LiverMultiScan (LMSv3) is indicated for use as a magnetic device software application for noninvasive liver evaluation that enables the generation, display and review of 2D magnetic resonance medical image data and pixel maps for MR relaxation times.

LiverMultiScan (LMSv3) is designed to utilize DICOM 3.0 compliant magnetic resonance image datasets, acquired from compatible MR Systems, to display the internal structure of the abdomen including the liver. Other physical parameters derived from the images may also be produced.

LiverMultiScan (LMSv3) provides a number of tools, such as automated liver segmentation and region of interest (ROI) placements, to be used for the assessment of selected regions of an image. Quantitative assessment of selected regions include the determination of triglyceride fat fraction in the liver (PDFF), T2* and iron-corrected T1 (cT1) measurements. PDFF may optionally be computed using the LMS IDEAL or three-point Dixon methodology.

These images and the physical parameters derived from the images, when interpreted by a trained clinician, yield information that may assist in diagnosis.

Device Description

LiverMultiScan (LMSv3) is a standalone software application for displaying 2D Magnetic Resonance (MR) medical image data acquired from compatible MR Scanners. LiverMultiScan runs on general-purpose workstations with a colour monitor, keyboard and mouse.

The main functionality of LiverMultiScan (LMSv3) includes:

Reading DICOM 3.0 compliant datasets stored on workstations, and display of the data acquisition information
Post-processing of MRI data to generate parametric maps of Proton Density Fat Fraction PDFF), T2*, T1 and ironcorrected T1 (cT1) of the liver.
Quantification, and calculation of PDFF, T2* and cT1 metrics using tools such as automatic liver segmentation and ROI (region of interest) placement.
Generation of a summary report demonstrating the quantitative assessment results of fat fraction in the liver (PDFF), T2* and iron-corrected T1 (cT1).

AI/ML Overview

Here's a summary of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a "table of acceptance criteria" with corresponding reported performance for specific metrics like sensitivity, specificity, accuracy, etc., as one might expect for a diagnostic device. Instead, the performance testing focuses on the accuracy, repeatability, reproducibility, and inter-/intra-operator variability of quantitative measurements, and particularly on demonstrating substantial equivalence to a predicate device (LMSv2).

The acceptance criteria are implicitly defined by the reported performance ranges and the conclusion that the device performs "as well as its predicate" and that "all the testing results are well within the acceptance criteria."

