Sonio Detect

K240406

Sonio · cleared 2024-04-26 · product code IYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
Sonio Detect is a Software as a Service SaaS solution that aims at helping sonographers, OB/GYN MFMs and Fetal surgeons (all three designated as healthcare professionals i.e. HCP in the following) to perform their routine fetal ultrasound examinations in real-time.
AlgorithmArtificial Intelligence, Lecture of biometrics, Colorimetry for 3D and Doppler
source quote (p.12)
Artificial Intelligence Lecture of biometrics Colorimetry for 3D and Doppler
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.13)
The following quality assurance measures were applied to the development of the system: • Risk Analysis • Design Reviews • Software Development Lifecycle • Algorithm Verification (Algorithm internal validation) • Software units verification • Software verification • Simulated use testing (Validation) • Performance testing • Cybersecurity testing

Validation studies (1)

Bench

n=36,769 images

endpoints: Automatic detection of 3D fetal ultrasound images; Automatic detection of Doppler fetal ultrasound images; Automatic detection of fetal ultrasound views through reading of annotations on images; Automatic detection of 7 T1 fetal ultrasound images; Automatic detection of 18 T2/T3 fetal ultrasound images; Automatic detection of 8 fetal brain anatomical structures on the views "Transthalamic”, “Transventricular”, "Transcerebellar" at T2/T3; Automatic detection of 6 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference", "Axial view of the kidneys" at T1; Automatic detection of 21 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference”, “Axial view of the kidneys” at T2/T3; Automatic detection of 4 fetal placenta anatomical structures on the views "Placenta insertion", "Placenta location" at T2/T3; Automatic detection of 8 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length”, “Nuchal Translucency”, “Profile” at T1; Automatic detection of 6 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length", “Nuchal Translucency”, “Profile” at T2/T3; Automatic detection of the Anterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3; Automatic detection of the Posterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3; Automatic detection of the "Female sex" for fetal sex for the view "External Genitalia"; Automatic detection of the "Male sex" for fetal sex for the view "External Genitalia"

Reported performance (25 observations)

