HERA Z20, R20, HERA Z30, R30 Diagnostic Ultrasound System
K241971Samsung Medison Co., Ltd. · cleared 2024-10-11 · product code IYN · Radiology
Premarket evidence — what FDA accepted
source quote (p.5)
“The HERA Z20, R20, HERA Z30, R30 diagnostic ultrasound system 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, MV-Flow mode, Multi-Image mode(Dual, Quad), 3D/4D mode. The proposed HERA Z20, R20, HERA Z30, R30 have included BiometryAssist, HeartAssist, ViewAssist previously cleared in the HERA W10/W9(K230084), based on AI technology, expanding the application as below,”
source quote (p.6)
“The proposed HERA Z20, R20, HERA Z30, R30 have included BiometryAssist, HeartAssist, ViewAssist previously cleared in the HERA W10/W9(K230084), based on AI technology, expanding the application as below, A deep learning based quality assessment algorithm was validated using 3,900 fetal ultrasound images for each view. The proposed HERA Z20, R20, HERA Z30, R30 have included EzVolume, an AI feature with the similar indications for use of Fibroid Mapping of Voluson Expert 22/20/18(K231965). The proposed HERA Z20, R20, HERA Z30, R30 have included Live ViewAssist, an Al feature with the similar indications for use of SonoLyst Live of Voluson Expert 22/20/18(K231965). The proposed HERA Z20, R20, HERA Z30, R30 have included UterineContour, an Al feature with the similar indications for use of BiometryAssist of V8/XV8/XH8, V7/XV7/XH7, V6/XV6/XH6, the primary predicate(K240631). A deep learning based segmentation algorithm was validated using 450 sagittal uterus images collected at three hospitals. A deep learning based view recognition algorithm was validated using 1600 fetal ultrasound images and fetal biometry images collected at two hospitals. A deep learning based view recognition algorithm was validated using 440 fetal heart at the hospitals. A deep learning based segmentation algorithm was validated using 360 fetal biometry images collected at two hospitals.”
Validation studies (6)
Retrospective clinical
n=3,900 images
endpoints: Quality assessment ('acceptable' or 'not-acceptable'); The average Cohen's kappa coefficient is 0.818 (threshold 0.7); Time/duration test; The average speed is 30.06 FPS (threshold 20 FPS)
Retrospective clinical
n=200 cases
endpoints: segmentation performance of EzVolume tested by both qualitative (acceptance rate) and quantitative (dices score) evaluations.; Acceptance Criteria: The acceptance rate of each label (fetus, head, body, limbs, fluid, umbilical-cord, placenta, uterus segmentation) should be higher than 70%.
Retrospective clinical
n=450 images · 3 site(s)
endpoints: image segmentation, 3D coronal view adaptation.; The average dice-score of uterus is 96%; The average dice-score of endometrium is 92%; the proportion of appropriateness was evaluated as clinically diagnosable, with over 90% of all cases.
Retrospective clinical
n=1,600 images · 2 site(s)
endpoints: view recognition and anatomy annotation(segmentation).; The average recognition accuracy is 94.50% (threshold 89%); The average dice-score is 0.892 (threshold 0.8)
Retrospective clinical
n=440 cases
endpoints: view recognition, segmentation and size measurement.; The average recognition accuracy is 95.00% (threshold 89%); The average dice-score is 0.876 (threshold 0.8); The error rate of area measured value is 8% or less; The error rate of angle measured value is 4% or less; The error rate of circumference measured value is 11% or less; The error rate of diameter measured value is 11% or less
Retrospective clinical
n=360 images · 2 site(s)
endpoints: Segmentation and Size measurement.; The average dice-score is 0.928 (threshold 0.8); The error rate of circumference measured value is 8% or less.; The error rate of distance measured value is 4% or less.; The error rate of NT, NB, IT measured value is 1mm or less.
Reported performance (20 observations)
source quote (p.9)
“The average Cohen's kappa coefficient is 0.818 (threshold 0.7)”
source quote (p.10)
“Fluid 0.96”
source quote (p.10)
“Fetus 0.91”
source quote (p.10)
“Umbilical-cord 0.68”
source quote (p.10)
“Placenta 0.74”
source quote (p.10)
“Uterus 0.93”
source quote (p.11)
“Fluid 0.78”
source quote (p.11)
“Head 0.94”
source quote (p.11)
“Body 0.68”
source quote (p.11)
“Umbilical-cord 0.67”
source quote (p.11)
“Limbs 0.66”
source quote (p.11)
“Placenta 0.75”
source quote (p.11)
“Uterus 0.80”
source quote (p.12)
“The average dice-score of uterus is 96%”
source quote (p.12)
“The average dice-score of endometrium is 92%”
source quote (p.13)
“The average recognition accuracy is 94.50% (threshold 89%)”
source quote (p.13)
“The average dice-score is 0.892 (threshold 0.8)”
source quote (p.14)
“The average recognition accuracy is 95.00% (threshold 89%)”
source quote (p.14)
“The average dice-score is 0.876 (threshold 0.8)”
source quote (p.15)
“The average dice-score is 0.928 (threshold 0.8)”
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
- 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
- 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).