Metric / Test Type	Acceptance Criteria (Implicit from Study Conclusion)	Reported Device Performance (Summary)
Phantom Testing
T1 Accuracy	T1 measurements consistent with literature-reported underestimation for MOLLI techniques.	Up to 18.89% lower to ground truth (95% CI Limits of Agreement)
T2* Accuracy	Accurate over expected physiological range.	-9.31% to 7.53% of ground truth (95% CI Limits of Agreement)
DIXON PDFF Accuracy (<30%)	Relatively accurate over expected physiological range; minor deviations due to known fat bias.	-7.37% to 1.72% (95% CI Limits of Agreement)
DIXON PDFF Accuracy (>30%)	Relatively accurate over expected physiological range; minor deviations due to known fat bias.	-28.93% to 6.83% (95% CI Limits of Agreement)
IDEAL PDFF Accuracy (<30%)	Accurate over expected physiological range.	-1.17% to 1.43% (95% CI Limits of Agreement)
IDEAL PDFF Accuracy (>30%)	Accurate over expected physiological range.	-5.05% to 10.70% (95% CI Limits of Agreement)
T1 Repeatability (same scanner)	Highly repeatable.	-13.88 to 14.47 ms (95% CI Limits of Agreement)
T2* Repeatability (same scanner)	Highly repeatable.	-0.89 to 1.43 ms (95% CI Limits of Agreement)
DIXON PDFF Repeatability (<30%)	Highly repeatable.	-0.66 to 0.82 % (95% CI Limits of Agreement)
DIXON PDFF Repeatability (>30%)	Highly repeatable.	-2.11 to 1.96% (95% CI Limits of Agreement)
IDEAL PDFF Repeatability (<30%)	Highly repeatable.	-1.27 to 0.87% (95% CI Limits of Agreement)
IDEAL PDFF Repeatability (>30%)	Highly repeatable.	-3.80 to 1.93 % (95% CI Limits of Agreement)
T1 Reproducibility (different scanners)	Reproducible between different scanners.	-2.66 to 10.78% (95% CI Limits of Agreement)
T2* Reproducibility (different scanners)	Reproducible between different scanners.	-3.43 to 2.42 ms (95% CI Limits of Agreement)
DIXON PDFF Reproducibility (<30%)	Reproducible between different scanners.	-1.86 to 5.95% (95% CI Limits of Agreement)
DIXON PDFF Reproducibility (>30%)	Reproducible between different scanners.	-8.64 to 23.52% (95% CI Limits of Agreement)
IDEAL PDFF Reproducibility (<30%)	Reproducible between different scanners.	-1.99 to 2.80% (95% CI Limits of Agreement)
IDEAL PDFF Reproducibility (>30%)	Reproducible between different scanners.	-13.46 to 6.98% (95% CI Limits of Agreement)
In-Vivo Testing
cT1 Repeatability	Highly repeatable.	-94.38 to 63.38 ms (ROI); -76.93 to 59.39 ms (Segmentation)
T2* Repeatability	Highly repeatable.	-6.07 to 5.70 ms (ROI)
DIXON PDFF Repeatability	Highly repeatable.	-1.77 to 3.64 % (ROI); -1.20 to 1.06% (Segmentation)
IDEAL PDFF Repeatability	Highly repeatable.	-1.92 to 1.54% (ROI); -1.83 to 1.28 % (Segmentation)
cT1 Reproducibility (between scanners)	Reproducible between scanners.	-89.70 to 120.58 ms (ROI); -84.91 to 121.79 ms (Segmentation)
T2* Reproducibility (between scanners)	Reproducible between scanners.	-3.68 to 6.35 ms (ROI)
DIXON PDFF Reproducibility (between scanners)	Reproducible between scanners.	-6.21 to 2.63% (ROI); -3.14 to 0.88% (Segmentation)
IDEAL PDFF Reproducibility (between scanners)	Reproducible between scanners.	-2.66 to 2.77% (ROI); -1.74 to 1.21% (Segmentation)
cT1 Intra-Operator Variability	Variation well within prescribed criteria; minor additional variation for ROI method.	-27.38 to 28.33ms (ROI); -20.81 to 13.06ms (Segmentation)
T2* Intra-Operator Variability	Variation well within prescribed criteria; minor additional variation for ROI method.	-2.29 to 2.91 ms (ROI)
DIXON PDFF Intra-Operator Variability	Variation well within prescribed criteria; minor additional variation for ROI method.	-0.78 to 1.90 % (ROI); -0.29 to 0.45% (Segmentation)
IDEAL PDFF Intra-Operator Variability	Variation well within prescribed criteria; minor additional variation for ROI method.	-1.26 to 1.05% (ROI); -0.16 to 0.14% (Segmentation)
cT1 Inter-Operator Variability	Variation well within prescribed criteria; minor additional variation for ROI method.	-48.05 to 39.89ms (ROI); -37.84 to 26.51ms (Segmentation)
T2* Inter-Operator Variability	Variation well within prescribed criteria; minor additional variation for ROI method.	-2.64 to 4.90 ms (ROI)
DIXON PDFF Inter-Operator Variability	Variation well within prescribed criteria; minor additional variation for ROI method.	-2.27 to 4.57% (ROI); -0.55 to 1.22% (Segmentation)
IDEAL PDFF Inter-Operator Variability	Variation well within prescribed criteria; minor additional variation for ROI method.	-2.09 to 1.82 % (ROI); -0.37 to 0.26% (Segmentation)
cT1 Worst-Case Variability	Highly reproducible.	-126.52 to 104.19 ms (ROI); -65.27 to 120.27 ms (Segmentation)
T2* Worst-Case Variability	Highly reproducible.	-3.68 to 6.35 ms (ROI)
DIXON PDFF Worst-Case Variability	Highly reproducible.	-2.04 to 0.76 % (ROI); -2.72 to 1.24% (Segmentation)
IDEAL PDFF Worst-Case Variability	Highly reproducible.	-3.75 to 2.83% (ROI); -1.92 to 1.35% (Segmentation)
Substantial Equivalence (LMSv3 vs. LMSv2.1)	Performs as well as its predicate.
Phantom T1	Negligible difference.	-1.96 to 2.09ms (95% CI Limits of Agreement)
Phantom T2*	Negligible difference.	-0.08 to 0.08ms (95% CI Limits of Agreement)
Phantom DIXON PDFF (< 30%)	Within 1% of predicate.	-0.18 to 0.10 % (95% CI Limits of Agreement)
Phantom DIXON PDFF (≥ 30%)	Within 2% of predicate.	-1.62 to 1.02 % (95% CI Limits of Agreement)
In-vivo T1	cT1 values within 30ms of predicate.	-28.08 to 28.73ms (95% CI Limits of Agreement)
In-vivo T2*	T2* values within 2ms of predicate.	-0.43 to 1.69ms (95% CI Limits of Agreement)
In-vivo DIXON PDFF	Negligible difference.	-0.18 to 0.10 % (95% CI Limits of Agreement)

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

Phantom Testing: The sample size for phantom testing is not explicitly stated as a number of phantoms, but it involved phantoms "designed to mimic the human data but provide a wider range" and covered "worst-case scenarios." The data provenance is controlled laboratory conditions, using prepared phantoms.
In-Vivo Testing (Clinical): The study used "in-vivo volunteer data." The precise number of volunteers is not specified. The data provenance is implicitly prospective, as it refers to "volunteer scans." No country of origin is explicitly mentioned, but the submitter (Perspectum Diagnostics Ltd) is based in the United Kingdom.
Substantial Equivalence Testing: Used both "phantom measurements" and "in-vivo measurements." The specific sample sizes for these comparisons are not detailed.

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

The document does not describe the establishment of a "ground truth" through expert consensus for the test set, specifically in the context of diagnostic accuracy. The performance testing focuses on the accuracy and variability of the quantitative measurements (cT1, T2*, PDFF) derived by the software rather than a diagnostic outcome.

For phantom testing, ground truth values are inherent to the precisely calibrated phantoms. For in-vivo testing, variability is measured, and for substantial equivalence, the comparison is against the predicate device's measurements. There is no mention of human experts establishing a ground truth for the quantitative values directly measured by the device for these performance tests.

4. Adjudication Method for the Test Set

Not applicable. The performance testing described does not involve human adjudication of diagnostic outcomes or image interpretation in the way a clinical study for sensitivity/specificity for a diagnosis would. It focuses on the quantitative output of the software.

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

No. The document describes performance testing for device accuracy, repeatability, reproducibility, and substantial equivalence to a predicate device. It does not mention an MRMC comparative effectiveness study involving human readers with and without AI assistance or an effect size of improvement.

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

Yes, the performance testing described is primarily standalone performance testing. LiverMultiScan (LMSv3) is explicitly described as a "standalone software application" and a "post-processing, standalone software device." The tests assess the algorithms' performance in generating quantitative metrics (accuracy, repeatability, reproducibility) without requiring human interpretation as part of the core measurement. Operators (trained PD operators) are involved in using the device to generate reports and place ROIs, and inter/intra-operator variability is assessed, but the fundamental measured values are algorithmically derived from the MR data.

