MotionVUE2 (Q.freeze) is a PET/CT, non- invasive image analysis software application designed to support the viewing and manipulation of medical images from PET and CT imaging modalities.

MotionVUE2 (Q.freeze) offers processing tools to optimize workflow of respiratory gated exams for PET, CT and fused images of respiratory gated datasets for simultaneous viewing in multiplanar volumes and cine loops.

MotionVUE2 (Q.freeze) allows the users to generate from their 4D-PET or 4D-PET/CT series a registered 4D-PET series used for quantification of lesions and analysis of functional activity. With MotionVUE2 (Q.freeze), users will have the possibility to compare static PET/CT, 4D-PET/CT, and registered 4DPET series including visual comparison, quantification of lesions, and analysis of functional activity.

MotionVUE2 (Q.freeze) provides registration performance of up to 2 mm of center of mass motion when motion is no larger than the diameter of the object.

MotionVUE2 (Q.freeze) provides comparable/equivalent improvement of quantification results (SUV and size) as 4D PET techniques.

MotionVUE2 (Q.freeze) can be used for features with locally concentrated activity within the entire Thorax area. This area includes the organs where PET/CT imaging has the most challenges due to respiratory motion: Lung, Liver, Pancreas.

Device Description

Motion VUE2 (Q.freeze) is a modification to the existing Motion VUE application. Motion VUE is a software application that provides review tools necessary for viewing, staging, planning and monitoring disease in respiratory gated PET and CT data sets. It is intended for use on Advantage Workstation platforms.

Motion VUE2 (Q.freeze) is product delivers the Non-Rigid Registration (NRR) function (Motion Freeze function) to the existing Motion VUE application on AW. The Motion VUE 2 program delivers:

Non-Rigid Registration of PET Gated Images
Visualization of Registered PET Gated Images
Visualization of Registered Average PET Gated Images
Presentation Layouts to display the Registered and Registered Average PET Images

(Non-rigid registration includes spatial normalization, which may be used to transform a patient data set to match a standardized anatomical space).

AI/ML Overview

Here's an analysis of the GE Q.Freeze software based on the provided 510(k) summary, structured to address your questions.

Device Name: GE Q.Freeze Software
510(k) Number: K113408
Date of Summary: November 18, 2011

1. Table of Acceptance Criteria and Reported Device Performance

The provided document details the stated performance goals of the Q.Freeze software without explicitly outlining a formal "acceptance criteria" table in the typical sense (e.g., pass/fail thresholds against specific metrics based on a pre-defined study protocol). However, it does state specific performance claims which can be interpreted as the criteria the device is expected to meet.

Acceptance Criterion (Stated Performance Claim)	Reported Device Performance
Registration performance of up to 2 mm of center of mass motion when motion is no larger than the diameter of the object.	The device provides registration performance of up to 2 mm of center of mass motion when motion is no larger than the diameter of the object. (The document states this as a feature/capability rather than a result from a specific study demonstrating it.)
Comparable/equivalent improvement of quantification results (SUV and size) as 4D PET techniques.	The device provides comparable/equivalent improvement of quantification results (SUV and size) as 4D PET techniques. (Similar to above, this is stated as a capability without detailed evidence in this summary.)
Performance of the device is substantially equivalent to legally marketed predicate devices (MotionVUE K081496).	The document asserts that "O.Freeze performs as well as currently marketed devices introduces no significant change in safety or effectiveness as compared to the predicate devices, and is therefore substantially equivalent in terms of safety and effectiveness to the currently marketed MotionVue."

Note on "Study that Proves": The 510(k) summary provided largely states the device meets these criteria implicitly through its design and comparison to predicate devices, rather than detailing a specific, comprehensive study that "proves" these claims with quantitative results from a test set. This is common in 510(k) summaries where substantial equivalence is demonstrated through design comparison and known performance characteristics of similar technologies.

2. Sample Size Used for the Test Set and Data Provenance

The provided 510(k) summary does not specify a separate test set, its sample size, or the provenance of the data (e.g., country of origin, retrospective/prospective) for validating the Q.Freeze software's performance against the stated criteria. The submission relies heavily on the device's substantial equivalence to a predicate device (MotionVUE K081496) and the inherent capabilities of "Non-Rigid Registration" technology.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

The 510(k) summary does not mention using experts from an external test set to establish ground truth.

4. Adjudication Method for the Test Set

Since no specific test set and expert review process is described, there is no mention of an adjudication method.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

An MRMC comparative effectiveness study was not mentioned or detailed in the provided 510(k) summary. The submission focuses on the software's ability to process and register images for quantification and analysis, rather than its impact on human reader performance in a clinical setting compared to unaided reading.

