Search Results

The SIGNA Victor 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, neck, TMI, spine, breast, 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 SIGNA Victor reflect the spatial distribution or molecular environment of nuclei exhibiting magnetic resonance.

These images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

SIGNA™ Victor is a whole body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan time. The system uses a combination of time-varying magnet 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, imaging techniques and reconstruction algorithms. The system features a 1.5T superconducting magnet with 60cm bore size. The system is designed to conform to NEMA DICOM standards (Digital Imaging and Communications in Medicine).

This document does not contain the information required to populate the requested table and answer the study-related questions. The provided text is a 510(k) summary for a Magnetic Resonance Diagnostic Device (SIGNA™ Victor).

Here's why and what information is available:

What the document does include:

• Device Name: SIGNA™ Victor
• Regulatory Status: 510(k) clearance, indicating substantial equivalence to predicate devices.
• Indications for Use: Broad diagnostic imaging of the entire body.
• Technology: 1.5T superconducting magnet, RF transmit/receive architecture, software application suite. Stated to employ the same fundamental scientific technology as predicate devices.
• Comparison to Predicates: Emphasizes that indications for use, technology, operating principles, and materials are similar to predicate devices (SIGNA™ Explorer (K143251), SIGNA™ Prime (K211980), SIGNA Voyager (K161567), SIGNA Artist Evo (K213603)).
• Non-Clinical Testing: Mentions compliance with various international standards (e.g., ANSI AAMI ES60601-1, IEC 60601-1-2, IEC 60601-2-33, IEC 62304, ISO 10993-1) and internal quality assurance measures (Risk Analysis, Requirements Reviews, Design Reviews, unit/integration/performance/simulated use testing). These tests demonstrate safety and performance but are usually technical safety and functional tests, not clinical performance metrics.
• Clinical Testing (or lack thereof): Crucially, the document states: "The subject of this premarket submission, the SIGNA™ Victor, did not require clinical studies to support substantial equivalence. Sample clinical images have been included in this submission. The sample clinical images demonstrate acceptable diagnostic image performance of the SIGNA™ Victor..."

Why the requested information is largely absent:

Because the device was cleared via the 510(k) pathway and "did not require clinical studies to support substantial equivalence," the detailed clinical performance data, acceptance criteria, sample sizes for test/training sets, ground truth establishment, expert qualifications, and MRMC study details that you're asking for are typically not part of such a submission.

The FDA's 510(k) pathway primarily focuses on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving de novo safety and effectiveness through extensive clinical trials. The statement "The image quality of the SIGNA™ Victor is substantially equivalent to that of the predicate devices" is the core "acceptance criteria" and "proof" in this context, inferred from the non-clinical tests and sample images.

Therefore, I cannot generate the table or provide specific answers to most of the study-related questions based on the provided text. The document explicitly states no clinical studies were required, which means there was no formal "study" in the sense of a clinical trial to generate the kind of data you're requesting regarding accuracy, sensitivity, specificity, or specific performance metrics with defined acceptance criteria and comparator data.

Based on the available information, here's what could be inferred, though it doesn't directly meet all your criteria:

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

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

• The document states "did not require clinical studies" and only "sample clinical images have been included." It does not specify a sample size for a formal test set or its provenance (country of origin, retrospective/prospective). This implies a very limited, possibly anecdotal, set of images used for visual comparison rather than a statistically powered study.

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

• Not specified. Given the lack of a formal clinical study, the process for establishing ground truth (if any beyond visual review) for the "sample clinical images" is not detailed. The document mentions images are "interpreted by a trained physician," which is a general statement for MRI use, not specific to this submission.

4. Adjudication method for the test set

• Not specified, as a formal test set and adjudication process are not described.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

• No, an MRMC study was not done. The document explicitly states "did not require clinical studies." Therefore, there is no effect size of human readers improving with AI vs. without AI assistance to report, as this is neither an AI device nor was such a study conducted.

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

• This device is an MRI machine, not an AI algorithm. Therefore, "standalone" algorithm performance is not applicable in the way it usually refers to AI/CADe devices. The MRI system itself has a "standalone" performance, which is assessed through technical and functional tests and comparison to its predicate devices.

7. The type of ground truth used

• For the "sample clinical images" (if any "ground truth" was formally established for them, which is unlikely given the context), it would implicitly be expert visual interpretation as determined by a trained physician for diagnostic purposes. It's not pathology or outcomes data from a formal study.

8. The sample size for the training set

• The device is an MRI scanner, not an AI algorithm trained on image data in the typical sense. Therefore, there is no "training set" of patient images as would be for a machine learning model. The system's "training" refers to its design, engineering, and testing against specifications and standards.

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

• Not applicable as there is no "training set" of patient images for an AI algorithm.

Ask a specific question about this device