7. Type of Ground Truth Used

Phantom Testing: The ground truth used was established by the precisely characterized properties of the phantoms, which were designed to mimic human data over a wide range of physiological values.
In-Vivo Testing: For the in-vivo volunteer data, the concept of "ground truth" for the measured parameters (cT1, T2*, PDFF) refers to the true physiological values within the volunteers, against which the device's precision and variability are assessed. While not explicitly stated how this "true" value would be independently confirmed, the focus is on self-consistency (repeatability, reproducibility, operator variability) of the device's measurements rather than comparison to an external gold standard like pathology.
Substantial Equivalence Testing: The ground truth for this comparison was the performance and measurements of the legally marketed predicate device, LiverMultiScan (LMSv2.1).

8. Sample Size for the Training Set

The document does not explicitly state the sample size (or any details) for a "training set." This type of detail is typically associated with AI/machine learning models where a dataset is used to train the algorithm. While LMSv3 includes "New algorithms" like Automatic Liver Segmentation, the document does not elaborate on how these algorithms were developed or if they involved a distinct training phase with a specific dataset.

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

Since a "training set" with established ground truth is not detailed, this information is not provided in the document.

Summary

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

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services seal on the left and the FDA acronym along with the full name of the agency on the right. The FDA part of the logo is in blue, with the acronym in a square and the full name in a sans-serif font. The logo is simple and professional, conveying the agency's authority and mission.

Perspectum Diagnostics Ltd Jaco Jacobs Chief Quality and Regulatory Compliance Officer 23-38 Hythe Bridge Street Oxford, Oxfordshire OX1 2ET UNITED KINGDOM

Re: K190017

Trade/Device Name: LiverMultiScan (LMSv3) Regulation Number: 21 CFR 892.1000 Regulation Name: Magnetic Resonance Diagnostic Device Regulatory Class: Class II Product Code: LNH Dated: May 31, 2019 Received: June 3, 2019

Dear Jaco Jacobs:

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. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. 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.

June 27, 2019

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

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

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) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

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 https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). 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 (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

For

Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known) K190017

Device Name LiverMultiScan (LMSv3)

Indications for Use (Describe)

These images and the physical parameters derived from the images, when interpreted by a trained clinician, yield information that may assist in diagnosis.

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

Image /page/3/Picture/2 description: The image shows the logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, dark gray font on the top line. Below that, the word "Diagnostics" is written in a lighter gray font. To the right of the words is a colorful circular logo with yellow, green, blue, and pink sections.

Date Prepared: 26th June 2019

1. Submitter Details

Owner Address:	Perspectum Diagnostics Ltd23-38 Hythe Bridge StreetOxford,Oxfordshire,OX1 2ETUnited Kingdom
Owner/Operator Number:	10056574
Establishment Registration Number:	3014232555
Contact Person:	Dr Jaco Jacobsjaco.jacobs@perspectum-diagnostics.com+44 (0) 1865 655329

2. Subject and Predicate Device

	Subject Device	Predicate Device
510(k) number	K190017	K172685
Legal Manufacturer	Perspectum Diagnostics Ltd	Perspectum Diagnostics Ltd
Owner/Owner Operator	Perspectum Diagnostics Ltd	Perspectum Diagnostics Ltd
Device Name	LMSv3	LMSv2
Proprietary/Common	LiverMultiScan	LiverMultiScan
Panel	Radiology	Radiology
Regulation	21 CFR 892.1000	21 CFR 892.1000
Risk Class	Class II	Class II
Product Class code	LNH	LNH
Classification	Magnetic Resonance Diagnostic Device	Magnetic Resonance Diagnostic Device

3. Subject Device Description

The main functionality of LiverMultiScan (LMSv3) includes:

. Reading DICOM 3.0 compliant datasets stored on workstations, and display of the data acquisition information
Post-processing of MRI data to generate parametric maps of Proton Density Fat Fraction PDFF), T2*, T1 and ironcorrected T1 (cT1) of the liver.
Quantification, and calculation of PDFF, T2* and cT1 metrics using tools such as automatic liver segmentation and ROI (region of interest) placement.

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

Image /page/4/Picture/1 description: The image is a logo for Perspectum Diagnostics. The word "Perspectum" is in bold, black font, and the word "Diagnostics" is in a smaller, gray font. To the right of the words is a colorful circle with four different colors: yellow, blue, green, and pink.

Generation of a summary report demonstrating the quantitative assessment results of fat fraction in the liver ● (PDFF), T2* and iron-corrected T1 (cT1).
LiverMultiScan (LMSv3) is intended to be used by trained operators. Reports generated by trained operators are intended for use by interpreting clinicians, including, but not limited to, radiologists, gastroenterologists, and hepatologists.

LiverMultiScan (LMSv3) is intended to be used as an aid to diagnosis. The results demonstrated by LMSv3 shall only be used as an additional input to existing procedures and diagnostic workflows. The responsibility for diagnosis and treatment decisions remains with the clinicians.

LiverMultiScan (LMSv3) is a post-processing, standalone software device which has no direct contact with the human body.

LiverMultiScan (LMSv3) presents a moderate level of concern.

Intended Use

Subject Device, LMSv3

"LiverMultiScan (LMSv3) is indicated for use as a magnetic resonance diagnostic device software application for noninvasive liver evaluation that enables the generation, display and review of 2D magnetic resonance medical image data and pixel maps for MR relaxation times.

