V8 Diagnostic Ultrasound System, V7 Diagnostic Ultrasound System

K223387

Samsung Medison Co., Ltd. · cleared 2023-02-13 · product code IYN · Radiology

Premarket evidence — what FDA accepted

Device typehardware with ml
source quote (p.4)
“The V8 / V7 are a general purpose, mobile, software controlled, diagnostic ultrasound system. Their function is to acquire ultrasound data and to display the data as 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode. The V8 / V7 also give the operator the ability to measure anatomical structures and offer analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The proposed V8 / V7 have expanded the detection nerve type (Head: Greater Occipital / Leg: Sciatic, Common Peroneal, Tibial) of NerveTrack based on AI in the previously cleared V8/V7 (K220975) The proposed V8 / V7 have included the BiometryAssist and ViewAssist which are based on AI version from the previously cleared HERA W9/ HERA W10 (K220043).”
AlgorithmAI algorithm, deep learning based segmentation algorithm, deep learning based view recognition algorithm
source quote (p.7)
“These are the details on validation of the AI algorithm used for all the new and improved AI-based features that includes expansion of the use of NerveTrack feature and the information about the dataset the device was tested on. A deep learning based segmentation algorithm was validated using 320 fetal biometry images collected at two hospitals. A deep learning based view recognition algorithm was validated using 680 fetal heart and fetal biometry images collected at two hospitals.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (8)

Retrospective clinical

n=18 patients

endpoints: Accuracy (%); Speed (FPS)

Retrospective clinical

n=320 images · 2 site(s)

endpoints: average dice-score

Retrospective clinical

n=320 images · 2 site(s)

endpoints: error rate of circumference measured value; error rate of distance measured value; error rate of NT(Nuchal Translucency) measured value

Retrospective clinical

n=680 images · 2 site(s)

endpoints: average recognition accuracy

Retrospective clinical

n=680 images · 2 site(s)

endpoints: average dice-score

Retrospective clinical

n=888 images · 5 site(s)

endpoints: average recognition accuracy

Retrospective clinical

n=888 images · 5 site(s)

endpoints: average dice-score

Retrospective clinical

n=888 images · 5 site(s)

endpoints: error rate of area measured value; error rate of angle measured value; error rate of circumference measured value; error rate of diameter measured value; PCC value

Reported performance (8 observations)

accuracyas written: “Accuracy (%) (NerveTrack)”90.3CI 88.6 to 92.0
source quote (p.7)
“Accuracy (%) Average 90.3 95% CI 88.6 to 92.0”
diceas written: “average dice-score (BiometryAssist Segmentation)”0.928
source quote (p.8)
“The average dice-score is 0.928 (threshold 0.8)”
accuracyas written: “average recognition accuracy (ViewAssist View recognition)”94.56
source quote (p.9)
“The average recognition accuracy is 94.56% (threshold 89%)”
diceas written: “average dice-score (ViewAssist Anatomy annotation/segmentation)”0.898
source quote (p.10)
“The average dice-score is 0.898 (threshold 0.8)”
accuracyas written: “(Fetus) The average recognition accuracy (HeartAssist View recognition)”93.21
source quote (p.11)
“(Fetus) The average recognition accuracy is 93.21% (threshold 89%)”
accuracyas written: “(Adult) The average recognition accuracy (HeartAssist View recognition)”98.31
source quote (p.11)
“(Adult) The average recognition accuracy is 98.31% (threshold 84%)”
diceas written: “(Fetus) The average dice-score (HeartAssist Segmentation)”0.88
source quote (p.11)
“(Fetus) The average dice-score is 0.88 (threshold 0.8).”
diceas written: “(Adult) The average dice-score (HeartAssist Segmentation)”0.93
source quote (p.11)
“(Adult) The average dice-score is 0.93 (threshold 0.9).”

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

85
recalls in product code, 24mo
554
MAUDE reports in code, 12mo
+85%
vs code's own 3-yr baseline
14
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K252018 (decision 2026-01-05) from Samsung Medison Co., Ltd. for a matching device line ("HERA Z20 Diagnostic Ultrasound System; HERA Z20e Diagnostic Ultrasound System; HERA Z20s Diagnostic Ultrasound System; R20 Diagnostic Ultrasound System; HERA Z30 Diagnostic Ultrasound System; R30 Diagnostic Ultrasound System") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K252018

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K250999 (decision 2025-07-18) from Samsung Medison Co., Ltd. for a matching device line ("V8 Diagnostic Ultrasound System; cV8 Diagnostic Ultrasound System; V7 Diagnostic Ultrasound System; cV7 Diagnostic Ultrasound System; V6 Diagnostic Ultrasound System; cV6 Diagnostic Ultrasound System; V5 Diagnostic Ultrasound System; cV5 Diagnostic Ultrasound System; V4 Diagnostic Ultrasound System; cV4 Diagnostic Ultrasound System") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K250999

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K243702 (decision 2025-02-12) from Samsung Medison Co., Ltd. for a matching device line ("V8 Diagnostic Ultrasound System; cV8 Diagnostic Ultrasound System; V7 Diagnostic Ultrasound System; cV7 Diagnostic Ultrasound System; V6 Diagnostic Ultrasound System; cV6 Diagnostic Ultrasound System") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K243702

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K242511 (decision 2024-12-10) from Samsung Medison Co., Ltd. for a matching device line ("V5 Diagnostic Ultrasound System, H5 Diagnostic Ultrasound System, XV5 Diagnostic Ultrasound System, XH5 Diagnostic Ultrasound System, V4 Diagnostic Ultrasound System, H4 Diagnostic Ultrasound System, XV4 Diagnostic Ultrasound System, XH4 Diagnostic Ultrasound System") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K242511

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K242444 (decision 2024-11-27) from Samsung Medison Co., Ltd. for a matching device line ("HERA W10 Diagnostic Ultrasound System; HERA W9 Diagnostic Ultrasound System") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K242444

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K241971 (decision 2024-10-11) from Samsung Medison Co., Ltd. for a matching device line ("HERA Z20, R20, HERA Z30, R30 Diagnostic Ultrasound System") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K241971

  • …and 8 more.

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/K223387