V8/H8 Diagnostic Ultrasound System, V7/H7 Diagnostic Ultrasound System, V6/H6 Diagnostic Ultrasound System
Samsung Medison Co., Ltd. • Radiology • 10/03/2023
Device Purpose
The Samsung Medison V8/H7/H6 series are advanced diagnostic ultrasound systems designed to provide comprehensive imaging capabilities across numerous clinical specialties through various operational modes, including 2D, Doppler, ElastoScan, and 3D/4D imaging. These systems incorporate AI-driven NerveTrack technology for enhanced pre-injection peripheral nerve visualization and segmentation, aiming to support clinicians in diagnostic procedures and fluid analysis.
Summary
The Samsung Medison V8/H8, V7/H7, and V6/H6 Diagnostic Ultrasound Systems are general-purpose, mobile, software-controlled devices designed to acquire ultrasound images and analyze body fluids for clinical diagnosis. These systems support a wide range of clinical applications, including fetal/obstetrics, abdominal, gynecological, intra-operative, pediatric, small organ, cephalic (neonatal and adult), trans-rectal, trans-vaginal, musculoskeletal, urological, cardiac (adult and pediatric), thoracic, trans-esophageal (cardiac), and peripheral vessel imaging. They operate in various modes such as 2D, Color Doppler, Power Doppler, M mode, Pulsed Wave (PW) Doppler, Continuous Wave (CW) Doppler, Tissue Doppler Imaging (TDI), Tissue Doppler Wave (TDW), ElastoScan, combined modes, multi-image (dual, quad), and 3D/4D modes. The systems also feature new transducers (L3-22, LA2-16S, CA1-7AD for V6/H6, LM2-18 for V8/H8) and new biopsy guides, along with the ability to measure anatomical structures and offer analysis packages. A key technological advancement in these systems is the AI-based NerveTrack segmentation function, designed for pre-injection use only and not as a guide for needling. NerveTrack provides contour segmentation for nerves like the interscalene brachial plexus (ISBP) and axillary brachial plexus (AxBP), as well as surrounding structures such as bone, blood vessels, and muscle, displayed with distinct colors. Validation of the NerveTrack AI algorithm demonstrated an average detection accuracy of 90.3% and a speed of 3.61 FPS on a dataset of 2,146 images from 18 Korean subjects. For segmentation, the accuracy was 98.69% and speed was 3.62 FPS, tested on 3,836 images from 11 Korean subjects. The system's performance was evaluated across different BMI subgroups, showing good generalizability, with the maximum depth of detected nerves being 3.31 cm. The systems display real-time mechanical and thermal indices and are intended for use by appropriately trained healthcare professionals.
AI Regulatory Concerns
Powered by
Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.
Keywords
Device Metadata
Relevant Clinical Questions
- Q1. How does the NerveTrack AI algorithm's performance (accuracy and speed) vary across different nerve types beyond ISBP and AxBP, and in diverse patient populations with varying ethnicities and anatomical characteristics not represented in the Korean-only test dataset?; What are the specific imaging characteristics or limitations of the new transducers (L3-22, LA2-16S, CA1-7AD, LM2-18) compared to previously available transducers for these systems, particularly in challenging imaging scenarios?; Given that NerveTrack is for pre-injection use only, what are the quantifiable benefits it provides to clinicians in terms of pre-procedural planning or accuracy improvement for peripheral nerve blocks compared to standard ultrasound guidance without this feature?; The NerveTrack testing data mentions a maximum detected nerve depth of 3.31 cm; how does the system's performance degrade for nerves located at greater depths, and what is the effective depth limit for reliable segmentation?; Considering the NerveTrack performance was validated on data acquired with Samsung ultrasound devices including the V8, how might variations in image acquisition parameters or operator skill influence the AI's real-world effectiveness?
Risk Classification
ESL AnalysisFDA Class II via 510(k) pathway; IEC 62304 Class B (software safety classification); Authorized before §524B enforcement
Learn how Parasoft automates IEC 62304 compliance testing →Cybersecurity Evidence
Powered by SBOMator™Based on AI-generated device summaries, not the full FDA submission. Items not detected here may still be present in the complete submission package.
Supply Chain BOM Evidence
Based on the CycloneDX / OWASP ECMA-424 xBOM ecosystem. Detection is from the AI-generated summary.
Analysis:
• Analysis is based on the AI-generated device summary, not the full FDA submission package. Click "Analyze Full FDA PDF" below to scan the actual submission document.
• Evidence of ML-BOM, OBOM detected in AI-generated device summary.
• This device was authorized before §524B took effect. Cybersecurity evidence requirements were less prescriptive at the time.
• Not detected in AI-generated device summary: SBOM, SaaSBOM, HBOM, CBOM, VDR/VEX. These may be present in the full FDA submission.
Preparing a similar submission?
ESL takes complete ownership of your software evidence work - SBOM & CVE remediation with SBOMator™, static analysis & unit testing with Parasoft, traceability, and full IEC 62304 lifecycle support.
Assess Your Readiness →Or contact ESL directly