(88 days)
The GSI Viewer accepts images from a CT System that can acquire CT images using different kV levels of the same anatomical region of a patient in a single rotation from a single source. The differences in the energy dependence of the attenuation coefficient of the different materials provide information about the chemical composition of body materials. This approach enables images to be generated at energies selected from the available spectrum to visualize and analyze information about anatomical and pathological structures.
GSI provides information of the chemical composition of renal calculi by calculation and graphical display of the spectrum of effective atomic number. GSI Kidney stone characterization provides additional information to aid in the characterization of uric acid versus non-uric acid stones. It is intended to be used on non-contrast studies as an adjunct to current standard methods for evaluating stone etiology and composition.
The unmodified device GSI Viewer with VUE option (K121827) offers the Gemstone Spectral Imaging (GSI) capability that uses rapid kV switching to acquire the dual energy samples almost simultaneously. This enables generation of material density data that can be used for the separation of materials and derivation of monochromatic spectral images using a projection based reconstruction algorithm.
GSI Viewer is a post processing visualization tool that allows users to view and process spectral images acquired by the GSI scan modes. It allows for the review of monochromatic energy images at user selectable energy levels, detailed analysis using material decomposed images (such as water-iodine, water calcium, etc.). and complementary information using the Effective-Z images by providing an estimate of the protons' effective atomic number in a voxel. With VUE option, it also produces a material suppressed image at a given monochromatic energy in the conventional CT Hounsfield Units.
The modification being introduced is the Fat option that produces an approximation of a Fat percentage in the liver.
This modification is based on the existing capability of the predicate device that generates material separated images in the Material Density (MD) space and VUE algorithm which is based upon Multi-Material Decomposition (MMD) a technique that allows for material separation and is the subject of this pre-market notification.
The provided text describes the 510(k) summary for the GE Medical Systems GSI Viewer with GSI Fat Option, focusing on its substantial equivalence to a predicate device. It details the device's intended use and the modifications introduced. However, it does not contain specific acceptance criteria tables, detailed study results with reported device performance figures, sample sizes for test sets, data provenance, the number or qualifications of experts used for ground truth, adjudication methods, details of MRMC studies or their effect sizes, whether a standalone algorithm-only performance study was conducted, the precise type of ground truth used, or the sample size and ground truth establishment methods for the training set.
The document outlines the testing performed as part of the substantial equivalence determination, which includes:
- Testing of accuracy based on different levels of fat using anthropomorphic and non-anthropomorphic phantoms.
- Testing for the confounding variable of iodinated contrast agent using comparisons between contrasted and non-contrasted phases.
- Testing for the confounding variable of hepatic iron using non-anthropomorphic phantoms with accuracy comparison to MR.
While these tests indicate the types of evaluations conducted, the document does not provide the quantitative results or the specific acceptance criteria defined for these tests.
Therefore, I cannot fulfill your request for:
- A table of acceptance criteria and the reported device performance: The document mentions types of testing but no specific criteria or performance data.
- Sample sizes used for the test set and the data provenance: Only mentions "anthropomorphic and non-anthropomorphic phantoms" and "clinical acquisition" for contrast agent testing, but no numbers or data origin.
- Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not present in the document.
- Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not present in the document.
- 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: Not present in the document.
- If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The "accuracy" and "comparison to MR" imply standalone performance evaluation, but it's not explicitly stated as "standalone" in contrast to human-in-the-loop.
- The type of ground truth used (expert concensus, pathology, outcomes data, etc.): For phantom studies, the ground truth would be the known fat/iron concentrations. For clinical acquisition, it's implied that comparison to MR is a form of ground truth for iron, but the specific method for contrast agent testing is not detailed. "Accuracy comparison to MR" is mentioned for iron.
- The sample size for the training set: Not present in the document. This is a 510(k) for a device that uses an algorithm based on existing capabilities and data, not explicitly a new AI model with training and test sets in the typical deep learning sense. The "modification" is an "option" built on existing material separation.
- How the ground truth for the training set was established: Not applicable/not present given the nature of the information provided for this 510(k).
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.