LiverMultiScan (LMSv3) provides a number of tools, such as automated liver segmentation and region of interest (ROI) placements, to be used for the assessment of selected regions of an image. Quantitative assessment of selected regions includes the determination of triglyceride fat fraction in the liver (PDFF), T2* and iron-corrected T1 (cT1) measurements. PDFF may optionally be computed using the LMS IDEAL or three-point Dixon methodology.

These images and the physical parameters derived from the images, when interpreted by a trained clinician, yield information that may assist in diagnosis."

4. Subject and Predicate Comparison

4.1. Intended Use Comparison

The subject device and the predicate device are both indicated for use in the non-invasive evaluation of the liver, which enables the generation, display and review of 2D magnetic resonance medical image data and pixel maps for MR relaxation times. Both devices are designed to utilize DIXCOM 3.0 data as input and provide a range of tools to display and process data to determine triglyceride fat fraction in the liver, T2* and iron-corrected T1 measurements.

4.2. Subject and Predicate Device Comparison

The following characteristics were compared between the subject device and the predicate device in order to demonstrate substantial equivalence.

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

Image /page/5/Picture/1 description: The image is a logo for Perspectum Diagnostics. The word "Perspectum" is in bold, black font, and the word "Diagnostics" is in a smaller, gray font. To the right of the words is a circular logo with four different colored sections: yellow, green, blue, and pink. The logo is a ring with a gap in the middle, and the pink section is a half-circle.

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

Image /page/6/Picture/0 description: The image shows the logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, black font, while the word "Diagnostics" is written in a smaller, gray font. To the right of the words is a colorful, circular logo with yellow, blue, green, and pink sections.

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

Image /page/7/Picture/1 description: The image shows the logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, dark gray font. Below it and slightly to the right, the word "Diagnostics" is written in a lighter gray font. To the right of the words is a circular logo with four different colored sections: yellow, green, blue, and pink.

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

Image /page/8/Picture/0 description: The image is the logo for Perspectum Diagnostics. The logo has the word "Perspectum" in bold black font, with the word "Diagnostics" in gray font to the right and slightly below the first word. To the right of the words is a circular logo with four different colored sections: yellow, green, blue, and pink.

{9}------------------------------------------------

Image /page/9/Picture/0 description: The image shows the logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, dark gray font, while the word "Diagnostics" is written in a lighter gray font and is slightly smaller in size. To the right of the text is a circular logo with four different colored sections: yellow, blue, green, and pink.

Table 1. Comparison of similar characteristics between the subject and predicate device.

4.3. Sterilization and Shelf Life

LMSv3 is a post-processing standalone software device thus is non-invasive and non-sterile. The shelf life of LMSv3 is indefinite as long as the manufacturer continues to support the device. Both sterilization and shelf life characteristics are equivalent to the predicate device.

4.4. Biocompatibility

LMSv3 is a post-processing standalone software device thus it is non-contact and non-invasive. Biocompatibility testing was not deemed necessary to demonstrate the safety and effectiveness of LMSv3 does not consists of materials that differ from the predicate device.

4.5. Software

LMSv3 was successfully validated and verified against the requirements specification and it's intended use. The results from the validation and verification activities, documented in this submission, corroborate that LMSv3 meets the product requirement specifications and intended use, which is deemed to be substantially equivalent to the predicate (see section below).

Validation and verification activities were conducted in a controlled environment and in compliance with IEC 62304:2006, ISO 13485:2016 and 21 CFR 820. LMSv3 is also in compliance with the DICOM standard.

{10}------------------------------------------------

Image /page/10/Picture/1 description: The image shows the logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, dark gray font. Below it, the word "Diagnostics" is written in a smaller, light gray font. To the right of the words is a circular graphic with four colored sections: yellow, light blue, light green, and pink.

The verification and validation activities conducted demonstrates that LMSv3 is at least as safe and effective as the predicate device and does not introduce any new risks.

4.6. Electromagnetic and Electrical Safety

LMSv3 is a standalone software device. There are no electrical safety risks associated with the direct use of the LMsv3 device. Electromagnetic or electrical safety testing was not deemed necessary to demonstrate the safety and effectiveness of LMSv3.

4.7. Discussion

According to the comparisons between the subject device, we can conclude that the subject device does not raise any new potential safety risks when compared to the chosen predicate device and performs in accordance with its intended use.

The subject device is substantially equivalent to the predicate device, both regulated under regulation 21 CFR 892.1000. Substantial equivalence is based on the following observations:

The indications for use and intended uses of both the subject device and predicate device are equivalent .
. The subject device and predicate device both support multi-slice MR data acquired using the specific acquisition protocols, from supported MR Systems, to acquire the input data
. The subject and predicate devices include software applications which utilise MR data to visualise and enable quantification of physiological characteristics in the liver to provide measurements which may be used to aid diagnosis
. Both the subject device and the predicate device include applications to facilitate the import and visualization of MR data sets and include tools to enable the manipulation of the views and to enable the quantification and analysis of tissue characteristics in the liver from the MR data
The subject and predicate device are both standalone software applications to facilitate the import and . visualization of MR data sets
The subject and predicate devices enable the quantification of analysis of tissue characteristics in the liver from . the MR data
The subject and predicate devices both support the region of interest (ROI) measurements derived from MR . images and parametric maps of tissue characteristics
The subject and predicate device use the same algorithms for the ROI measurements on cT1, T2* and DIXON . PDFF
The subject and predicate device facilitate the creation of a medical report containing the images and analysis . output derived from quantification of liver tissue parameters intended to be interpreted by a trained clinician
The reports produced from both the subject and predicate device include tabular display of quantification . statistics, parametric map images and include normal range references
. Both the subject and predicate devices are designed to run on general-purpose computing hardware
Both the subject and predicate device are intended to be used in the same use environment and by trained PD . operators
Performance testing demonstrates that the subject device performs at least as safely and effectively as the . proposed predicate device

{11}------------------------------------------------

Image /page/11/Picture/1 description: The image is a logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, dark gray font. Below it, the word "Diagnostics" is written in a lighter gray font. To the right of the words is a circular graphic with four colored sections: yellow, green, blue, and pink.

