(88 days)
The SIGNA™ Artist Evo system is a whole body magnetic resonance scanner designed to support high signal-to-noise ratio, and short scan times. It is indicated for use as a diagnostic imaging device to produce axial, sagittal. coronal and oblique images, spectroscopic images, parametric maps, and/or spectra, dynamic images of the structures and/ or functions of the entire body, including, but not limited to, head, neart, abdomen, pelvis, joints, prostate, blood vessels, and musculoskeletal regions of the body. Depending on the region of interest being imaged, contrast agents may be used.
The images produced by the SIGNA™ Artist Evo system reflect the spatial distribution or molecular environment of nuclej exhibiting magnetic resonance. These images and/or spectra when interpreted by a trained physician vield information that may assist in diagnosis.
The SIGNA™ Artist Evo system is a whole body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan times. The system features a superconducting magnet. The data acquisition system accommodates up to 128 independent receive channels in various increments and multiple independent coil elements per channel during a single acquisition series. The system uses a combination of time varying magnetic fields (gradients) and RF transmissions to obtain information regarding the density and position of elements exhibiting magnetic resonance. The system can image in the sagittal, coronal, axial, oblique, and double oblique planes, using various pulse sequences and reconstruction algorithms.
The provided text is a 510(k) summary for the SIGNA™ Artist Evo magnetic resonance diagnostic device. It details how the device is considered substantially equivalent to a predicate device (SIGNA™ Artist) rather than presenting a study for meeting specific acceptance criteria itself. The document focuses on non-clinical testing for safety and performance, and the claim of "acceptable diagnostic image performance" based on sample clinical images, but does not outline a formal study with acceptance criteria for a specific AI or image perception outcome.
Therefore, I cannot fulfill all parts of your request as the provided text does not contain the acceptance criteria and the comprehensive study details you've asked for related to device performance in an AI context.
However, based on the information provided, here's what can be extracted and inferred regarding the device's substantial equivalence claim:
1. Table of Acceptance Criteria and Reported Device Performance
As this is a 510(k) for a magnetic resonance diagnostic device (not an AI algorithm with specific performance metrics like sensitivity/specificity for a particular disease), the "acceptance criteria" are related to substantial equivalence to a predicate device in terms of safety, technological characteristics, and image quality.
| Acceptance Criteria (Inferred from 510(k) Process) | Reported Device Performance (Summary) |
|---|---|
| Safety and Performance Standards Compliance | Compliant with: AAMI/ANSI ES60601-1, IEC 60601-1-2, IEC 60601-2-33, AAMI/ANSI 62304, applicable NEMA MS standards for MRI, NEMA PS3 (DICOM), ISO 10993. |
| Technological Characteristics | Same 1.5T LCC magnets, no changes to RF transmit/receive subsystems. Introduces new IRMW gradient coil. Key performance specifications (magnet stability, spatial homogeneity, max gradient strength) unchanged from predicate. Same software version as predicate with minor hardware accommodation changes. No changes to pulse sequences, imaging protocols, image processing. |
| Image Quality | Sample clinical images demonstrate acceptable diagnostic image performance, substantially equivalent to the predicate device. No new hazards, adverse effects, or safety/performance concerns significantly different from general MR imaging identified. |
| Risk Management | Subject to similar risk management activities as the predicate device (Risk Analysis, Requirements Reviews, Design Reviews, Unit/Module/Integration/Performance/Simulated Use Testing). |
| Indications for Use | Identical to the predicate device. |
Regarding specific study details for AI/perception performance:
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- The document states: "Sample clinical images have been included in this submission." It does not specify a test set sample size, data provenance, or whether it was retrospective or prospective. This implies a qualitative assessment rather than a structured quantitative study.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not specified. The assessment of "acceptable diagnostic image performance" would inherently involve expert interpretation, but the number and qualifications of these experts are not detailed.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not specified.
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 is described. The device is an MRI scanner, not an AI-assisted diagnostic tool discussed in this document.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not applicable as this is a medical imaging device, not an AI algorithm being evaluated for standalone performance. "The images produced...when interpreted by a trained physician yield information that may assist in diagnosis."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- For the "acceptable diagnostic image performance," the ground truth is implicitly expert interpretation of images for diagnostic quality, likely a qualitative assessment. There's no mention of pathology or outcomes data being used to establish ground truth for this aspect.
8. The sample size for the training set
- Not applicable. There is no mention of a "training set" as this device is not an AI/machine learning algorithm undergoing a training/validation process in the context of this 510(k) summary.
9. How the ground truth for the training set was established
- Not applicable.
In summary: The provided 510(k) relates to the substantial equivalence of an MRI scanner (SIGNA™ Artist Evo) to its predicate device (SIGNA™ Artist) based on non-clinical engineering and systems testing, and a qualitative assessment of sample clinical images for diagnostic performance. It is not a submission detailing the performance of an AI diagnostic algorithm, and therefore the specific criteria you've asked for related to AI-driven studies are not present in this document.
§ 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.