Velacur

K223287

Sonic Incytes · cleared 2023-04-20 · product code IYO · Radiology

Premarket evidence — what FDA accepted

Device typehardware with ml
source quote (p.5)
“Minor hardware and software changes were made to the device. One such change was the change in the vibration frequencies produced by the activation unit to create shear waves in the liver. The shear waves are now produced at 40, 50, and 60 Hz, as compared to the predicate device (45, 50, 55, 60Hz). The significant change was the addition two deep learning based algorithms. The first being an organ/liver segmentation algorithm. The second algorithm changes the predicate's rules-based scan quality to a deep learning based shear wave quality algorithm.”
Algorithmdeep learning based algorithms
source quote (p.5)
“The significant change was the addition two deep learning based algorithms. The first being an organ/liver segmentation algorithm. The second algorithm changes the predicate's rules-based scan quality to a deep learning based shear wave quality algorithm.”
Adaptive (vs locked)No
PCCPNo
Cybersecurity addressedNo

Validation studies (2)

Bench

sample size not stated

endpoints: Electrical safety; electromagnetic interference; Performance verification testing; Attenuation testing

standards: IEC 60601-1-2 Edition 4.0

Retrospective clinical

n=35 patients

endpoints: Dice Coefficient; pixel accuracy; sensitivity; specificity

Reported performance (5 observations)

sensitivity0.8CI greater than 80%
source quote (p.6)
“For the Wave Quality Guide, the Dice Scores were 0.7 or higher and the sensitivity and specificity was 80% or greater.”
specificity0.8CI greater than 80%
source quote (p.6)
“For the Wave Quality Guide, the Dice Scores were 0.7 or higher and the sensitivity and specificity was 80% or greater.”
diceas written: “Dice Score (Organ Segmentation Guide)”0.7CI greater than 0.7
source quote (p.6)
“For the Organ Segmentation Guide, the average Dice Score was greater than 0.7, and overall pixel based accuracy was greater than 80%.”
accuracyas written: “Pixel Accuracy (Organ Segmentation Guide)”0.8CI greater than 80%
source quote (p.6)
“For the Organ Segmentation Guide, the average Dice Score was greater than 0.7, and overall pixel based accuracy was greater than 80%.”
diceas written: “Dice Score (Wave Quality Guide)”0.7CI 0.7 or higher
source quote (p.6)
“For the Wave Quality Guide, the Dice Scores were 0.7 or higher and the sensitivity and specificity was 80% or greater.”

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

8
recalls in product code, 24mo
344
MAUDE reports in code, 12mo
-40%
vs code's own 3-yr baseline
2
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K233977 (decision 2024-09-04) from Sonic Incytes for a matching device line ("Velacur") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K233977

  • recall_reason_pattern

    Software/algorithm-related recall in product code IYO (Civco Medical Instruments Co. Inc., initiated 2026-03-02): "There was an error in inspection and programming of the eTRAX needle sensor for Aurora trackers. The result is a potential for the needle tip position to be incorrectly identified " Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:98513

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/K223287