5. Reference Devices

5.1. First Reference Device

Legal manufacturer:	Siemens AG
Common name:	Software syngo MR E11A for the MAGNETOM systems Aera/Skyra
Device name/Trade name:	MAGNETOM AeraMAGNETOM Skyra
Classification Regulation:	21 CFR 892.1000
510(k) Number:	K141977
Regulation Name:	Magnetic Resonance Diagnostic Device
Device Classification:	Class II
Device Panel:	Radiology
Device Product Code:	LNH

5.2.	Second Reference Device
Legal manufacturer:	GE Medical Systems
Common name:	IDEAL IQ Software Option
Device name/Trade name:	IDEAL IQ Software Option
Classification Regulation:	21 CFR 892.1000
510(k) Number:	K103411
Regulation Name:	Magnetic Resonance Diagnostic Device
Device Classification:	Class II
Device Panel:	Radiology
Device Product Code:	LNH

We make use of other legally marketed devices as reference devices to abridge differences in technological characteristics between the predicate and subject device and to substantiate claims that no different questions of safety and effectiveness are raised using a reference device that is already 510(k) cleared and legal marketed.

6. Performance Testing

General

LMSv3 underwent full performance testing under controlled conditions to corroborate that it is safe and effective to use. The performance testing conducted demonstrates that LMSv3 is at least as safe and effective as the predicate device and does not introduce any new risks.

6.1. Performance Testing – Bench

Phantom Testing

The phantom performance testing was conducted to verify the accuracy, repeatability of the device measurements on the phantoms which were designed to mimic the human data but provide a wider range.

The results of worst-case scenarios are summarized in the tables below, demonstrating:

The MOLLI-based T1 measurement produced by LMSv3 is consistent with the literature-reported . underestimation of ground truth T1 using MOLLI techniques [3][4].
LMSv3 measurements of T2* and IDEAL PDFF are accurate over the expected physiological range of values. .
LMSv3 measurements of DIXON PDFF are relatively accurate over the expected physiological range of values. • There are only minor deviations due to the known fat bias associated with the DIXON method.

{12}------------------------------------------------

Image /page/12/Picture/1 description: The image shows the logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, dark gray font, while the word "Diagnostics" is written in a smaller, light gray font and is placed below and to the right of "Perspectum". To the right of the words is a circular logo with four different colored sections: yellow, blue, green, and pink.

Phantom Metrics	Accuracy
	95% CI Limits of Agreement
T1	Up to 18.89% lower to the ground truth
T2*	- 9.31% to 7.53% of the ground truth
DIXON PDFF < 30%	-7.37% to 1.72%
DIXON PDFF > 30%	-28.93% to 6.83%
IDEAL PDFF < 30%	-1.17% to 1.43%
IDEAL PDFF > 30%	-5.05% to 10.70%

LMSv3 measurements of T1, T2* and PDFF are highly repeatable within the same scanner •

LMSv3 measurements of T1, T2* and PDFF are reproducible between different scanners .

Phantom Metrics	Repeatability95% CI Limits of Agreement	Reproducibility95% CI Limits of Agreement
T1	- 13.88 to 14.47 ms	- 2.66 to 10.78%
T2*	- 0.89 to 1.43 ms	- 3.43 to 2.42 ms
DIXON PDFF < 30%	- 0.66 to 0.82 %	- 1.86 to 5.95%
DIXON PDFF > 30%	- 2.11 to 1.96%	- 8.64 to 23.52%
IDEAL PDFF < 30%	- 1.27 to 0.87%	- 1.99 to 2.80%
IDEAL PDFF > 30%	- 3.80 to 1.93 %	- 13.46 to 6.98%

Performance Testing – Clinical 6.2.

ln-vivo

The performance testing using in-vivo volunteer data was conducted to assess the precision of LMSv3, inter- and intra- operator variability and the worst-case variability.

The results of worst-case scenarios are summarized in the tables below and demonstrate the following:

LMSv3 measurements of cT1, T2* and PDFF are highly repeatable ●
LMSv3 measurements of cT1, T2* and PDFF are reproducible between the scanners ●
. The variation introduced by operator measuring with the segmentation method is well within the prescribed acceptance criteria. There is only minor additional variation introduced by having two operators examining the same metrics using ROI method.
LMSv3 measurements of cT1, T2* and PDFF under the 'worst case' variability conditions are highly reproducible

Volunteer Metrics	Repeatability95% CI Limits of Agreement	Reproducibility95% CI Limits of Agreement
cT1 (ROI)	- 94.38 to 63.38 ms	-89.70 to 120.58 ms
cT1 (Segmentation)	-76.93 to 59.39 ms	-84.91 to 121.79 ms
T2* (ROI)	- 6.07 to 5.70 ms	-3.68 to 6.35 ms
DIXON PDFF (ROI)	-1.77 to 3.64 %	-6.21 to 2.63%
DIXON PDFF (Segmentation)	-1.20 to 1.06%	-3.14 to 0.88%
IDEAL PDFF (ROI)	-1.92 to 1.54%	-2.66 to 2.77%
IDEAL PDFF (Segmentation)	-1.83 to 1.28 %	-1.74 to 1.21%

{13}------------------------------------------------

Image /page/13/Picture/0 description: The image shows the logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, black font, while the word "Diagnostics" is written in a smaller, gray font and is placed below the first word. To the right of the words is a circular logo with four different colored sections: yellow, blue, green, and pink.