6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance

The device itself, being a software application for image processing and registration, can be considered for its standalone algorithmic performance. The document states:

"MotionVUE2 (Q.freeze) provides registration performance of up to 2 mm of center of mass motion when motion is no larger than the diameter of the object."
"MotionVUE2 (Q.freeze) provides comparable/equivalent improvement of quantification results (SUV and size) as 4D PET techniques."

These statements represent the standalone performance claims of the algorithm itself, without human intervention in the registration process. However, the details of the study or verification that directly yielded these exact performance figures are not provided in this summary. It's implied that these are expected or demonstrated through internal testing or knowledge of the underlying technology.

7. Type of Ground Truth Used

Given the nature of the device (non-rigid registration of medical images), the "ground truth" would ideally involve:

Highly accurate, independent measurements of motion (e.g., fiducial markers tracked by external systems) in respiratory-gated data to verify registration accuracy.
Pathology or clinical outcomes data to validate the impact of improved quantification (SUV and size) on clinical diagnosis or prognosis.

However, the provided 510(k) summary does not explicitly state the type of ground truth used for validating the 2mm registration claim or the claim about comparable/equivalent quantification improvement. It relies on the assertion that the technology itself (Non-Rigid Registration) is well-understood and performs as described, and that its output is equivalent to existing 4D PET techniques.

8. Sample Size for the Training Set

The 510(k) summary does not provide information on the sample size used for training the Q.Freeze software, as it is a specific software application with an algorithm rather than a machine learning model that typically undergoes explicit "training" on a dataset for classification or prediction tasks. The "training" in this context would implicitly refer to the development and refinement of the NRR algorithm itself.

9. How the Ground Truth for the Training Set Was Established

As noted above, the concept of a "training set" with established ground truth as understood in machine learning is not directly applicable or described in this 510(k) summary. The Q.Freeze software is described as implementing a "Non-Rigid Registration (NRR) function," which is an established image processing technique. The ground truth for developing and validating such an algorithm would typically involve theoretical models, phantom studies, and possibly human expert review of registration accuracy on various clinical cases during the development phase. However, this information is not detailed in the provided document.

Summary

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

K113408

FEB 2 4 2012 GE Healthcare

510(k) Summary of Safety and Effectiveness iin accordance to 21 CFR

807.87{h))

Device Name Proprietary Device Name: Date prepared:

Q.freeze Software November 18, 2011

Establishment Name and Registration Number of Submitter

Name: Registration Number: Corresponding Official: GE Medical Systems LLC 2126677 D. Duersteler GE Healthcare P.O. Box 414 Milwoukee, WI 53201 Phone: 262-312-7029 FAX: · · 262-312-7144 Email: david.duersteler@med.ge.com

Device Classification Classification Code: Panel Identification: Classification Name:

Common Name: Classification Class: Reason for 510(k) Submission:

ಡಿರಿ KPS Radiology Emission Computed Tomography System (Per 21CFR 892.1200) PET/CT Imaging Software Class II Product New device

Device Description

Motion VUE2 (Q.freeze) is product delivers the Non-Rigid Registration (NRR) function (Motion Freeze function) to the existing Motion VUE application on AW. The Motion VUE 2 program delivers:

് 1: 1: Non-Rigid Registration of PET Gated Images
- Visualization of Registered PET Gated Images 2.
- .3. Visualization of Registered Average PET Gated Images
- Presentation Layouts to display the Registered and Registered Average PET 4. lmaqes ్నా

(Non-rigid registration includes spatial normalization, which may be used to transform a patient data set to match a standardized anatomical space).

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

GE Healthcare

510(k) Summary of Safety and Effectiveness November 18. 2011 Page 2

ldentification of Legally Marketed Equivalent Devices

Discovery PET/CT 600 and 690

GE Medical Systems LLC

K081496

Comparison with Predicate Devices

MotionVUE2 (Q.freeze) PET Software is similar in design, materials, energy sources, and technology to the above predicate devices. All major features have been previously marketed, and intended uses are substantively the same. O.Freeze performs as well as currently marketed devices introduces no sianificant change in safety or effectiveness as compared to the predicate devices, and is therefore substantially equivalent in terms of safety and effectiveness to the currently marketed MotionVue on GE Healthcare's Discoverv Series of products.

Indications for Use of Device

MotionVUE2 (Q.freeze) is a PET/CT, non-invasive image analysis software application designed to support the viewing and manipulation of medical images from PET and CT imaging modalities.

MotionVUE2 (Q.freeze) allows the users to generate from their 4D-PET or 4D-PET/CT series a reaistered 4D-PET series used for quantification of lesions and analysis of functional activity. With MotionVUE2 (Q.freeze), users will have the possibility to compare static PET/CT, 4D-PET/CT, and reaistered 4DPET series including visual comparison, quantification of lesions, and analysis of functional activity.

