· is a software option intended for use on Achieva and Ingenia 1.5T & 3.0T MR Systems
· is a non-invasive triglyceride fat fraction calculation
· is a 3D, single breath-hold acquisition and reconstruction technique
· allows for water-fat separation generating Water-only, Fat-only images as well as Out-phase and In-phase images
· is indicated for magnetic resonance imaging of the liver

Device Description

mDIXON-Quant acquisition and reconstruction is based on the mDIXON product developed previously. Acquisition relies on a gradient echo acquisition (FFE) including a large number of echoes (6 or more). Furthermore, mDIXON-Quant reconstruction includes the use of multiple spectral peaks of triglyceride fat, correction of the T2* confounding effect and reduction of T1 bias.

mDIXON-Quant allows for water-fat separation and generates Water-only, Fat-only images as well as Out-phase and In-phase images synthesized from the Water and Fat images. Additionally, mDIXON-Ouant produces images representing triglyceride fat fraction as well as images representing transverse magnetization relaxation.

The feature requires:

· Specific parameter settings for the mDIXON sequence, within cleared parameter limits, to acquire the MR signals
· A new calculation function to generate the new images for Fat Fraction, T2 *. This function uses a set of MR images as input that is generated in a cleared manner from the acquired MR signals.
· The new images need to be stored and displayed with the appropriate labels for Fat Fraction, T2 *, applying the facilities provided by the cleared platform.

AI/ML Overview

Here's a summary of the acceptance criteria and study information based on the provided text for the mDIXON-Quant device:

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria	Reported Device Performance
FF accuracy ±3.5%	FF accuracy is ±3.5% for both field strengths and all possible parameter combinations
T2* range and reproducibility 1.5%	T2* range and reproducibility is 1.5% for both field strengths
No error messages during Acquisition and Reconstruction testing	No error messages displayed
Scan time < 20 seconds	Scan time < 20 seconds (13.6s for 3T, 14.6s for 1.5T)
FF and T2* images available	FF and T2* images available
All images opened in gray scale	All images opened in gray scale
Look-Up Table showed images in expected colors	Look-Up Table showed images in the expected colors
ROI could be drawn	ROI could be drawn
Two values of area and mean displayed (for ROI)	Two values of area and mean were displayed
No error messages during SW startup, phantom positioning, examcard loading, survey scan activation	No error messages displayed
Images generated in < 5 minutes	Images generated in < 5 minutes
Clinical validation completed successfully	All clinical user needs passed for Achieva and Ingenia 1.5T and 3T systems
Volunteers able to hold breath for scan duration	All volunteers were able to hold their breath for the scan time (13.6s for 3T, 14.6s for 1.5T)
System didn't crash or hang-up	System didn't crash or hang-up
Workflow was smooth	Workflow was smooth
No problems occurred	No problems occurred

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

The document does not explicitly state a specific "test set" sample size in terms of number of cases or patients for a clinical validation study. The clinical validation involved "volunteers."

Sample Size (clinical validation): Not explicitly stated, but involved "all volunteers."
Data Provenance: The document does not specify the country of origin of the data. The clinical validation was prospective ("The clinical user needs were tested as part of the validation testing... All volunteers were able to hold their breath for that time. As such, the clinical validation of mDIXON-Quant completed successfully.").

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

The document does not mention the use of experts to establish ground truth for a test set, nor does it detail any qualifications for such experts. The primary assessments for the clinical validation appear to be directly related to the device's functional output (image generation, ROI functionality, etc.) and user experience (breath-hold, workflow smoothness).

4. Adjudication Method for the Test Set

Not applicable. The document does not describe any expert adjudication process for establishing ground truth or evaluating disagreements, as it primarily focuses on device functionality and user experience during clinical validation.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance

No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not reported. The study focused on the performance of the mDIXON-Quant device itself, not on how human readers' diagnostic accuracy is affected by using the device. The device is a "non-invasive triglyceride fat fraction calculation" and "generates Water-only, Fat-only images as well as Out-phase and In-phase images," implying it provides quantitative data and separated images, not an AI-assisted diagnostic classification.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, a standalone performance assessment was conducted for the algorithm's core functionality, particularly for quantification accuracy and reproducibility:

Quantification Performance testing: "test results showed that the FF accuracy is ±3.5% for both field strengths and all possible parameter combinations, and the T2* range and reproducibility is 1.5% for both field strengths."
Acquisition and Reconstruction testing: Verified "FF and T2* images were available."

These tests demonstrate the algorithm's ability to produce accurate and reproducible quantitative results and generate the intended image types independently of human interpretation of those results.

7. The Type of Ground Truth Used

The ground truth for the quantitative performance (Fat Fraction accuracy, T2* range and reproducibility) was established against an assumed reference standard for these measurements, likely using phantoms or controlled experimental conditions where the true values were known. The document states "Quantification Performance testing" but does not explicitly name the reference method for establishing this ground truth. For the qualitative aspects of clinical validation (e.g., image availability, ROI capability, workflow), the ground truth was essentially whether the device successfully performed the intended functions as observed by the testers.