Volunteer Metrics	Intra-Operator95% CI Limits of Agreement(Range)	Inter-Operator95% CI Limits of Agreement(Range)
cT1 (ROI)	-27.38 to 28.33ms	-48.05 to 39.89ms
cT1 (Segmentation)	-20.81 to 13.06ms	-37.84 to 26.51ms
T2* (ROI)	-2.29 to 2.91 ms	-2.64 to 4.90 ms
DIXON PDFF (ROI)	-0.78 to 1.90 %	-2.27 to 4.57%
DIXON PDFF (Segmentation)	-0.29 to 0.45%	-0.55 to 1.22%
IDEAL PDFF (ROI)	-1.26 to 1.05%	-2.09 to 1.82 %
IDEAL PDFF (Segmentation)	-0.16 to 0.14%	-0.37 to 0.26%

Volunteer Metrics	Worst-Case Variability95% CI Limits of Agreement (Range)
cT1 (ROI)	-126.52 to 104.19 ms
cT1 (Segmentation)	- 65.27 to 120.27 ms
T2* (ROI)	-3.68 to 6.35 ms
DIXON PDFF (ROI)	-2.04 to 0.76 %
DIXON PDFF (Segmentation)	-2.72 to 1.24%
IDEAL PDFF (ROI)	-3.75 to 2.83%
IDEAL PDFF (Segmentation)	-1.92 to 1.35%

6.3. Performance Testing - Substantial Equivalence

The substantial equivalence testing conducted on LMSv3 against its predicate device, LMSv2, is summarized in the tables below. The latest version of predicate, LMSv2.1 was used in this testing.

Phantom measurements show the negligible difference between the results of LMSv3 and LMSv2.1. LMSv3 produces T1 value within in 3ms and T2* value within in 0.1ms of the predicate device. PDFF is within 1% of the predicate device when measuring PDFF<30%, and within 2% when measuring PDFF>30%.

Phantom Metric	Results (Range)
	95% CI Limits of Agreement
T1	-1.96 to 2.09ms
T2*	-0.08 to 0.08ms
DIXON PDFF (< 30)	-0.18 to 0.10 %
DIXON PDFF (≥ 30)	-1.62 to 1.02 %

{14}------------------------------------------------

Image /page/14/Picture/0 description: The image is a logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, dark gray font. To the right of "Perspectum" is the word "Diagnostics" in a smaller, light gray font. To the right of the words is a circular logo with four different colored sections: yellow, blue, green, and pink.

In-vivo measurements show that cT1 values produced by LMSv3 lie within 30ms of the predicate device, with T2* values within 2ms. There is negligible difference in the measurement of PDFF between LMSv3 and the predicate.

Volunteer Metric	Results (Range)
	95% CI Limits of Agreement
T1	-28.08 to 28.73ms
T2*	-0.43 to 1.69ms
DIXON PDFF	-0.18 to 0.10 %

As all the testing results are well within the acceptance criteria, it is concluded that LMSv3, when used as intended, performs as well as its predicate.

7. Conclusion

In a conclusion, all the information submitted to FDA is able to demonstrate that:

. The subject device, LiverMultiScan (LMSv3) has the same intended use as the predicate device, LiverMultiScan (LMSv2).
The subject device, LiverMultiScan (LMSv3) has slightly different technological characteristics. However, when used as intended, it does not raise different questions of safety and effectiveness in comparison to the predicate, LiverMultiScan (LMSv2).
The subject device, LiverMultiScan (LMSv3) is at least as safe and effective as the legally marketed predicate.

{15}------------------------------------------------

Image /page/15/Picture/1 description: The image shows the logo for Perspectum Diagnostics. The word "Perspectum" is written in a bold, dark gray font, while the word "Diagnostics" is written in a smaller, light gray font and is placed below the first word. To the right of the words is a circular logo with four different colored sections: yellow, blue, green, and pink.

References

[1] Dixon W. Simple proton spectroscopic imaging. Radiology 1984;153:189–194.
[2] Reeder, S.B., Pineda, A.R., Wen, Z., Shimakawa, A., Huanzhou, Y., Brittain, J.H., Gold, G.E., Beaulieu, C.H., Pelc, N.J., "Iterative Decomposition of Water and Fat with Echo Asymmetry and Least-Squares Estimation (IDEAL):
Application with Fast Spin-Echo Imaging", Magn Reson in Medicine, 2005, 54, pp 636-644.
[3] Piechnik et al. (2010) Journal of Cardiovascular Magnetic Resonance 12:69
[4] Puntmann et al. (2013) Journal of Cardiovascular Magnetic Resonance 15(Suppl1):E18

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.