MotionVUE2 (Q.freeze) provides registration performance of up to 2 mm of center of mass motion when motion is no larger than the diameter of the object.

MotionVUE2 (Q.freeze) provides comparable/equivalent improvement of quantification results (SUV and size) as 4D PET techniques.

MotionVUE2 (Q.freeze) can be used for features with locally concentrated activity within the entire Thorax area: This area includes the organs where PET/CT imaging has the most challenges due to respiratory motion: Lunq, Liver, Pancreas.

Conclusion

. . . . .

In the opinion of General Electric Medical Systems, the O.freeze Software is substantially the same in design, materials, energy sources, and technology, does not introduce new safety concerns, performs as well as currently marketed devices, and is therefore substantially equivalent in terms of safety and effectiveness to the currently marketed MotionVUE (K081496).

ﻴﺮ,

General Electric Company P.O. Box 414 Milwaukee, W1 53201

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

Image /page/2/Picture/0 description: The image shows the seal of the Department of Health & Human Services - USA. The seal is circular and contains the department's name around the perimeter. In the center of the seal is an abstract image of an eagle.

DEPARTMENT OF HEALTH & HUMAN SERVICES

Public Health Service

Food and Drug Administration 10903 New Hampshire Avenue Document Control Room - WO66-G609 Silver Spring, MD 20993-0002

FEB 2 4 2012

Mr. David Duersteler Safety and Regulatory Engineering GE medical Systems LLC 3000 N. Grandview Blvd. WAUKESHA WI 53188

Re: K113408

Trade/Device Name: GE Q.Freeze software Regulation Number: 21 CFR 892.1200 Regulation Name: Emission computed tomography system Regulatory Class: II Product Code: KPS Dated: November 18, 2011 Received: November 28, 2011

Dear Mr. Duersteler:

We have reviewed your Section 510(k) premarket notification of intent to market the device we nave reviewed your becamed the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate 10 use stated in the encrosure) to regarry thanks of the Medical Device Amendments, or to commerce prov to this 20, 1978, 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 I ou may, merelore, manel of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration.

If your device is classified (see above) into class II (Special Controls), it may be subject to such II your device is classified (see above) into ena affecting your device can be found in Title 21, adultional controls. Disting mayor regates 800 to 895. In addition, FDA may publish further Ode of Pourial concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean Frease be advised that I Dri 3 issuance or our device complies with other requirements of the Act that IDA has made a determinations administered by other Federal agencies. You must of any I cachar statutes and regulations and limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Parts 801 and 809); medical device reporting (reporting of

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

Page 2

medical device-related adverse events) (21 CFR 803); and good manufacturing pactice medical device-lefated develse events) (21 cegulation (21 CFR Part 820). This letter requirences as set form in the quality of enime ( ( described in your Section 510(k) premarket will anow you to begal mainen.org your antial equivalence of your device to a legally marketed nontication. The I Dr I minding of cassification for your device and thus, permits your device to proceed to the market.

If you desire specific advice for your device on our labeling regulation (21 CFR Parts 801 and If you desire specific advice of In Vitro Diagnostic Device Evaluation and Safety at (301) 796-5450. 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.

You may obtain other general information on your responsibilities under the Act from the Tou may obtain of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address http://www.fda.gov/cdrh/industry/support/index.html.

Sincerely Yours,

Janine M. Morris

Acting Director Division of Radiological Devices Office of In Vitro Diagnostic Device Evaluation and Safety Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known): K113408

Device Name: GE Q.Freeze software

Indications for Use:

MotionVUE2 (Q.freeze) is a PET/CT, non- invasive image analysis software application designed to support the viewing and manipulation of medical images from PET and CT imaging modalities.

MotionVUE2 (Q.freeze) provides registration performance of up to 2 mm of center of mass motion when motion is no larger than the diameter of the object.

MotionVUE2 (Q.freeze) provides comparable/equivalent improvement of quantification results (SUV and size) as 4D PET techniques.

ﻢ Prescription Use (21 CFR 801 Subpart D)

AND/OR

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

(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED)

Concurrence of CDRH, Office of In Vitro Diagnostic Devices (OIVD)

Mary Slott Post Janine Monia
(Division Sign-Off
Division of Radiological Devioce
Office of In Vitro Diagnostic Devics Evaluation and Safety

Regulation Number and Section

§ 892.1200 Emission computed tomography system.

(a)
Identification. An emission computed tomography system is a device intended to detect the location and distribution of gamma ray- and positron-emitting radionuclides in the body and produce cross-sectional images through computer reconstruction of the data. This generic type of device may include signal analysis and display equipment, patient and equipment supports, radionuclide anatomical markers, component parts, and accessories.(b)
Classification. Class II.