FerriSmart is indicated to:
· measure liver iron concentration in individuals with confirmed or suspected systemic iron overload;
· monitor liver iron burden in transfusion dependent thalassemia patients with sickle cell disease receiving blood transfusions:
• aid in the identification and monitoring of non-transfusion-dependent thalassemia patients receiving therapy with deferasirox.

Device Description

FerriSmart is a stand-alone software application that automatically analyses multi-slice, spin-echo MRI data sets encompassing the abdomen to determine the signal decay rate (R>) that is used to characterize iron loading in the liver, which is then transformed by a defined calibration curve to provide a quantitative measure of liver iron concentrations in vivo.

The software application is a measuring medical device intended to be hosted either in a cloudbased or on site hosted platform and used directly by the radiographer. It does not drive the MRI machine and does not come into direct contact with patients.

The key components of FerriSmart are:

Specific Magnetic Resonance Imaging Protocol: Use of a specific magnetic resonance imaging protocol for acquisition of the raw image data. The imaging protocol is critical to ensure the quality of the end results. Its adherence is verified by the IQC Module, an automated algorithm that checks the correctness of the parameters of the data acquisition protocol.
FerriSmart AI Analysis Software: Custom-designed image analysis software performing the R2 measurement based on AI (Artificial Intelligence) technology.
An additional software module (algorithmic) that Liver Iron Measurement: incorporates a calibration curve relating R2 to liver iron concentration (LIC) is added to allow production of a liver iron concentration report.

The result report provides the patient's average LIC reported in micromole and milligram per gram dry weight of liver. The images analysed are included in the report for review by the radiologist. The results are intended to assist in clinical diagnosis, and/or in making decisions concerning clinical management.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

Acceptance Criteria (Implicit)	Reported Device Performance (FerriSmart vs. FerriScan)
Repeatability (Precision)	Below 3 mg Fe/g dry tissue: Repeatability is consistent with FerriScan. Above 3 mg Fe/g dry tissue: Upper and lower 95% limits of repeatability ratios of 1.26 (95% CI 1.24-1.28) and 0.79 (95% CI 0.78 – 0.81). This corresponds to a standard error on a single measurement of approximately 9%, which is better than biopsy (19-40%).
Accuracy (Bias)	Below 3 mg Fe/g dry tissue: Negligible bias. Above 3 mg Fe/g dry tissue: Clinically acceptable bias. Note: FerriSmart and FerriScan should not be considered interchangeable.
Diagnostic Performance (Sensitivity & Specificity for various LIC thresholds)	LIC Threshold: 1.8 mg Fe/g dry tissue (upper 95% limit of normal LIC): Sensitivity: 96% (95% CI 94-97%) Specificity: 80% (95% CI 73-87%) LIC Threshold: 3.0 mg Fe/g dry tissue (interrupt deferasirox for NTDT): Sensitivity: 96% (95% CI 94-97%) Specificity: 95% (95% CI 92-98%) LIC Threshold: 3.2 mg Fe/g dry tissue (historical HHC definition, lower optimal for chelation): Sensitivity: 94% (95% CI 92-96%) Specificity: 95% (95% CI 92-98%) LIC Threshold: 5.0 mg Fe/g dry tissue (consider deferasirox for NTDT): Sensitivity: 91% (95% CI 89-94%) Specificity: 97% (95% CI 95-99%) LIC Threshold: 7.0 mg Fe/g dry tissue (upper optimal for chelation, increased risk): Sensitivity: 92% (95% CI 90-95%) Specificity: 97% (95% CI 95-98%) LIC Threshold: 15.0 mg Fe/g dry tissue (greatly increased cardiac risk, increase deferasirox dose): Sensitivity: 89% (95% CI 85-93%) Specificity: 98% (95% CI 98-99%) Overall, most sensitivities and specificities are above 90%, with the exception of specificity at 1.8 mg Fe/g dry tissue (80%) and sensitivity at 15.0 mg Fe/g dry tissue (89%). These exceptions are deemed acceptable for clinical use.
Usability	All participants found the product easy to use, fast, and technically reliable (no bugs).
Software Verification & Validation	Developed, verified, and validated following Design Control principles and General Principles of Software Validation guidelines.

