Imaging of the whole body (including the head, abdomen, heart, pelvis, spine, blood vessels, limbs and extremities), fluid visualization, 2D/3D Imaging, MR Angiography, MR. Fluoroscopy.

Device Description

Version 3.1 software consists of two model upgrades to the FLEXART™ system. The MRT-50GP/E2 (Flexart™) includes such new applicational features as FastASE, QuadScan and MR Fluoroscopy for scanning and MSOFT and PASTA for fat supression. The MRT-50GP/H1 (Flexart™/Hyper) increases the gradient field strength over that of the Flexart™ .

AI/ML Overview

This 510(k) summary describes upgrades to an MRI system (FLEXART™ V3.1), focusing on improvements in hardware and software. It primarily discusses safety parameters and imaging performance in the context of demonstrating substantial equivalence to a previously cleared device. Due to the nature of this submission (upgrades to an existing MRI system for improved image quality and functionality, rather than a novel AI/CAD device), many of the specific questions regarding AI device evaluation (e.g., acceptance criteria for diagnostic performance metrics, human reader studies, ground truth establishment) are not directly applicable or reported in this document.

Here's an analysis based on the provided text, highlighting what is and isn't available:

Analysis of Acceptance Criteria and Device Performance Study (K962138)

This submission (K962138) concerns upgrades to an existing Magnetic Resonance Device (FLEXART™ V3.1). The primary goal of the submission is to demonstrate substantial equivalence to a previously cleared device (K933018, FLEXART™) by showing that the upgrades improve performance without raising new questions of safety or efficacy.

Therefore, the "acceptance criteria" and "device performance" in this context are focused on safety parameters and qualitative imaging performance improvements rather than quantitative diagnostic accuracy metrics typically seen for AI/CAD products.

1. Table of Acceptance Criteria and Reported Device Performance

Given that this is an upgrade to an existing MRI system, the "acceptance criteria" are implicitly tied to maintaining or improving upon the safety and image quality of the predicate device, and demonstrating conformance with consensus standards.

Acceptance Criteria Category	Specific Criteria (Implicit/Explicit)	Reported Device Performance (FLEXART™ V3.1)
Safety Parameters	- Max static field strength compliant. - Rate of change of magnetic field (τ=1000ms) compliant and below IEC standard. - Max RF power deposition compliant. - Acoustic Noise levels within acceptable limits (below 100 dB(A) for patient-observed levels).	MRT-50GP/E2: - Max static field strength: 0.5 T (Same as predicate) - Rate of change of magnetic field: 11 T/sec (Same as predicate) - Max RF power deposition: <0.256 W/kg (Same as predicate) - Acoustic Noise levels: 100.2 dB (A) (Max) (Same as predicate) MRT-50GP/H1 (Hyper): - Max static field strength: 0.5 T (Same as predicate) - Rate of change of magnetic field: 13.3 T/sec (Higher but explicitly stated as "less than the IEC standard and that of other manufacturers systems currently on the market") - Max RF power deposition: <0.34 W/kg (Higher but within acceptable limits) - Acoustic Noise levels: 98.5 dB (A) (Max) (Slightly improved/lower than predicate)
Imaging Performance	- Conformance with consensus standards for: - Signal-to-Noise ratio (SNR) - Uniformity - Slice Profiles - Geometric Distortion - Slice Thickness/Interslice Spacing	"Sample phantom images and clinical images were presented for all new sequences, demonstrating conformance with consensus standards requirements for Signal-to-Noise ratio, Uniformity, Slice Profiles, Geometric Distortion and Slice Thickness/Interslice Spacing." (Note: No specific quantitative performance metrics are provided in this summary, only a qualitative statement of conformance).
Intended Use	- Maintenance of current anatomical regions and diagnostic uses.	The new software ("Software upgrades provide for improved image quality, but do not change the intended uses of the device.") maintains the broad Intended Use of Head, Body, Extremity, Spine, Neck, TMJ, and Heart, and diagnostic uses like 2D/3D Imaging, MR Angiography, MR Fluoroscopy.
Equivalency	- Demonstrates substantial equivalence to K933018 (FLEXART™) without introducing new questions of safety or efficacy.	The submission asserts that the upgrades "improve the performance of the basic FLEXART™, without introducing new questions of safety or efficacy."

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

Test Set Description: The document mentions "Sample phantom images and clinical images were presented for all new sequences."
Sample Size: Not specified. The number of phantom and clinical images used is not provided.
Data Provenance: Not specified. The country of origin or whether the data was retrospective or prospective is not mentioned. Given the device is manufactured in Japan, it's plausible the initial data may have originated there, but this is not stated.

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

Ground Truth Establishment: For imaging performance, the assessment was based on "conformance with consensus standards requirements." This implies evaluation against established MRI image quality metrics rather than expert consensus on a specific diagnostic finding.
Number/Qualifications of Experts: Not specified. There is no mention of experts involved in establishing a specific "ground truth" for the test set images or their qualifications.

