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.

Device Description

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.

AI/ML Overview

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).

Summary

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

April 24, 2018

Image /page/0/Picture/1 description: The image shows the logo for the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo includes the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" and "ADMINISTRATION" in blue text.

GE Medical Systems SCS % Kristine Schraufnagel Senior Regulatory Affairs Manager GE Medical Systems, LLC 3000 North Grandview Blvd. WAUKESHA WI 53188

Re: K180225

Trade/Device Name: GSI Viewer with GSI Fat Option Regulation Number: 21 CFR 892.1750 Regulation Name: Computed tomography x-ray system Regulatory Class: II Product Code: JAK Dated: January 26, 2018 Received: January 29, 2018

Dear Kristine Schraufnagel:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

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

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Michael D. D'Hara For

Robert Ochs. Ph.D Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K180225

Device Name GSI Viewer with GSI Fat Option

Indications for Use (Describe)

Type of Use (Select one or both, as applicable)
-------------------------------------------------	--

X Prescription Use (Part 21 CFR 801 Subpart D)

Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

510(k) Summary

In accordance with 21 CFR 807.92 the following summary of information is provided:

Date:	April 12, 2018
Submitter:	GE Medical Systems SCS283, rue de la Minière78530 Buc, France
Primary Contact Person:	Peter UhlirRegulatory Affairs LeaderTel: 00 36 1 4793318Fax: (262) 548 2317
Secondary Contact Person:	Kristine SchraufnagelSenior Regulatory Affairs ManagerTel: (262) 269-4273Fax: (262) 548 2317
Device Trade Name:	GSI Viewer with GSI Fat Option
Common/Usual Name:	GSI Viewer with GSI Fat Option
Regulation Number:	21CFR 892.1750
Classification Name:	Computed Tomography X-ray System
Classification Panel:	Radiology
Regulatory Class:	Class II
Product Code:	JAK
Predicate Device:	K121827 – GSI Viewer with VUE Option
Regulation Number:	21CFR 892.1750
Classification Name:	Computed Tomography X-ray System
Classification Panel:	Radiology
Regulatory Class:	Class II
Product Code:	JAK
Device Description /Intended Use:	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 spectralimages using a projection based reconstruction algorithm.
	GSI Viewer is a post processing visualization tool that allows users toview and process spectral images acquired by the GSI scan modes. Itallows for the review of monochromatic energy images at userselectable energy levels, detailed analysis using material decomposedimages (such as water-iodine, water calcium, etc.). and complementaryinformation using the Effective-Z images by providing an estimate ofthe protons' effective atomic number in a voxel. With VUE option, italso produces a material suppressed image at a given monochromaticenergy in the conventional CT Hounsfield Units.
	The modification being introduced is the Fat option that produces anapproximation of a Fat percentage in the liver.
	This modification is based on the existing capability of the predicatedevice that generates material separated images in the MaterialDensity (MD) space and VUE algorithm which is based upon Multi-Material Decomposition (MMD) a technique that allows for materialseparation and is the subject of this pre-market notification.
Indications for Use:	The GSI Viewer accepts images from a CT System that can acquire CTimages using different kV levels of the same anatomical region of apatient in a single rotation from a single source. The differences in theenergy dependence of the attenuation coefficient of the differentmaterials provide information about the chemical composition of bodymaterials. This approach enables images to be generated at energiesselected from the available spectrum to visualize and analyzeinformation about anatomical and pathological structures.
	GSI provides information of the chemical composition of renal calculiby calculation and graphical display of the spectrum of effective atomicnumber. GSI Kidney stone characterization provides additionalinformation to aid in the characterization of uric acid versus non-uricacid stones. It is intended to be used on non-contrast studies as anadjunct to current standard methods for evaluating stone etiology andcomposition.
	The Indications for Use are identical to that of the predicate device.
Technology:	The GSI Viewer with GSI Fat Option software employs the samefundamental scientific technology as its predicate device.
	The GSI Viewer with GSI Fat Option relies on the predicate device'sability to generate material separated images in the material density(MD) space. Additionally, while the predicate device provides theability to create fat as one of the material decomposed basis pairs(typically with iodine or calcium as the other basis) in units of
	voluminal mass (mg/ml or μg/ml), the GSI Viewer with GSI Fat Optionadds the ability to provide a liver fat fraction.
Determination of SubstantialEquivalence:	Summary of Non-Clinical Tests:The GSI Viewer with GSI Fat Option software complies with NEMA PS3.1 - 3.20 (2016) Digital Imaging and Communications in Medicine(DICOM) Set (Radiology) standard.The GSI Viewer with GSI Fat Option software employs the samefundamental scientific technology as its predicate device, GSI Viewerwith VUE Option.This modification is based on the existing capability of the predicatedevice that generates material separated images in the MaterialDensity (MD) space and VUE algorithm which is based upon Multi-Material Decomposition (MMD) a technique that allows for materialseparation and is the subject of this pre-market notification.
	The following quality assurance measures were applied to thedevelopment of the system:■ Risk Analysis■ Requirements Reviews■ Design Reviews■ Integration testing (System verification)■ Performance testing (Bench testing, validation)■ Safety testing (Verification)
	The substantial equivalence determination is based on the softwaredocumentation for a MODERATE level of concern device.The substantial equivalence is established with performance testing involving:
	■ testing of accuracy based on different levels of fat usinganthropomorphic and non-anthropomorphic (cylindrical withvarying diameter) phantoms,
	■ testing confounding variable of iodinated contrast agent fromclinical acquisition using comparison between contrasted andnon-contrasted phases,
testing confounding variable of hepatic iron based on different■levels of fat and iron concentration using non-anthropomorphicphantom with accuracy comparison to MR.
Conclusion:	GE Healthcare considers the GSI Viewer with GSI Fat Option softwareapplication to be as safe, as effective, and performance is substantiallyequivalent to the predicate device.

{4}------------------------------------------------

{5}------------------------------------------------

Regulation Number and Section

§ 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.