8. The Sample Size for the Training Set

The document does not provide any information regarding a training set or its sample size. This is a medical imaging reconstruction and quantification software, not a machine learning model that typically requires a distinct training set in the conventional sense. The "training" of such a system would involve engineering and calibration against known physical properties and signal characteristics rather than labeled clinical data.

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

Not applicable, as no training set (in the context of machine learning) is described. The development of such an algorithm would rely on established physics and signal processing principles, validated against phantom studies and potentially pre-existing clinical data for fine-tuning.

Summary

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

Image /page/0/Picture/0 description: The image shows the word "PHILIPS" in large, bold, black letters. Above the word, there is handwritten text that appears to be a document or page identifier, possibly "K133526 page 1 of 5". The handwriting is in black ink and contrasts with the clean, printed font of the brand name.

Philips Medical Systems Nederland B.V.

510(k) Summary

FEB 1222014

mDIXON-Quant

This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of 21 CFR 807.92.

General Information 【.

21 CFR 807.92 (a)(1), (2)

Company Name:	Philips Medical Systems Nederland B.V.
Address:	Veenpluis 4-65684 PC BestThe Netherlands
Registration No .:	3003768277
Contact Person:	Susan QuickTel: (440)-483-2291Fax: (440)-483-4799E-mail: susan.quick@philips.com
Prepared (date):	2013 November 14, Revised 2014 January 24,2014 February 06
Trade Name of Device:	mDIXON-Quant
Classification:	Class II
Regulatory Section:	Magnetic Resonance Diagnostic Device.892.1000
Product Code:	90LNH

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

` 21 CFR 807.92(a)(3):Legally marketed predicate device to which substantial equivalence is claimed:

Predicate Device:	IDEAL Software Option
Manufacturer:	GE Healthcare
Predicate Device k#:	K103411
Reference Device:	mDIXON
Manufacturer:	Philips Medical Systems Nederland B.V.
Reference Device k#:	K102344

21 CFR 807.92(a)(4): Description of the device that is the subject of this premarket notification:

Summary of functions of the device and its major components

The feature requires:

· Specific parameter settings for the mDIXON sequence, within cleared parameter limits, to acquire the MR signals
· A new calculation function to generate the new images for Fat Fraction, T2 *. This function uses a set of MR images as input that is generated in a cleared manner from the acquired MR signals.
· The new images need to be stored and displayed with the appropriate labels for Fat Fraction, T2 *, applying the facilities provided by the cleared platform.

21 CFR 807.92(a)(5): Intended Use

mDIXON-Quant:

· is a software option intended for use on Achieva and Ingenia 1.5T & 3.0T MR Systems
· is a non-invasive triglyceride fat fraction calculation
· is a 3D, single breath-hold acquisition and reconstruction technique
· allows for water-fat separation generating Water-only, Fat-only images as well as Outphase and In-phase images
· is indicated for magnetic resonance imaging of the liver

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

21 CFR 807.92(a)(6): Technological Characteristics:

The main functional units in the software are:

(acquisition of MR signals by means of MR pulse sequences) - Methods
Reconstruction (transforming the MR signals to images)
Patient Administration (storing of the images in the database and providing access)
Viewing (display of images and measuring ROI)

The technical impact of the feature mDJXON-Quant comprises:

Methods: modify an existing sequence to acquire the data required for mDIXON-Quant, within the cleared limits provided by the basic MR system.
Reconstruction: add a new calculation function that generates the new output images (Fat Fraction, T2*-maps and R2* (=1/T2*).
Patient Administration and Viewing: enable storage and display of the new output images with appropriate labels (SW-M and SW-P).

No off-the-shelf software is used for the feature mDIXON-Quant. The off-the-shelf software used in the basic MR system for the Ingenia and Achieva 1.5T and 3.0T MR systems is cleared by K110151.

The basic MR system provides the features for interoperability and internet connections. which are already cleared. The feature mDIXON-Quant does not have any additions or modifications related to interoperability and connections to an external network.

Hardware platform description

mDIXON-Ouant does not require any change of the hardware platform. The main extension introduced by mDIXON-Quant, the new reconstruction algorithm, runs on the Reconstructor computer.

Computer characteristics:

· Manufacturer: HP; Model: Z400 or Z420; Processor speed: ≥3.6 GHz; Memory: 16-32 GB RAM, 1-2 x quad core processors
· Operating system: Windows 7, 64 bits

The mDIXON-Ouant algorithm does not add specific requirements to the Ingenia and Achieva 1.5T and 3.0T MR systems as cleared by K110151.

Workflow

For the operator the only new element for the mDIXON-Quant-feature in this clinical routine workflow is:

Protocol selection: The operator selects an ExamCard with mD1XON-Quant protocols

All other steps are not changed. Only in the planscan phase the user may want to change the predefined selection of output image-types. The newly generated image types can be viewed, post-processed, printed and archived as any other image type. The display of the images on the console can be switched between grey-scale and color scale. During post processing the operator can do further analysis (such as calculation of average values in a ROI) using the image processing facilities as provided by the standard platform.