4. Adjudication method for the test set

Adjudication Method: Not applicable/Not specified. This type of submission does not typically involve diagnostic adjudication for a test set. The evaluation is against technical standards for image quality.

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

MRMC Study: No. This device is an MRI scanner system, not an AI/CAD diagnostic aid. Therefore, an MRMC comparative effectiveness study to assess human reader improvement with AI assistance is not relevant and was not performed.

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

Standalone Performance: No. This device is an MRI scanner; it does not perform automated diagnostic interpretation or analysis as a standalone algorithm. Its "performance" refers to its ability to generate high-quality images.

7. The type of ground truth used

Ground Truth Type: For imaging performance, the "ground truth" implicitly refers to technical conformance with established consensus standards for MRI image quality (e.g., NEMA guidelines, inherent properties of phantom materials) for metrics like SNR, Uniformity, etc. For safety parameters, the "ground truth" is compliance with regulatory limits and industry standards (e.g., IEC standards for gradient fields, NEMA for acoustic noise).

8. The sample size for the training set

Training Set Sample Size: Not applicable/Not specified. This document describes a software and hardware upgrade to an MRI scanner, not an AI model requiring a "training set." The software improvements are likely based on engineering design and optimization, not machine learning training data in the modern sense.

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

Training Set Ground Truth Establishment: Not applicable/Not specified. As there is no mention of a "training set" for an AI model, the method for establishing its ground truth is not relevant to this submission.

Summary

{0}------------------------------------------------

DEC 2 3 1996

K962138

510(k) Summary

SUMMARY OF SAFETY AND EFFECTIVENESS

1.	Model Name:	MRT-50GP/E2 and MRT-50GP/H1
	Device Name:	Magnetic Resonance Device
	Trade/Proprietary Name:	FLEXARTTM V3.1

Establishment Registration: 2. #2936923
TOSHIBA AMERICA MRI, INC. 3. U.S. Agent Name and Address: 280 Utah Ave. South San Francisco, CA 94080

Steven M. Kay Contact Person: (714) 730-5000

Toshiba Corporation Manufacturing Site: 4. 1385 Shimoishigami Otawara-shi, Tochigi-Ken Japan 324

May 30 1996 5. DATE OF SUBMISSION:

ર. DEVICE DESCRIPTION

SAFETY PARAMETERS 7.

	MRT-50GP	MRT-50GP/E2	MRT-50G/H1
Maximum static field strength:	0.5 T	Same	Same
Rate of change of magnetic field (τ = 1000ms):	11 T/sec,	Same	13.3 T/sec.
Max. Radio frequency power deposition:	<0.256 W/kg	Same	<0.34 W/kg
Acoustic Noise levels:	100.2 dB (A)	Same	98.5 dB (A)
	(Maximum)	(Maximum)	(Maximum)

Acoustic noise data was measured in accordance with NEMA guidelines. The user is cautioned to have the patient wear acoustic noise protection during scanning, that the patient observed noise level is significantly below 100 dB (A).

{1}------------------------------------------------

510(k) Summary (cont'd)

SUMMARY OF SAFETY AND EFFECTIVENESS

8. IMAGING PERFORMANCE PARAMETERS

		MRT-150A	MRT-150/H1	MRT-150/F1
Specification volume:	Head:	10.4 cm dsv	14 cm dsv	14 cm dsv
	Body:	10.4 cm dsv	28 cm dsv	28 cm dsv

Sample phantom images and clinical images were presented for all new sequences, demonstrating conformance with consensus standards requirements for Signal-to-Noise ratio, Uniformity, Slice Profiles, Geometric Distortion and Slice Thickness/Interslice Spacing.

INTENDED USE 9.

Anatomical Region:	Head, Body, Extremity, Spine, Neck, TMJ, and Heart
Nuclei excited:	Hydrogen
Diagnostic Use:	Imaging of the whole body (including the head, abdomen, heart, pelvis, spine, blood vessels, limbs and extremities), fluid visualization, 2D/3D Imaging, MR Angiography, MR. Fluoroscopy.

10. EQUIVALENCY INFORMATION

Toshiba America Medical Systems, Inc. (TAMS) believes the FLEXART™ and FLEXARTM/HYPER systems with V3.1 are substantially equivalent to the MRT-50GP FLEXART™ because they consist of hardware and software upgrades that improve the performance of the basic FLEXART™, without introducing new questions of safety or efficacy. The FLEXART™ was cleared by K933018. The increased gradient field strength is less than the IEC standard and that of other manufacturers systems currently on the market. New surface coils for this system received prior market clearance from the Agency. Software upgrades provide for improved image quality, but do not change the intended uses of the device. MR Fluoroscopy is similar to the same function that was cleared for the MRT-35A. Good Manufacturing Practices requirements are unchanged from those already in effect for the FLEXART™.

Regulation Number and Section

§ 892.1000 Magnetic resonance diagnostic device.

(a)
Identification. A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).(b)
Classification. Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.