(134 days)
Vivid S60N/Vivid S70N is a general-purpose ultrasound system, specialized for use in cardiac imaging. It is intended for use by, or under the direction of a qualified and trained physician for ultrasound imaging, measurement, display and analysis of the human body and fluid. The device is intended for use in a hospital environment including echo lab, other hospital settings, operating room, Cath lab and EP lab or in private medical offices. The systems support the following clinical applications: Fetal/Obstetrics, Abdominal (including renal, GYN), Pediatric, Small Organ (breast, thyroid), Neonatal Cephalic, Adult Cephalic, Cardiac (adult and pediatric), Peripheral Vascular, Musculo-skeletal Conventional, Musculo-skeletal Superficial, Urology (including prostate), Transvaginal, Transvaginal, Transrectal, Intra-cardiac and Intra-luminal, Interventional Guidance (including Biopsy, Vascular Access), Thoracic/Pleural, and Intraoperative (vascular). Modes of operation include: 3D/4D Imaging mode, B, M, PW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse and Combined modes: B/M, B/PWD or CWD, B/ Color/PWD or CWD, B/Power/PWD.
Vivid S60N / Vivid S70N is a Track 3, diagnostic ultrasound system for use by qualified and trained healthcare professionals, which is primarily intended for cardiac imaging and analysis but also includes vascular and general radiology applications. It is a full featured diagnostic ultrasound system that provides digital acquisition, processing, analysis and display capability.
The Vivid S60N / Vivid S70N consists of a mobile console with a height-adjustable control panel, color LCD touch panel, LCD display monitor and optional image storage and printing devices. It includes a variety of electronic array transducers operating in linear, curved, sector/phased array, matrix array or dual array format, including dedicated CW transducers and real time 3D transducer. System can also be used with compatible ICE transducers.
The system includes electronics for transmit and receive of ultrasound data, ultrasound signal processing, software computing, hardware for Image storage, hard copy printing, and network access to the facility through both LAN and wireless (supported by use of a wireless LAN USBadapter) connection.
The provided text focuses on the 510(k) premarket notification for the GE Vivid S60N/S70N ultrasound system. It details device descriptions, intended use, technological characteristics, and non-clinical tests. Crucially, it includes information on the "AI Summary of Testing: Easy Auto EF and Easy AFI LV," which addresses the performance of the AI algorithms incorporated into the device.
Here's a breakdown of the requested information based on the provided text:
Acceptance Criteria and Study that Proves Device Meets Acceptance Criteria
The document states that the acceptance criterion for the AI algorithms (Easy Auto EF and Easy AFI LV) is an average dice score of 91% or higher across various testing conditions.
Study Proving Device Meets Acceptance Criteria:
The study involved testing the AI algorithms on datasets from different countries, scanning views, and left ventricle volumes.
1. Table of Acceptance Criteria and Reported Device Performance:
| Feature/Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| AI Algorithm Accuracy (Average Dice Score) - Datasets from different countries | $\geq$ 91%* | 92% or higher |
| AI Algorithm Accuracy (Average Dice Score) - Datasets from different scanning views | $\geq$ 91%* | 91% or higher |
| AI Algorithm Accuracy (Average Dice Score) - Datasets from different left ventricle volumes | $\geq$ 91%* | 92% or higher |
*Note: The text states "92% or higher" and "91% or higher" for the reported performance, implying the acceptance criterion was at least 91%.
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size: 45 exams from assumed 45 patients (exact number of patients unknown due to anonymization). 135 images extracted from the 45 exams.
- Data Provenance:
- Country of Origin: Europe, Asia, US (mixed data from different countries).
- Retrospective/Prospective: Not explicitly stated, but the description of "data collection protocol was standardized across all data collection sites" and "During testing of the AI algorithm, we have included images from different countries..." suggests a pre-existing collected dataset, making it likely retrospective.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
- Number of Experts:
- Initial Delineation and Review: 2 certified cardiologists.
- Consensus Review: A panel of experienced experts.
- Qualifications of Experts:
- "Certified cardiologists" (for initial delineation and review).
- "Experienced experts" (for the consensus review panel). Specific number of years of experience is not provided, but "certified" and "experienced" imply relevant qualifications.
4. Adjudication Method for the Test Set:
- Method: A multi-stage adjudication process was used:
- Two certified cardiologists performed manual delineation.
- They then reviewed each other's annotations.
- A "consensus reading" was performed where the two cardiologists discussed agreement/disagreement.
- A panel of experienced experts further reviewed annotations that the two cardiologists could not agree on.
- The final ground truth relied on annotations that the two cardiologists agreed upon, and the consensus annotations achieved by the expert panel.
5. If a Multi Reader Multi Case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No MRMC comparative effectiveness study was done. The information provided focuses on the standalone performance of the AI algorithm (Easy Auto EF and Easy AFI LV) in terms of Dice score accuracy for image segmentation, not on reader performance with or without AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance evaluation of the AI algorithm was done. The reported "average dice score" is a metric for the algorithm's performance in automatically segmenting cardiac structures (Left Ventricle volume). The study describes the AI's accuracy in delineating these structures.
7. The Type of Ground Truth Used:
- Expert Consensus. The ground truth was established through manual delineation by certified cardiologists, followed by their mutual review, and a final consensus adjudicated by a panel of experienced experts.
8. The Sample Size for the Training Set:
- Not explicitly stated in the provided text. The document only mentions that "To ensure that the testing dataset is not mixed with the training data, we used datasets from different clinical sites for testing as compared to the clinical sites for training." This implies a training set existed and was distinct, but its size is not given.
9. How the Ground Truth for the Training Set Was Established:
- Not explicitly stated in the provided text. While the method for establishing ground truth for the test set is detailed, the process for the training set is not described. It is implied that ground truth was established, as AI models require labeled data for training, but the specific methodology is omitted.
§ 892.1550 Ultrasonic pulsed doppler imaging system.
(a)
Identification. An ultrasonic pulsed doppler imaging system is a device that combines the features of continuous wave doppler-effect technology with pulsed-echo effect technology and is intended to determine stationary body tissue characteristics, such as depth or location of tissue interfaces or dynamic tissue characteristics such as velocity of blood or tissue motion. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.