Search Results

The uMR 790 system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces sagittal, transverse, coronal, and oblique cross sectional images, and that display internal anatomical structure and/or function of the head, body and extremities.

These images and the physical parameters derived from the interpreted by a trained physician yield information that may assist the diagnosis. Contrast agents may be used depending on the region of interest of the scan.

The uMR 790 is a 3.0T superconducting magnetic resonance diagnostic device with a 60cm size patient bore. It consists of components such as magnet, RF power amplifier, RF coils, gradient power amplifier, gradient coils, patient table, spectrometer, computer, equipment cabinets, power distribution system, internal communication system, and vital signal module etc. The uMR 790 Magnetic Resonance Diagnostic Device is designed to conform to NEMA and DICOM standards.

This document describes the uMR 790 MRI system, and the studies mentioned are for the general safety and performance of the device itself (like signal-to-noise ratio, geometric distortion, image uniformity, etc.), not for a specific AI algorithm within the device for a particular diagnostic task. Therefore, the standard AI acceptance criteria and study components you've requested are not directly applicable in this context.

However, I can extract information regarding the general performance testing and safety studies conducted for the uMR 790, which are somewhat analogous to "acceptance criteria" for an MRI system.

Here's the information based on the provided text, adapted to the closest relevant categories:

1. A table of acceptance criteria and the reported device performance

For the uMR 790, the "acceptance criteria" are implied by adherence to various NEMA and ISO standards for MRI performance. The document states that the device "conforms to NEMA and DICOM standards" and lists specific NEMA MS standards against which tests were conducted. The "reported device performance" is summarized by the statement: "The test results demonstrated that the device performs as expected and thus, it is substantially equivalent to the predicate devices to which it has been compared."

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size for Test Set: The document mentions "Sample clinical images" and "A volunteer study" without specifying the exact number of images or volunteers.
• Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). The volunteer study would be prospective in nature.

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

• The document states that images produce information "when interpreted by a trained physician." However, it does not specify the number or qualifications of experts used to establish ground truth for the "sample clinical images" or the volunteer study evaluation.

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

• No specific adjudication method is mentioned for the evaluation of the sample clinical images or the volunteer study.

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. This device is a general MRI system, not an AI-powered diagnostic algorithm.

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

• Not applicable as this is an MRI system, not a standalone algorithm.

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

• For the "sample clinical images," the ground truth is implicitly based on the ability of "trained physicians" to interpret the images for diagnosis.
• For the volunteer study, the ground truth relates to physiological responses to gradient stimulation.

8. The sample size for the training set

• Not applicable. This is not an AI algorithm requiring a training set in the conventional sense. The "training" for the device's design and operation would come from engineering principles and existing MRI technology.

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

• Not applicable for a device like an MRI scanner.

Ask a specific question about this device