Comparison of subject and Predicate Device
Characteristic	LMSv3 (Subject device)	LMSv2 (Predicate device)
Intended Useand Indicationsfor Use	"LiverMultiScan (LMSv3) is indicated for use as amagnetic resonance diagnostic device softwareapplication for non-invasive liver evaluation thatenables the generation, display and review of 2Dmagnetic resonance medical image data andpixel maps for MR relaxation times.LiverMultiScan (LMSv3) is designed to utilizeDICOM 3.0 compliant magnetic resonance imagedatasets, acquired from compatible MR Systems,to display the internal structure of the abdomenincluding the liver. Other physical parametersderived from the images may also be produced.LiverMultiScan (LMSv3) provides a number oftools, such as automated liver segmentation andregion of interest (ROI) placements, to be usedfor the assessment of selected regions of animage. Quantitative assessment of selectedregions includes the determination oftriglyceride fat fraction in the liver (PDFF), T2*and iron-corrected T1 (cT1) measurements. PDFFmay optionally be computed using the LMSIDEAL or three-point Dixon methodology.These images and the physical parametersderived from the images, when interpreted by atrained clinician, yield information that mayassist in diagnosis."	"LiverMultiScan is indicated for useas a magnetic resonance diagnostic devicesoftware application for non-invasive liverevaluation that enables the generation, displayand review of 2D magnetic resonance medicalimage data and pixel maps for MR relaxationtimes.LiverMultiScan is designed to utilize DICOM 3.0compliant magnetic resonance image datasets,acquired from compatible MR Systems, todisplay the internal structure of the abdomenincluding the liver. Other physical parametersderived from the images may also be produced.LiverMultiScan provides a numberof quantification tools, such as Region of Interest(ROI) placements, to be used for the assessmentof regions of an image to quantify liver tissuecharacteristics, including the determinationof triglyceride fat fraction in the liver, T2* andiron-corrected T1 measurements.These images and the physical parametersderived from the images, when interpreted by atrained clinician, yield information that mayassist in diagnosis."
TargetPopulation	Patients suitable to undergo an MRI scan and notcontra-indicated for MRI.	Patients suitable to undergo an MRI scan and notcontra-indicated for MRI.
Device User	Trained PD operator	Trained PD operator
Report User	An interpreting clinician or healthcarepractitioner	An interpreting clinician or healthcarepractitioner
Device UseEnvironment	Installation of LMSv3 is controlled and installedon general purpose workstations at PD's imageanalysis centre	Installation of LMSv2 is controlled and installedon general purpose workstations at PD's imageanalysis centre
Clinical Setting	LMSv3 is a standalone software device that'sintended to be installed on general useworkstations at PD's image analysis centre. Theintended device users will log on to the	LMSv2 is a standalone software device that'sintended to be installed on general useworkstations at PD's image analysis centre. Theintended device users will log on to the
Comparison of subject and Predicate Device
Characteristic	LMSv3 (Subject device)	LMSv2 (Predicate device)
	workstations, access the device, and use thedevice on general-use HD monitors.	workstations, access the device, and use thedevice on general-use HD monitors.
	LMSv3 is a post-processing software, theintended device users are trained internal PDoperators.	LMSv2 is a post-processing software, theintended device users are trained internal PDoperators.
	The end-users for the output from the device,the pdf report, are clinicians who receive andinterpret LMSv3 reports.	The end-users for the output, the pdf report, areclinicians who receive and interpret LMSv2reports.
AnatomicalLocation	Abdomen, Liver	Abdomen, Liver
EnergyConsiderations	Software only application. The device, astandalone software application, does notdeliver, monitor or depend on energy deliveredto or from patients.	Software only application. The device, astandalone software application, does notdeliver, monitor or depend on energy deliveredto or from patients.
Design:Purpose	Standalone software application to facilitate theimport and visualization of MR data setsencompassing the abdomen, including the liverwith functionality independent of the MRIequipment vendor.Software application intended to display andvisualize 2D multi-slice, spin-echo MR data setsencompassing the abdomen. The user mayprocess, and review DICOM 3.0 compliantdatasets within the system.	Standalone software application to facilitate theimport and visualization of MR data setsencompassing the abdomen, including the liverwith functionality independent of the MRIequipment vendor.Software application intended to display andvisualize 2D multi-slice, spin-echo MR data setsencompassing the abdomen. The user mayprocess, and review DICOM 3.0 compliantdatasets within the system and/or acrosscomputer networks.
Design: Tools	Allows for the visualisation via parametric mapsand quantification of metrics (cT1, T2* and PDFF)from liver tissue and exportation of results &images to a deliverable pdf report.LMSv3 allows for:cT1 ROI placed method on the cT1 map with IQRand median metrics from the placed ROI'spotentially across multiple acquired slices. Full segmentation of the outer liver contourand liver vasculature of the cT1 parametricmap. IQR and median metrics are reportedfrom the segmentation. T2 ROI placed method on the T2* map withIQR and median metrics from the placedROI's potentially across multiple acquired	Allows for the visualisation via parametric mapsand quantification of metrics (cT1, T2* and PDFF)from liver tissue and exportation of results &images to a deliverable pdf report.LMSv2 allows for:cT1 ROI placed method on the cT1 map with IQRand median metrics from the placed ROI'spotentially across multiple acquired slices. T2* ROI placed method on the T2* map withIQR and median metrics from the placed
Comparison of subject and Predicate Device
Characteristic	LMSv3 (Subject device)	LMSv2 (Predicate device)
