79
source quote (p.11)
“[Cohen's weighted kappa = 0.74 [95% CI: 0.70 - 0.79] for the four breast density categories (a-b-c-d)”
accuracyas written: “Overall accuracy for dense vs non-dense assessment”88.9CI 95% CI: 86.6% - 90.9%
source quote (p.11)
“and 88.9% [95% CI: 86.6% - 90.9%]”
agreement_kappaas written: “Cohen's weighted kappa for dense vs non-dense assessment”0.78CI 95% CI: 0.72 - 0.84
source quote (p.11)
“[Cohen's weighted kappa = 0.78 [95% CI: 0.72 - 0.84]] for the dense vs non-dense assessment.”

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
1
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K241831 (decision 2024-11-25) from ScreenPoint Medical B.V. for a matching device line ("Transpara (2.1.0)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K241831

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/K232096