Study Information

Sample sizes used for the test set and the data provenance:
- Repeatability Study Test Set: 60 subjects scanned twice. The provenance of this data (country of origin, retrospective/prospective) is not specified.
- Clinical Study Test Set: 971 datasets from multiple makes and models of MRI scanners. The provenance (country of origin, retrospective/prospective) is not specified.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The ground truth for the clinical study was the predicate device, FerriScan R2-MRI Analysis System. For the predicate, "human interaction for Region of Interest (ROI) selection" was noted.
- The text does not specify the number or qualifications of experts involved in establishing the FerriScan results used as ground truth for this FerriSmart study. It only mentions that FerriScan is used "in-house by Resonance Health's analysts."
Adjudication method for the test set:
- The text does not explicitly state an adjudication method (such as 2+1 or 3+1) for the comparison between FerriSmart and FerriScan results, or for the FerriScan results themselves. The ground truth was based on the FerriScan device output.
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No, an MRMC comparative effectiveness study was not done. The study's clinical performance evaluation was a standalone performance assessment of FerriSmart against a predicate device (FerriScan), not a comparison of human readers with vs. without AI assistance. The user of FerriSmart is stated to be a radiologist, who oversees the report, but the study focuses on the algorithm's performance relative to the predicate.
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance study was done. FerriSmart is described as a "stand-alone software application" which "automatically analyses" MRI data. The clinical study assessed its R2 and LIC measurements and diagnostic performance against the predicate without direct human intervention in the analysis process besides the radiologist reviewing the final report. FerriSmart uses an algorithm for automatic quality checks, whereas the predicate "requires human input" for some checks.
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The ground truth for the study was the results from the predicate device, FerriScan R2-MRI Analysis System. FerriScan itself uses an algorithmic approach with human interaction for ROI selection and aims to provide quantitative measures of LIC, which would ultimately correlate to other clinical ground truths like liver biopsy in its own validation studies (as hinted by the comparison to biopsy error rates).
The sample size for the training set:
- The document states, "FerriSmart AI Analysis Software has been trained on FerriScan data." However, the sample size for the training set is not explicitly provided in the given text.
How the ground truth for the training set was established:
- The ground truth for the FerriSmart training set was established using data processed by the predicate device, FerriScan R2-MRI Analysis System. The text explicitly states, "FerriSmart AI Analysis Software has been trained on FerriScan data." This implies that the outputs from FerriScan (R2 measurements and LIC values) were used as the target for the AI's learning process.

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 logo on the left and the FDA logo on the right. The FDA logo features the letters 'FDA' in a blue square, followed by the words 'U.S. FOOD & DRUG ADMINISTRATION' in blue text.

November 30, 2018

Celine Royet Regulatory Affairs Manager Resonance Health Analysis Service Pty Ltd 141 Burswood Rd Burswood 61000 AUSTRALIA

Re: K182218

Trade/Device Name: FerriSmart Analysis System Regulation Number: 21 CFR 892.1001 Regulation Name: Liver iron concentration imaging companion diagnostic for deferasirox Regulatory Class: Class II Product Code: PCS Dated: October 22, 2018 Received: October 26, 2018

Dear Celine Royet:

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.

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

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

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/CombinationProducts/GuidanceRegulatoryInformation/ucm597488.htm); 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 http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice

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

Sincerely,

Michael D. O'Hara
For

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

Enclosure

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

Indications for Use

510(k) Number (if known) K182218

Device Name FerriSmart

Indications for Use (Describe)

FerriSmart is indicated to:

· measure liver iron concentration in individuals with confirmed or suspected systemic iron overload;

· monitor liver iron burden in transfusion dependent thalassemia patients with sickle cell disease receiving blood transfusions:

• aid in the identification and monitoring of non-transfusion-dependent thalassemia patients receiving therapy with deferasirox.

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

X | Prescription Use (Part 21 CFR 801 Subpart D)

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

CONTINUE ON A SEPARATE PAGE IF NEEDED.

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

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

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

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

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

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

510(K) SUMMARY

This Summary has been prepared in accordance with 21 CFR 807.92.

Date Prepared	28-Nov-2018
Submitted by	Resonance Health Analysis Service Pty Ltd141 Burswood RdBurswood 6100AUSTRALIA
Main Contact	Mrs Celine RoyetRegulatory Affairs Managerceliner@resonancehealth.comTel: +61 8 9286 5300Fax: +61 8 9286 5399
US Contact (US Agent)	Rene Van De ZandeDirector & GMEmergo Global Representation LLC2500 Bee Cave Road Building 1, Suite 300Austin, TX 78746Phone: 512 3279997Fax: 512 3279998Email: USAgent@ul.com