	slices T2* parametric maps are calculatedfrom the Gradient Multi-Echo method.PDFF ROI placed method on the PDFF map withIQR and median metrics from the placedROI's potentially across multiple acquiredslices potentially across multiple acquiredslices. PDFF parametric maps can be calculatedusing either the LMS IDEAL method [2] orthe three-point DIXON method. [1] Full liver segmentation of the PDFFparametric map where IQR and medianmetrics are reported from thesegmentation.	ROI's potentially across multiple acquiredslices T2* parametric maps are calculatedfrom the Gradient Multi-Echo method.PDFF ROI placed method on the PDFF map withIQR and median metrics from the placedROI's potentially across multiple acquiredslices potentially across multiple acquiredslices. PDFF parametric maps are calculated fromthe three-point DIXON method. [1]
Design:Algorithms	Previously cleared algorithms:Noise Determination Algorithms T1 mapping Algorithms T2* mapping Algorithms Unwrapping Phase Image Algorithms Creation of cT1 image Algorithms Water and Fat Mapping Algorithms New algorithms: IDEAL Processing Algorithms MAGO Processing Algorithms Quality Check for Shimming Automatic Liver Segmentation Algorithms Segmentation Mapping to T2/PDFFalgorithms LMSv3 uses identical algorithms cleared in LMSv2to quantify cT1, T2 and DIXON PDFF using ROI's.	Noise Determination Algorithms T1 mapping Algorithms T2* mapping Algorithms Unwrapping Phase Image Algorithms Creation of cT1 image Algorithms Water and Fat Mapping Algorithms
Design: MRRelaxometry	T1, iron-corrected T1 (cT1) and T2* mapping.	T1, iron-corrected T1 (cT1) and T2* mapping.
Design: LiverFatQuantification	Utilizes MR images that exploit the difference inresonance frequencies between hydrogen nucleiin water and triglyceride fat using either LMSIDEAL method or three-point DIXON method.	Utilizes MR images that exploit the difference inresonance frequencies between hydrogen nucleiin water and triglyceride fat using the three-point DIXON method.
Comparison of subject and Predicate Device
Characteristic	LMSv3 (Subject device)	LMSv2 (Predicate device)
Design: LiverSegmentation	LMSv3 supports automatic multi-slice full liversegmentation of the cT1 and PDFF parametricmap. Use of this functionality is at the discretionof the operator instead or in combination withthe ROI based method.The cT1 segmented liver is presented in colourlevel window, while the rest of the cT1 image ispresented in greyscale level window with ductsand liver vasculature excluded from thesegmented volume.	Does not support whole liver segmentation. Seefirst reference device below, LiverLab.
Design: Regionsof Interest(ROI)	Median and interquartile range measurementscreated from a cross sectional slice of livertissue. For each parametric map, statistics frommultiple Regions of Interest (ROIs) — potentiallyplaced across multiple slices – are summarised.Also supports the display of 'Live' ROI statisticswhen moving the ROI across the parametricmap.	Median and interquartile range measurementscreated from a cross sectional slice of livertissue. For each parametric map, statistics frommultiple Regions of Interest (ROIs) — potentiallyplaced across multiple slices - are summarised.Also supports the display of 'Live' ROI statisticswhen moving the ROI across the parametricmap.
Design:ParametricMaps	Iron corrected T1 (cT1), T2* and triglyceride fat(i.e. DIXON or IDEAL Proton Density Fat Fraction(PDFF)) parametric maps are supported.PDFF parametric maps are calculated with eitherMAGNITUDE ONLY-IDEAL, when the data isreceived from GE and Phillips scanners, andCOMPLEX-IDEAL for Siemens. When analysingCOPLEX-IDEAL data a field map is also availableduring analysis. PDFF may also be calculatedusing the three-point DIXON method.	Iron corrected T1 (cT1), T2* and triglyceride fat(i.e. DIXON Proton Density Fat Fraction (PDFF))parametric maps are supported.
Design:Visualisation	Iron corrected T1 (cT1), T2* and triglyceride fat(also known as Proton Density Fat Fraction(PDFF)) parametric maps are supported.Iron corrected T1 (cT1) displayed using LMSv3colourmap, designed to have maximum contraston liver parenchymal tissue.	Iron corrected T1 (cT1), T2* and triglyceride fat(also known as Proton Density Fat Fraction(PDFF)) parametric maps are supported.Iron corrected T1 (cT1) displayed using LMSv2colourmap, designed to have maximum contraston liver parenchymal tissue.
Design:SupportedModalities	DICOM 3.0 compliant MR data from supportedMRI scanners.	DICOM 3.0 compliant MR data from supportedMRI scanners.
Design: Report	Quantified metrics from liver tissue and imageanalysis collated in a deliverable pdf report.Histogram of segmented area and proportion ofPDFF intensities are included in the final reportto give a better understanding on thedistribution of PDFF intensities.	Quantified metrics from liver tissue and imagesanalysis collated in a deliverable pdf report.
Comparison of subject and Predicate Device
Characteristic	LMSv3 (Subject device)	LMSv2 (Predicate device)
Compatibilitywith theenvironment	Installation of LMSv3 is controlled and is installedon general purpose workstations at PD's imageanalysis centre.LMSv3 reads in local files compliant with DICOM3.0.	Installation of LMSv2 is controlled and is installedon general purpose workstations at PD's imageanalysis centre.LMSv2 reads in local files compliant with DICOM3.0.
Performance	Validated with phantom scans, synthetic rawdata and volunteer scans covering a range ofphysiological values for cT1, T2* and PDFF.	Validated with phantom scans, synthetic rawdata and volunteer scans covering a range ofphysiological values for cT1, T2* and PDFF.
Supported MRISystems	Validated across all listed supportedmanufacturers and field strengths.	Validated across all listed supportedmanufacturers and field strengths.
Standards	IEC 62304, IEC 62366, DICOM 3.0, ISO 14971, ISO13485	IEC 62304, DICOM 3.0, ISO 14971, ISO 13485
System/Operating System	Mac OS	Mac OS
Materials	Not applicable, standalone software.	Not applicable, standalone software.
Biocompatibility	Not applicable, standalone software.	Not applicable, standalone software.
Sterility	Not applicable, standalone software.	Not applicable, standalone software.
Electrical Safety	Not applicable, standalone software.	Not applicable, standalone software.
MechanicalSafety	Not applicable, standalone software.	Not applicable, standalone software.
Chemical Safety	Not applicable, standalone software.	Not applicable, standalone software.
Thermal Safety	Not applicable, standalone software.	Not applicable, standalone software.
RadiationSafety	Not applicable, standalone software.	Not applicable, standalone software.