Search Results

The device is a general-purpose ultrasound system. Specific clinical applications remain the same as previously cleared: Fetal/OB; Abdominal (including renal and GYN/pelvic); Pediatric; Small Organ (breast, testes, thyroid, salivary gland, lymph nodes, pediatric and neonatal patients); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Peripheral Vascular (PV); Musculo-skeletal Conventional and Superficial; Transrectal (TV).

Intended Use: Diagnostic ultrasound imaging or fluid flow analysis of the human body as follows:
Fetal / Obstetrics; Abdominal (including renal, GYN/Pelvic); Pediatric; Small Organ (breast, testes, thyroid, salivary gland, lymph nodes, pediatric and neonatal patients); Neonatal Cephalic; Adult Cephalic; Cardiac (Adult and Pediatric); Peripheral Vascular; Musculo-skeletal Conventional; Musculo-skeletal Superficial; Transrectal (includes urology/prostate); Transvaginal (includes infertility monitoring of follicle development).

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 accurate real-time three-dimensional imaging supporting all standard acquisition modes.

This document describes the GE Healthcare Voluson S8/S10/S10 Expert ultrasound system and its equivalence to predicate devices, but it does not provide acceptance criteria or a study that proves the device meets specific acceptance criteria in the way you've outlined for AI/ML performance evaluation.

Instead, this is a 510(k) premarket notification summary from the FDA, focusing on:

• Substantial Equivalence: Comparing the new device to existing legally marketed devices (predicates).
• Safety and Effectiveness: Ensuring the device meets recognized safety standards and performs as intended.

Here's an analysis based on the provided text, addressing your questions where possible:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not contain a table of numerical acceptance criteria or reported specific device performance metrics for AI/ML algorithms as typically seen in studies evaluating diagnostic accuracy (e.g., sensitivity, specificity, AUC).

Instead, it asserts "substantial equivalence" to predicate devices, meaning its performance characteristics are deemed similar enough that it doesn't raise new questions of safety or effectiveness. The "performance" discussed is related to its ability to perform diagnostic ultrasound imaging and fluid flow analysis, offering various imaging modes, and complying with safety standards.

2. Sample Size Used for the Test Set and Data Provenance:

• Sample Size for Test Set: Not applicable / Not provided. This document specifies that "The subject of this premarket submission... did not require clinical studies to support substantial equivalence." Therefore, no specific test set of patient data was used for performance evaluation of new AI/ML features in what would typically be considered an AI/ML clinical study.
• Data Provenance (country of origin, retrospective/prospective): Not applicable / Not provided.

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

• Number of Experts: Not applicable / Not provided. Since clinical studies for substantial equivalence were not required, there was no separate ground truth establishment process involving external experts for performance evaluation. The ground truth for general ultrasound imaging is established through standard medical practice and expert interpretation.
• Qualifications of Experts: Not applicable / Not provided specifically for this submission.

4. Adjudication Method for the Test Set:

• Adjudication Method: Not applicable / Not provided. No specific test set performance evaluation was described.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

• MRMC Study Done: No. The document explicitly states: "The subject of this premarket submission... did not require clinical studies to support substantial equivalence."
• Effect Size of Human Readers with vs. without AI Assistance: Not applicable / Not provided.

6. Standalone (Algorithm Only) Performance Study:

• Standalone Study Done: No. The document states that clinical studies were not required. The "improved version of existing software feature IOTA LR2 model called IOTA Simple Rules," "3D Analysis feature of the endometrial cavity called SonoMetrium," "enhanced feature of existing software feature HDlive called HDlive Silhouette," and "enhanced feature of existing software feature SRI called VSRI" are mentioned as being "previously cleared with K172342" or are enhancements of existing features. This indicates that these features were likely evaluated in the context of substantial equivalence to previous versions or predicate devices, rather than as new standalone AI detections requiring their own independent performance studies for this specific submission.

7. Type of Ground Truth Used:

• Type of Ground Truth: Not explicitly stated or required for this type of submission. For ultrasound imaging systems, ground truth is typically established by medical professionals through established diagnostic protocols, expert interpretation, and potentially correlation with other diagnostic modalities or pathology where applicable. However, no specific ground truth was established for a new clinical performance study for this submission.

8. Sample Size for the Training Set:

• Sample Size for Training Set: Not applicable / Not provided. As this submission focuses on substantial equivalence of an ultrasound system and enhancements to existing software features, specific AI model training data sizes are not detailed in this regulatory document.

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

• How Ground Truth Was Established: Not applicable / Not provided.

Summary of AI/ML Specifics from the Document:

The document mentions several "improved" or "enhanced" software features that could potentially involve AI/ML components (e.g., IOTA Simple Rules, SonoMetrium, HDlive Silhouette, VSRI, Radiantflow). However, for this specific 510(k) submission (K180374), these features are explicitly stated to be either:

• "previously cleared with K172342" (a reference predicate).
• "an improved version of existing software feature" or "an enhanced feature of existing software feature."

This implies that the novelty of these features for this particular submission was not in their initial safety and effectiveness evaluation as new AI/ML tools, but rather in their inclusion or minor enhancement within the Voluson S8/S10/S10 Expert system, aligning with existing predicate clearances. Therefore, detailed performance studies for these specific AI/ML components are not provided within this document, as they were likely addressed in previous clearances (like K172342 for the Voluson E Series).

Conclusion: This document is a 510(k) premarket notification for an ultrasound system, demonstrating substantial equivalence to predicate devices and adherence to general safety and performance standards. It does not contain the detailed AI/ML specific acceptance criteria or performance study data that you requested, as the submission strategy relied on substantial equivalence rather than novel clinical performance data for new AI/ML features.

Ask a specific question about this device