General Information

Device Information

Name of Device	FerriSmart
Trade/proprietary Name	FerriSmart
Classification	Class II
Product Code	90-PCS
CFR Section	892.1001Liver Iron Concentration Imaging CompanionDiagnostic For Deferasirox
Panel	Radiology

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

Description of the Device

The key components of FerriSmart are:

Specific Magnetic Resonance Imaging Protocol: Use of a specific magnetic resonance imaging protocol for acquisition of the raw image data. The imaging protocol is critical to ensure the quality of the end results. Its adherence is verified by the IQC Module, an automated algorithm that checks the correctness of the parameters of the data acquisition protocol.
FerriSmart AI Analysis Software: Custom-designed image analysis software performing the R2 measurement based on AI (Artificial Intelligence) technology.
An additional software module (algorithmic) that Liver Iron Measurement: incorporates a calibration curve relating R2 to liver iron concentration (LIC) is added to allow production of a liver iron concentration report.

Intended Use

The intended use of FerriSmart is:

For the measurement of R2 and iron concentration in the liver from MRI scans.

Indications for Use

FerriSmart is indicated to:

measure liver iron concentration in individuals with confirmed or suspected systemic iron overload;
monitor liver iron burden in transfusion dependent thalassemia patients and patients with sickle cell disease receiving blood transfusions;.
. aid in the identification and monitoring of non-transfusion-dependent thalassemia patients receiving therapy with deferasirox.

PREDICATE INFORMATION

FerriSmart is substantially equivalent to the predicate device FerriScan R2-MRI Analysis System (Resonance Health Analysis Services) - DEN130012 / K124065.

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

Reference Device

The reference device is FerriScan R2-MRI Analysis System (Resonance Health Analysis Services) – K043271.

Substantial Equivalence Information

The table below summarizes the main similarities and differences between FerriSmart, the predicate and the reference device.

	Proposed Device	Predicate Device		Reference Device
	FerriSmart	FerriScanAnalysis System	R2-MRI	FerriScanAnalysis System	R2-MRI
Regulatory Class	II	II		II
510(k) number	K182218	DEN130012 / K124065		K043271
ClassificationName	Liver Iron ConcentrationImaging CompanionDiagnostic ForDeferasirox	Liver Iron ConcentrationImaging CompanionDiagnostic ForDeferasirox		System, NuclearMagnetic ResonanceImaging, System, ImageProcessing Radiological
CFR Section	892.1001	892.1001		892.1000
Product Code andClassificationPanel	90 PCS	90 PCS		90 LNH
Description	Standalone softwarepackage thatautomatically analysesmulti-slice, spin-echoMRI data setsencompassing theabdomen to provideobjective andreproducibledetermination of liverparameters to supportclinicians in theassessment of liver ironstatus.The software tooldetermines the signaldecay rate (R2) that isused to characterize ironloading in the liver,which is then transformedby a defined calibrationcurve to provide a	Software tool to facilitatethe import andvisualization ofmulti-slice, spin-echoMRI data setsencompassing theabdomen, withfunctionality independentof the MRI equipmentvendor, to provideobjective andreproducibledetermination of liverparameters to supportclinicians in theassessment of liver ironstatus.The software tool alsocalculates the signaldecay rate (R2) that isused to characterize ironloading in the liver,which is then transformed		Software tool to facilitatethe import andvisualization ofmulti-slice, spin-echoMRI data setsencompassing theabdomen, withfunctionality independentof the MRI equipmentvendor, to provideobjective andreproducibledetermination of liverparameters to supportclinicians in theassessment of liver ironstatus.The software tool alsocalculates the signaldecay rate (R2) that isused to characterize ironloading in the liver,which is then transformedby a defined calibration
	Proposed Device	Predicate Device		Reference Device
	FerriSmart	FerriScanAnalysis System	R2-MRI	FerriScanAnalysis System	R2-MRI
	quantitative measure ofliver iron concentrationsin vivo.	by a defined calibrationcurve to provide aquantitative measure ofliver iron concentrationsin vivo.	curve to provide aquantitative measure ofliver iron concentrationsin vivo.
Technology	Convolutional neuralnetworks for the imageanalysis.Algorithmic for theimages quality checksand R2 conversion intoLIC.	Algorithmic, with humaninteraction for Region ofInterest (ROI) selection.	Algorithmic, with humaninteraction for Region ofInterest (ROI) selection.
Intendedpurpose(s)	1. Supporting clinicaldiagnoses about the statusof liver ironconcentration.2. Supporting thesubsequent clinicaldecision-makingprocesses.3. Supporting the use inclinical research trials,directed at studyingchanges in liver ironconcentration as a resultof interventions.	1. Supporting clinicaldiagnoses about the statusof liver ironconcentration.2. Supporting thesubsequent clinicaldecision-makingprocesses.3. Supporting the use inclinical research trials,directed at studyingchanges in liver ironconcentration as a resultof interventions.4. It contains an imageviewer for importingDICOM images,browsing through patientdatasets, viewing imagesand performing region ofinterest analysis.	1. Supporting clinicaldiagnoses about the statusof liver ironconcentration.2. Supporting thesubsequent clinicaldecision-makingprocesses.3. Supporting the use inclinical research trials,directed at studyingchanges in liver ironconcentration as a resultof interventions.4. It contains an imageviewer for importingDICOM images,browsing through patientdatasets, viewing imagesand performing region ofinterest analysis.
Intended Use	Measurement of R2 andiron concentration in theliver from MRI scans	For the analysis of multi-slice, spin-echo MRI datasets of the liver for themeasurement of liver R2and liver ironconcentration and toassist in the provision ofiron chelation therapy	Measurement of R2 andiron concentration in theliver from MRI scans.
Indications	Indicated to:• measure liver ironconcentration inindividuale with	Measure liver ironconcentration to aid inthe identification andmonitoring of non-	The R2-MRI AnalysisSystem is an accessorydiagnostic device to MRIscanners and is intended

