DASI Dimensions (V1.0)

K231324

DASI Simulations · cleared 2024-01-08 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
“DASI Dimensions is an image post-processing software system intended for clinical decision support in the context of pre-procedural planning of Transcatheter Aortic Valve Replacement (TAVR) procedures. The software provides users with a report of generated dimensions of cardiac structures. DASI Dimensions software is not operated by physicians.”
Algorithmstatic deep learning artificial intelligence (AI) model
source quote (p.4)
“The report is generated using proprietary algorithms that (a) detect key aortic root control points with the assistance of a static deep learning artificial intelligence (AI) model and (b) calculate anatomical measurements relevant for pre-TAVR evaluation.”
Adaptive (vs locked)No
source quote (p.4)
“The report is generated using proprietary algorithms that (a) detect key aortic root control points with the assistance of a static deep learning artificial intelligence (AI) model and (b) calculate anatomical measurements relevant for pre-TAVR evaluation.”
PCCPNo
Cybersecurity addressedYes
source quote (p.7)
“(ii) Cybersecurity testing (TP130 and TR130) was conducted to ensure that there were no unidentified vulnerabilities and that the appropriate risk control measures were implemented to protect from known vulnerabilities when the device is subject to a source of threat. The testing showed that appropriate risk control measures were implemented.”

Validation studies (5)

Standalone

sample size not stated

endpoints: error resulted in a success rate of 75.3% of points; acceptance criteria of ≤ 3 mm

Standalone

sample size not stated

endpoints: primary measurements showed ≤15% error in ≤95% of cases; secondary measurements showed ≤20% error in ≤95% of the cases

Retrospective clinical

n=40 patients

endpoints: Al generated control points performed at an 85.3% success rate achieving the acceptance criteria of ≥75%; mean percentage error in primary outputs was 0.93% (Cl: positive 8.65%, negative -6.80%) and -1.02% (CI: positive 3.49%, negative -5.54%) respectively for the annulus area and perimeter, satisfying the acceptance criteria of ≤10% error in ≥95% of cases; mean percentage difference in secondary outputs was 4.77% (Cl: positive 11.26%, negative -1.72%), 4.13% (CI: positive 11.61%, negative -3.35%), 3.29% (CI: 8.83%, negative -2.25%) respectively for the left-, right- and non-coronary sinus of valsalva diameters, 1.25% (CI: positive 8.80%, negative -6.30%) and 2.20% (CI: positive 8.46%, negative -4.06%) respectively for sinotubular junction maximum and minimum diameters, and 0.12% (Cl: positive 5.29%, negative -5.05%) for the ascending aorta maximum diameter, satisfying the acceptance criteria of ≤15% error in ≥95% of cases; mean percentage difference in the tertiary output between DASI Dimensions and clinician truthing was 2.66% (CI: positive 24.98%, negative - 19.66%) for the aortic valve angle, satisfying the acceptance criteria of ≤25% error in ≥95% of cases

Standalone

n=14 cases

endpoints: excellent inter-operator agreement (precision) and to clinician ground truth measurements (accuracy), with an ICC of 0.96 and ≤ 10% difference from clinician measurements in ≥95% of cases

Bench

n=14 cases

endpoints: resulting automatic annulus area measurements had percent errors ≤ 10%, meeting the acceptance criteria

Reported performance (0 observations)

FDA source did not state a quantitative performance metric — non-reporting is itself the signal.

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/K231324