sensitivityas written: “Automatic detection of 3D fetal ultrasound images Sensitivity0.892CI (0.836-0.931)
source quote (p.14)
Automatic detection of 3D fetal ultrasound images 0.892 (0.836-0.931)
sensitivityas written: “Automatic detection of Doppler fetal ultrasound images Sensitivity0.973CI (0.937-0.988)
source quote (p.14)
Automatic detection of Doppler fetal ultrasound images 0.973 (0.937-0.988)
sensitivityas written: “Automatic detection of fetal ultrasound views through reading of annotations on images Sensitivity0.913CI (0.852-0.951)
source quote (p.14)
Automatic detection of fetal ultrasound views through reading of annotations on images 0.913 (0.852-0.951)
sensitivityas written: “Automatic detection of 7 T1 fetal ultrasound images Sensitivity0.914CI (0.906-0.921)
source quote (p.14)
Automatic detection of 7 T1 fetal ultrasound images 0.914 (0.906-0.921)
sensitivityas written: “Automatic detection of 18 T2/T3 fetal ultrasound images Sensitivity0.937CI (0.933-0.940)
source quote (p.14)
Automatic detection of 18 T2/T3 fetal ultrasound images 0.937 (0.933-0.940)
sensitivityas written: “Automatic detection of 8 fetal brain anatomical structures on the views "Transthalamic”, “Transventricular”, "Transcerebellar" at T2/T3 Sensitivity0.934CI (0.925-0.943)
source quote (p.14)
Automatic detection of 8 fetal brain anatomical structures on the views "Transthalamic”, “Transventricular”, "Transcerebellar" at T2/T3 0.934 (0.925-0.943)
specificityas written: “Automatic detection of 8 fetal brain anatomical structures on the views "Transthalamic”, “Transventricular”, "Transcerebellar" at T2/T3 Specificity0.949CI (0.942-0.955)
source quote (p.14)
Automatic detection of 8 fetal brain anatomical structures on the views "Transthalamic”, “Transventricular”, "Transcerebellar" at T2/T3 0.949 (0.942-0.955)
sensitivityas written: “Automatic detection of 6 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference", "Axial view of the kidneys" at T1 Sensitivity0.861CI (0.841-0.878)
source quote (p.14)
Automatic detection of 6 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference", "Axial view of the kidneys" at T1 0.861 (0.841-0.878)
specificityas written: “Automatic detection of 6 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference", "Axial view of the kidneys" at T1 Specificity0.938CI (0.926-0.948)
source quote (p.14)
Automatic detection of 6 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference", "Axial view of the kidneys" at T1 0.938 (0.926-0.948)
sensitivityas written: “Automatic detection of 21 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference”, “Axial view of the kidneys” at T2/T3 Sensitivity0.919CI (0.913-0.924)
source quote (p.14)
Automatic detection of 21 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference”, “Axial view of the kidneys” at T2/T3 0.919 (0.913-0.924)
specificityas written: “Automatic detection of 21 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference”, “Axial view of the kidneys” at T2/T3 Specificity0.976CI (0.974-0.978)
source quote (p.14)
Automatic detection of 21 fetal thorax and heart anatomical structures on the views "Four chambers", "LVOT”, “RVOT”, "Three vessels or Three vessels and trachea", "Abdominal Circumference”, “Axial view of the kidneys” at T2/T3 0.976 (0.974-0.978)
sensitivityas written: “Automatic detection of 4 fetal placenta anatomical structures on the views "Placenta insertion", "Placenta location" at T2/T3 Sensitivity0.967CI (0.955-0.975)
source quote (p.14)
Automatic detection of 4 fetal placenta anatomical structures on the views "Placenta insertion", "Placenta location" at T2/T3 0.967 (0.955-0.975)
specificityas written: “Automatic detection of 4 fetal placenta anatomical structures on the views "Placenta insertion", "Placenta location" at T2/T3 Specificity0.856CI (0.838-0.871)
source quote (p.14)
Automatic detection of 4 fetal placenta anatomical structures on the views "Placenta insertion", "Placenta location" at T2/T3 0.856 (0.838-0.871)
sensitivityas written: “Automatic detection of 8 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length”, “Nuchal Translucency”, “Profile” at T1 Sensitivity0.898CI (0.885-0.910)
source quote (p.15)
Automatic detection of 8 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length”, “Nuchal Translucency”, “Profile” at T1 0.898 (0.885-0.910)
specificityas written: “Automatic detection of 8 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length”, “Nuchal Translucency”, “Profile” at T1 Specificity0.862CI (0.845-0.878)
source quote (p.15)
Automatic detection of 8 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length”, “Nuchal Translucency”, “Profile” at T1 0.862 (0.845-0.878)
sensitivityas written: “Automatic detection of 6 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length", “Nuchal Translucency”, “Profile” at T2/T3 Sensitivity0.893CI (0.879-0.906)
source quote (p.15)
Automatic detection of 6 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length", “Nuchal Translucency”, “Profile” at T2/T3 0.893 (0.879-0.906)
specificityas written: “Automatic detection of 6 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length", “Nuchal Translucency”, “Profile” at T2/T3 Specificity0.956CI (0.949-0.962)
source quote (p.15)
Automatic detection of 6 fetal CRL/NT/Profile anatomical structures on the views "Crown Rump Length", “Nuchal Translucency”, “Profile” at T2/T3 0.956 (0.949-0.962)
sensitivityas written: “Automatic detection of the Anterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3 Sensitivity0.959CI (0.918-0.980)
source quote (p.15)
Automatic detection of the Anterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3 0.959 (0.918-0.980)
specificityas written: “Automatic detection of the Anterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3 Specificity0.966CI (0.924-0.986)
source quote (p.15)
Automatic detection of the Anterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3 0.966 (0.924-0.986)
sensitivityas written: “Automatic detection of the Posterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3 Sensitivity0.966CI (0.924-0.986)
source quote (p.15)
Automatic detection of the Posterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3 0.966 (0.924-0.986)
specificityas written: “Automatic detection of the Posterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3 Specificity0.959CI (0.918-0.980)
source quote (p.15)
Automatic detection of the Posterior placenta location for the views “Placenta insertion”, “Placenta location" at T2/T3 0.959 (0.918-0.980)
sensitivityas written: “Automatic detection of the "Female sex" for fetal sex for the view "External Genitalia" Sensitivity0.977CI (0.942-0.991)
source quote (p.15)
Automatic detection of the "Female sex" for fetal sex for the view "External Genitalia" 0.977 (0.942-0.991)
specificityas written: “Automatic detection of the "Female sex" for fetal sex for the view "External Genitalia" Specificity0.987CI (0.963-0.996)
source quote (p.15)
Automatic detection of the "Female sex" for fetal sex for the view "External Genitalia" 0.987 (0.963-0.996)
sensitivityas written: “Automatic detection of the "Male sex" for fetal sex for the view "External Genitalia" Sensitivity0.987CI (0.963-0.996)
source quote (p.15)
Automatic detection of the "Male sex" for fetal sex for the view "External Genitalia" 0.987 (0.963-0.996)
specificityas written: “Automatic detection of the "Male sex" for fetal sex for the view "External Genitalia" Specificity0.977CI (0.942-0.991)
source quote (p.15)
Automatic detection of the "Male sex" for fetal sex for the view "External Genitalia" 0.977 (0.942-0.991)

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
5
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K252433 (decision 2026-03-16) from Sonio for a matching device line ("Sonio Detect (v3)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K252433

  • recall_reason_pattern

    Software/algorithm-related recall in product code IYN (Philips Ultrasound, LLC, initiated 2025-10-31): "Ultrasound system compatibility issues with Apple devices running iOS 18 may cause a failure to perform live imagining." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97843

  • recall_reason_pattern

    Software/algorithm-related recall in product code IYN (GE Medical Systems, LLC, initiated 2025-09-18): "The Ultrasound-Guided Attenuation Parameter (UGAP) measurement data may display inaccurate values representing liver steatosis. This could potentially lead to inappropriate clinica" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97726

  • recall_reason_pattern

    Software/algorithm-related recall in product code IYN (GE Medical Systems China Co., Ltd. Dev. Zone National Hi-Tech; No., initiated 2025-05-16): "GE HealthCare has become aware that the Estimated Fetal Weight (EFW) measurement data feature on the Versana Premier R3 and LOGIQ F R3 series ultrasound systems can display previou" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:96992

  • recall_reason_pattern

    Software/algorithm-related recall in product code IYN (Siemens Medical Solutions USA, Inc., initiated 2024-08-15): "If ultrasound systems with software, are changed from factory default to : 1) Milliliters per second (ml/sec, mL/sec) or 2) Milliliters per minute (ml/min, mL/min); then systems wi" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:95254

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). 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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K240406