Search Results

smart-sync is intended to generate a gating signal for MR scanners (1.5T and 3T) for motion compensation by detecting the heartbeat of a patient using Doppler ultrasound. Thus, smart-sync is intended to improve the image quality by reducing movement artefacts for MR images of the whole body, where motion compensation of the heart movement is necessary.

smart-sync is intended to be used on pregnant women, where the fetus is examined. smart-sync is also intended to be used for adult MR examinations.

smart-sync is not intended to monitor any physiological parameters.

smart-sync is an MRI-compatible Doppler ultrasound system that determines the cardiac cycle of patients and synchronizes it with the MRI imaging, smart-sync can be used for the synchronization of the heartbeat both for fetuses and adults.

The heartbeat of the patient is detected by positioning an ultrasound sensor above the patient's heart. The ultrasound sensor is fixated with a flexible belt. The reflection of Doppler ultrasound signals is analyzed, and a trigger signal is derived for every heartbeat. smart-sync sends the Doppler ultrasound signal and the trigger signal (synchronization signal) to the MRI scanner utilizing a wireless connection.

The provided document is a 510(k) summary for the device "smart-sync." It describes the device's intended use, technological characteristics, and a summary of non-clinical and clinical performance data. However, it does not provide detailed information about specific acceptance criteria or a comprehensive study report with quantitative performance metrics for the AI component of the device.

Based on the provided text, the "smart-sync" device does not appear to be an AI/ML-driven device in the context of image analysis or diagnostic aid. It is described as a Doppler ultrasound system that generates a gating signal for MR scanners to compensate for motion by detecting a patient's heartbeat. Its primary function is to improve image quality by reducing movement artifacts, not to perform analysis or diagnosis using AI.

Therefore, many of the requested points regarding AI/ML device testing (e.g., sample size for test set, number of experts for ground truth, MRMC study, standalone performance) are not applicable to the "smart-sync" device as described in this 510(k) summary.

Here's what can be extracted and inferred from the provided text, addressing the points where information is available or can be logically deduced:

Device Name: smart-sync
Product Code: LNH
Regulation Name: Magnetic resonance diagnostic device

Acceptance Criteria and Device Performance (as far as can be inferred for this type of device):

The "acceptance criteria" for a motion-gating device like smart-sync would primarily revolve around its ability to reliably detect the heartbeat and provide an accurate gating signal to the MRI machine, leading to improved image quality. The document refers to "clinical performance" and "effectiveness in improving image quality," but it does not specify quantitative metrics or thresholds for these.

Since this is a non-AI device focused on mechanical/electrical performance, traditional AI performance metrics (like sensitivity, specificity, AUC) are not directly relevant. The "performance" is about its ability to generate a correct and timely gating signal and the resulting visual improvement in MR images.

1. A table of acceptance criteria and the reported device performance:
See table above. Quantitative acceptance thresholds (e.g., minimum percentage reduction in motion artifact, or specific ECG/gating signal accuracy) are not provided in the document. The performance is described qualitatively as "effective in improving image quality" and "safe."

2. Sample size used for the test set and the data provenance:

• Sample Size for Test Set: Not explicitly stated in terms of a numerical count of patients or studies. The text mentions "Clinical studies from clinicians at different hospitals across Europe and the US." This implies a multi-site study, but without specific numbers.
• Data Provenance: "Europe and the US" (country of origin). The studies appear to be "clinical studies," implying a prospective or at least a clinical trial setting rather than purely retrospective database analysis.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not Applicable in the context of AI/ML-driven diagnostic device evaluation.
• For a device like smart-sync, the "ground truth" would be the actual cardiac rhythm and the resulting improvement (or lack thereof) in image quality as assessed by radiologists in a clinical setting. The document mentions "clinicians at different hospitals" and "radiographers and radiologists" as the intended user group who would assess image quality.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

• Not Applicable (as this is not an AI diagnostic device and no AI-specific adjudication of ground truth for classification tasks is described).

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:

• Not Applicable. The device is a motion compensation tool, not an AI assistance tool for human readers. No MRMC study comparing human performance with/without AI assistance is mentioned because AI assistance is not its function.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

• Not Applicable. The device is described as generating a gating signal for the MR scanner, which is a standalone function in this context (i.g., it produces a signal based on its sensor input). However, this is not an "AI algorithm only" performance test in the typical sense of diagnostic AI. The performance is then assessed in a clinical context by human readers evaluating the resulting MR images.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

• The "ground truth" for the device's effectiveness appears to be primarily clinical assessment of image quality by clinicians/radiologists based on whether motion artifacts are reduced and images are improved. The accuracy of heartbeat detection would be the underlying "ground truth" for the device's direct function.

8. The sample size for the training set:

• Not Applicable. This is not an AI/ML device that requires a "training set" in the context of machine learning model development.

9. How the ground truth for the training set was established:

• Not Applicable. As per point 8.

Summary of Key Findings from the Document regarding "smart-sync":

• Device Type: MRI-compatible Doppler ultrasound system for cardiac gating.
• Purpose: To generate a gating signal for MR scanners (1.5T and 3T) to compensate for heart movement, thereby improving image quality by reducing motion artifacts.
• Patient Groups: Adults and pregnant women (fetus examined from 30th gestational week).
• Technology: Uses Doppler ultrasound to detect myocardial wall and blood flow motion, deriving a trigger signal. Wireless transmission to MRI scanner.
• Performance Evaluation:
  • Bench Tests: Demonstrated effectiveness in providing gating signals and compliance with safety standards.
  • Clinical Studies: Conducted at hospitals in Europe and the US, indicating effectiveness in improving image quality for cardiac MRI examinations in the intended patient population.
  • Usability Tests: Confirmed safe use by radiographers and radiologists.
• Substantial Equivalence: Claimed based on clinical evidence, non-clinical bench testing, electrical safety, electromagnetic compatibility, product verification and validation, showing it does not raise different questions of safety and effectiveness compared to predicate devices (ECG-based gating cables) and a reference device (Doppler-based fetal monitors). The different acquisition method (Doppler ultrasound vs. ECG) was addressed through comparison with a Doppler reference device and analytical comparison showing similar cardiac information can be derived.

Ask a specific question about this device