Search Results

The device is a general purpose ultrasound system intended for use by qualified and trained healthcare professionals. Specific clinical applications remain the same as previously cleared: Fetal/OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Vascular; Transvaginal (including GYN); Transrectal

Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography and Combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/ PWD, B/Elastography. The Voluson™ Expert 18, Voluson™ Expert 20, Voluson™ Expert 22 is intended to be used in a hospital or medical clinic.

The systems are full-featured Track 3 ultrasound systems, primarily for general radiology use and specialized for OB/GYN with particular features for real-time 3D/4D acquisition. They consist of a mobile console with keyboard control panel; color LCD/TFT touch panel, color video display and optional image storage and printing devices. They provide high performance ultrasound imaging and analysis and have comprehensive networking and DICOM capability. They utilize a variety of linear, curved linear, matrix phased array transducers including mechanical and electronic scanning transducers, which provide highly accurate real-time three-dimensional imaging supporting all standard acquisition modes.

The following probes are the same as the predicate: RIC5-9-D, IC5-9-D, RIC6-12-D, 9L-D, 11L-D, ML6-15-D, RAB6-D, C1-6-D, C2-9-D, M5Sc-D, RM7C, eM6CG3, RSP6-16-D , RIC10-D, 6S-D and L18-18iD, RIC12-D.

The existing cleared Probe C1-6-D is being added to previously cleared SW- AI Feature Sonolyst 1st Trimester.

The provided text describes the FDA 510(k) clearance for the Voluson Expert Series ultrasound systems, specifically focusing on the AI feature "Sonolyst 1st Trimester" and the addition of the C1-6-D transducer to this feature.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

Additional Performance Data (Mean values across transabdominal and transvaginal scans):

2. Sample Sizes Used for the Test Set and Data Provenance

• SonoLyst 1st Trim IR: 7970 images

• SonoLyst 1st Trim X: 4931 images

• SonoLyst 1st Trim Live: 9111 images

• SonoBiometry CRL: 243 images

• Specific to Probegroup CL2 (which includes C1-6-D Probe): Data was collected from 396 patients.

• Data Provenance: Data was collected from multiple geographical sites including the UK, Austria, India, and USA. The data was collected using different systems (GE Voluson V730, P8, S6/S8, E6, E8, E10, Expert 22, Philips Epiq 7G).

• Retrospective/Prospective: The document does not explicitly state whether the test data was retrospective or prospective. However, the mention of "data acquired with transabdominal vs transvaginal probes" and "patients within the dataset includes pregnancies between 11 and 14 weeks of gestation, with no known fetal abnormalities at the time of imaging" suggests that the images were pre-existing or collected specifically for this evaluation, implying a retrospective or a pre-defined prospective collection for the study.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

• Initial Curation: A single sonographer curated (sorted and graded) the images initially.
• Review Panel for Graded Images: Where the system's grading differed from the initial ground truth, the images were reviewed by a 5-sonographer review panel to determine the grading accuracy of the system.
• Qualifications: The document identifies them as "sonographers." Specific years of experience or expertise in fetal ultrasound are not provided, other than their role in image curation and review.

4. Adjudication Method for the Test Set

• Initial Sorting and Grading: Images were initially curated (sorted and graded) by a single sonographer.
• Reclassification during Sorting: The SonoLyst IR/X First Trimester process resulted in some images being reclassified during sorting based on the majority view of the panel (after the step where the system had sorted them).
• Grading Accuracy Review: For graded images where the initial single sonographer's ground truth differed from the system, a 5-sonographer review panel was used to determine the accuracy. This suggests an adjudication process where the panel formed a consensus or majority opinion to establish the final ground truth when discrepancies arose. The exact method (e.g., simple majority, weighted vote) is not specified beyond "majority view of the panel."

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

• The document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done to evaluate how much human readers improve with AI vs. without AI assistance. The testing focused on the standalone performance of the AI algorithm against a ground truth established by sonographers.
• The verification of SonoLystLive 1st Trim Trimester features was based on the "average agreement between a sonographer panel and the output of the algorithm regarding Traffic light quality," which involves human readers assessing traffic light quality in relation to the algorithm's output, but it's not a study designed to measure human improvement with AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

• Yes, a standalone performance evaluation was conducted. The performance metrics (SonoLystIR, SonoLystX, SonoLystLive, SonoBiometry CRL success rate) are reported as the accuracy of the algorithm comparing its output directly against the established ground truth. This is a measure of the algorithm's ability to perform its specified functions independently.

7. The Type of Ground Truth Used

• The ground truth was established through expert consensus/review by sonographers.
  • Initial curation by a single sonographer.
  • Review and reclassification during sorting based on the "majority view of the panel."
  • A 5-sonographer review panel was used to determine grading accuracy for discrepancies.
• The ground truth also adhered to standardized imaging protocols based on internationally recognized guidelines (AIUM Practice Parameter, AIUM Detailed Protocol, ISUOG Practice Guidelines, ISUOG Detailed Protocol, and the study by Yimei Liao et al.) which informed the quality and consistency of the expert review.

8. The Sample Size for the Training Set

• 122,711 labelled source images from 35,861 patients were used for training.

9. How the Ground Truth for the Training Set Was Established

• The document states that "Data used for both training and validation has been collected across multiple geographical sites using different systems to represent the variations in target population."
• While the specific method for establishing ground truth for the training set is not explicitly detailed in the same way as the test set, it can be inferred that similar expert labeling and curation processes would have been applied given the emphasis on "labelled source images." The document focuses on the test set truthing process as part of verification, implying that the training data would have undergone a robust labeling process to ensure quality for machine learning.

Ask a specific question about this device