Search Results

Imaging of:

• The Whole Body (including head, abdomen, pelvis, limbs and extremities, spine, neck, TMJ, -The whole body (including reast). [Application terms include MR Fluoroscopy, MR Irography, MRCP (MR Cholangiopancreatography), MR Myelography, SAS (Surface Anatomy Scan), Dynamic Scan and Cine Imaging.]
• Fluid Visualization -
• 2D/3D Imaging -
• MR Angiography/MR Vascular Imaging -

This submission consists of three upgrades to the MRT-150/H1 and MRT-150/F1 (VISART™) system. The first upgrades the software from V3.1 (which was the software cleared with the VISART™ in K961092) to V3.5. The second is the introduction of the VISART™/Hyper system, which increases the gradient field strength over that of the standard VISART™ with V3.5 software. The third is the introduction of optional phased array coils.

The provided text describes a 510(k) summary for a Magnetic Resonance Device (MRT-150/H1, MRT-150/F1, MRT-150/H2, MRT-150/F2, marketed as VISART and VISART/Hyper). It introduces upgrades to the software (from V3.1 to V3.5) and hardware (VISART/Hyper system with increased gradient field strength and optional phased array coils).

Here's an analysis based on the information provided, specifically addressing the questions you've posed:

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes safety and imaging performance parameters for the device. While explicit "acceptance criteria" for a study aren't clearly defined as pass/fail thresholds in the typical sense for a clinical study, the specifications listed for the upgraded devices represent the targeted performance that was demonstrated to be met.

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

The document mentions "Sample phantom images and clinical images were presented for all new sequences".

• Sample Size for Test Set: This is not explicitly stated in terms of the number of clinical images or patients.
• Data Provenance: This is not explicitly stated. It's likely from Japan (where the manufacturing site is located) but not confirmed. The document does not specify if it was retrospective or prospective.

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

This information is not provided in the document. The submission focuses on technical specifications and device equivalency rather than a clinical study requiring expert ground truth for interpretation.

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

This information is not provided. As no clinical study requiring expert interpretation is described in detail, adjudication methods would not typically be mentioned.

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 reported. This submission predates the widespread integration of AI in medical imaging interpretation as described in the 510(k) summary (1996). The improvements mentioned are related to image quality provided by the updated device hardware and software, not AI assistance for human readers.

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

Not applicable/Not reported. This device is an MRI machine with upgraded software and hardware, not a standalone algorithm.

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

For the safety and performance parameters, the "ground truth" seems to be objective measurements against design specifications and consensus standards. For example:

• Safety parameters (field strength, RF power, acoustic noise): Measured values against established safety limits and NEMA guidelines.
• Imaging performance parameters (SNR, Uniformity, Slice Profiles, Geometric Distortion, Slice Thickness/Interslice Spacing): Demonstrated conformance with "consensus standards requirements" using phantom and clinical images.
  No specific ground truth (expert consensus, pathology, outcomes data) for diagnostic accuracy is described since this filing is about device upgrades and equivalency, not a diagnostic accuracy claim for a specific clinical indication based on interpreted images.

8. The sample size for the training set:

Not applicable/Not reported. This document describes an MRI device upgrade, not a machine learning algorithm that requires a training set in the conventional sense.

9. How the ground truth for the training set was established:
Not applicable/Not reported. As above, this is an MRI device, not an AI algorithm requiring a training set.

Ask a specific question about this device