Search Results

The Whole Body (including head, abdomen, pelvis, limbs and extremities, joints, spine, neck, -TMJ, heart, blood vessels, and breast). [Application terms include MRCP (MR Frida, nours, ever a reasony, MR Myeiography, MR Myeiography, SAS (Surface Anatomy Scan), Dynamic Scan and Cine Imaging.]
Fluid Visualization -
2D/3D Imaging .
MR Angiography/MR Vascular Imaging -

Device Description

This submission consists of two upgrades to the MRT-50GP/E2 (FLEXART™) and MRT-50GP/H2 (FLEXART™/Hyper) system. The first is the V3.5 software, which is an upgrade over the V3.1 software. The second is the introduction of phased array coils into the coil lineup.

AI/ML Overview

The provided K970573 document describes an upgrade to existing Magnetic Resonance Imaging (MRI) systems (FLEXART™/FLEXART™/Hyper V3.5 software and new phased array coils). This submission focuses on demonstrating substantial equivalence to a previously cleared device (FLEXART™ V3.1) and enhanced performance without introducing new safety or efficacy questions.

Here's an analysis of the acceptance criteria and study information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" against which the device's performance is strictly measured in a quantitative manner for clinical efficacy. Instead, it focuses on demonstrating that the updated system maintains or improves upon the performance of the predicate device (V3.1) and adheres to general MRI safety parameters and consensus standards.

However, we can infer performance parameters that were evaluated for the upgrade:

Metric	Acceptance Criteria (Implied)	Reported Device Performance (V3.5)
Safety Parameters	Remain similar or within acceptable limits of predicate device
Max static field strength	Must be 1.5T	1.5T (Same as V3.1)
Rate of change of magnetic field	Must be 11 (13.3)T/sec	11 (13.3)T/sec (Same as V3.1)
Max. Radio frequency power deposition	Must be <0.4W/kg	<0.4W/kg (Increased from <0.34W/kg in V3.1, but still within acceptable safety limits)
Acoustic Noise levels	Must be 100.2 (98.5) dB Maximum	100.2 (98.5) dB Maximum (Same as V3.1)
Imaging Performance	Conformance to consensus standards for MRI image quality
Specification volume (Head)	At least 10 cm dsv	16cm dsv (Improved from 10 cm dsv in V3.1)
Specification volume (Body)	At least 20 cm dsv	28cm dsv (Improved from 20 cm dsv in V3.1)
Image Quality	Conformance to consensus standards for SNR, Uniformity, Slice Profiles, Geometric Distortion, Slice Thickness/Interslice Spacing	Demonstrated conformance via sample phantom and clinical images
Intended Use	Maintain or expand anatomical regions and diagnostic uses	Maintained and slightly expanded (due to new coils)

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

The document states: "Sample phantom images and clinical images were presented for new sequences and optional coils..."

Sample size: The specific number of "sample phantom images" and "clinical images" is not explicitly stated. It only mentions "sample" images.
Data provenance: The country of origin for the data is not explicitly stated. Given that Toshiba Corporation, the manufacturer, is in Japan, and the U.S. Agent is Toshiba America MRI, Inc., it is plausible the data could originate from either region or a combination. The document does not specify if the data was retrospective or prospective.

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

The document does not mention the use of experts to establish ground truth for the test set or their qualifications. The evaluation appears to be based on physical measurements and qualitative assessment ("demonstrating conformance"). This is typical for MRI system upgrades focusing on technical performance and image quality rather than diagnostic accuracy that would require expert reads.

4. Adjudication method for the test set

The document does not mention any adjudication method for the test set.

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

A multi-reader, multi-case (MRMC) comparative effectiveness study was not conducted based on the provided text. This submission is for an MRI system and software upgrade, not an AI-powered diagnostic tool, so such a study would not be applicable in this context. There is no mention of AI.

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

This is an MRI system and software upgrade, not a standalone AI algorithm. Therefore, no standalone algorithm performance study was conducted in the sense of an algorithm operating independently for diagnostic tasks. The "performance" refers to the system's ability to produce images of a certain quality, which humans then interpret.

7. The type of ground truth used

The ground truth used for evaluating the imaging performance parameters (SNR, Uniformity, Slice Profiles, Geometric Distortion, Slice Thickness/Interslice Spacing) were measurements and assessments against consensus standards requirements using phantom images and clinical images. For the general safety parameters, the ground truth was based on physical measurements (e.g., maximum static field strength, rate of change of magnetic field, RF power deposition, acoustic noise levels) compared against established safety limits.

8. The sample size for the training set

The concept of a "training set" is not applicable here as this is not a machine learning or AI-driven device requiring training data. The software upgrade improves image acquisition and processing techniques themselves, rather than learning from data.

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

As there is no training set for an AI algorithm, the question of establishing ground truth for a training set is not applicable.

Ask a Question

Ask a specific question about this device

Page 1 of 1