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

21 CFR 807.92(b)(1): Brief discussion of nonclinical tests submitted, referenced or relied on in this premarket notification:

All non-clinical testing was performed on a 1.5T Ingenia and a 3.0T Achieva TX.

All Integration testing completed with passing results, with regression testing completing without error messages and greater than 90% of all scans present in the batch running successfully.

All System Verification testing completed with passing results. For the System Verification testing, a dS-Torso. Posterior coil and Anterior coil were used on the Ingenia 1.5T and a Sense-XL-Torso coil was used on the Achieva 3.0T. All Acquisition and Reconstruction, Viewing, Calculation, and Performance testing passed. In the Acquisition and Reconstruction testing, there were no error messages, scan time was < 20 seconds and FF and T2* images were available. In the Viewing testing, all images opened in gray scale and the Look-Up Table showed the images in the expected colors. In the Calculation testing, the ROI could be drawn and two values of area and mean were displayed. For the Performance testing, no error messages were displayed during SW startup, phantom positioning, examcard loading, survey scan activation, and images were generated in < 5 minutes.

For the Quantification Performance testing, test results showed that the FF accuracy is ±3.5% for both field strengths and all possible parameter combinations, and the T2* range and reproducibility is 1.5% for both field strengths.

Overall, all tests performed for mDIXON-Quant were successful. While using mDIXON-Quant the system didn't crash or hang-up. Workflow was smooth and no problems occurred.

All defects have been analyzed and are confirmed that they are not safety defects and will not cause any hazardous situation on using this application.

21 CFR 807.92(b)(2): Brief discussion of clinical tests submitted, referenced or relied on in this premarket notification:

The clinical user needs were tested as part of the validation testing.

The same systems and coils used in the Verification testing were used for the Validation testing. mDIXON-Quant produced Fat Fraction and T2* images, and operator could create a ROI in the acquired images. All protocol steps as stated in the test plan, completed successfully. The mDIXON-Quant protocols were scanned in 13.6sec for 3T and in 14.6sec for 1.5T. All volunteers were able to hold their breath for that time. As such, the clinical validation of mDIXON-Quant completed successfully. All clinical user needs have passed for Achieva and Ingenia 1.5T and 3T systems.

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

K133526
Page 5 of 5

21 CFR 807.92(b)(3): The conclusions drawn from the nonclinical and clinical tests that demonstrate that the device is as safe, as effective, and performs as well as or better than the legally marketed device identified in paragraph (a)(3) of this section:

The nonclinical and clinical tests have demonstrated that the device is safe and works according to its intended use.

The mDIXON-Quant software does not introduce new indications for use, nor does the use of the device result in any new potential hazard. Philips Medical Systems considers mDIXON-Quant to be substantially equivalent to the above mentioned predicate device.

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

Image /page/5/Picture/1 description: The image shows the seal of the Department of Health & Human Services (HHS) of the United States. The seal features the department's name encircling a symbol. The symbol is a stylized representation of an eagle with outstretched wings, with three wavy lines emanating from its body.

Public Health Service

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

February 12, 2014

Philips Medical Systems Nederland B.V. % Ms. Susan Quick Regulatory Affairs Specialist Philips Medical Systems (Cleveland), Inc. 595 Miner Road CLEVELAND OH 44143

Re: K133526

Trade/Device Name: mDIXON-Quant Regulation Number: 21 CFR 892.1000 Regulation Name: Magnetic resonance diagnostic device Regulatory Class: II Product Code: LNH Dated: November 14, 2013 Received: November 15, 2013

Dear Ms. Quick:

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 (reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

{6}------------------------------------------------

Page 2-Ms. Quick

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Division of Small Manufacturers, International and Consumer Assistance at its tollfree number (800) 638 2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR 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 Division 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/MedicalDevices/ResourcesforYou/Industry/default.hum.

Sincerely yours,

Michael D. O'Hara.

for

Janine M. Morris Director, Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health

Enclosure

{7}------------------------------------------------

DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration

Form Approved: OMB No. 0910-0120 Expiration Date: January 31, 2017 See PRA Statement on last page.

Indications for Use

510(k) Number (if known) K 133526

Device Name mDIXON-Quant

DIXON-Quan

Indications for Use (Describe)

mDIXON-Quant:

· is a software option intended for use on Achieva and Ingenia 1.5T & 3.0T MR Systems
· is a non-invasive triglyceride fat fraction calculation
· is a 3D, single breath-hold acquisition and reconstruction technique
· allows for water-far separation generating Water-only, Fat-only images as well as Out-phase images
· is indicated for magnetic resonance imaging of the liver

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)

PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON A SEPARATE PAGE IF NEEDED.

FOR FDA USE ONLY

Concurrence of Center for Devices and Radiological Health (CDRH) (Signature)

Michael D. O'Hara

{8}------------------------------------------------

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."

Regulation Number and Section

§ 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.