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

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

	Proposed Device	Predicate Device	Reference Device
	FerriSmart	FerriScanR2-MRIAnalysis System	FerriScanR2-MRIAnalysis System
	confirmed orsuspected systemiciron overload;monitor liver ironburden in transfusiondependentthalassemia patientsand patients withsickle cell diseasereceiving bloodtransfusions;.aid in theidentification andmonitoring of non-transfusion-dependentthalassemia patientsreceiving therapywith deferasirox.	thalassemia patientsreceiving therapy withdeferasirox.	present images thatreflect the magneticresonance spectra for thedetermination of iron onthe liver.
User	Radiologist	Resonance Health'strained analyst	Resonance Health'strained analyst
Hosting platform	Cloud-based or on-sitehosting	Resonance Health'sinternal server	Resonance Health'sinternal server
Image-typeutilized	Magnetic Resonance	Magnetic Resonance	Magnetic Resonance
Image format	DICOM	DICOM	DICOM
Data Acquisitionmethod	Single Spin Echo (SSE)	Single Spin Echo (SSE)	Single Spin Echo (SSE)
Anatomical Sites	Liver	Liver	Liver

Similarities with the predicate:

Both systems are stand-alone software applications, independent of the MRI scanner. Both systems have the same MRI data acquisition protocol: Single Spin Echo (SSE).

The anatomical site scanned (liver) is the same.

Both systems produce an output report comprising a quantitative measure of the signal decay rate (R2), which is then converted using the same calibration curve into Liver Iron Concentration (LIC).

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

Differences with the predicate:

Analysis technology is different: FerriScan is an algorithm-based technology. FerriSmart uses convolutional neural networks for image recognition and analysis. However FerriSmart AI Analysis Software has been trained on FerriScan data.

The image input quality check is different: parameters checked are the same but FerriSmart uses an algorithm to automatically perform the checks whereas FerriScan requires human input.

Users are different: FerriScan is used in-house by Resonance Health's analysts and results are provided as a service. FerriSmart user is the radiologist.

FerriSmart is cloud-based. FerriScan is kept in-house on Resonance Health's internal server.

Indications: FerriSmart encompasses the Indications of the predicate with additional indications supported by literature and demographics of the validation dataset used during the clinical validation against the predicate.

PERFORMANCE DATA

Resonance Health has followed the principles developed by the IMDRF and recently published by the FDA: Software as a Medical Device (SaMD): Clinical Evaluation. Final Guidance for Industry and FDA Staff. December 2017, to design the performance testing that support FerriSmart, using the predicate device FerriScan R2-MRI Analysis System (DEN130012/ K124065) as the reference standard.

The following performance data were provided in order to support the substantial equivalence determination and comply with the Special Controls defined by 21 CFR 892.1001.

Software Verification and Validation:

FerriSmart software has been developed, verified and validated following the Design Control principles and in accordance with the General Principles of Software Validation; Final Guidance for Industry and FDA Staff. U.S. Department Of Health and Human Services Food and Drug Administration. January 2002.

User Testing:

A User Testing study was conducted to assess to the usability of FerriSmart, including readability of the patient report and Instructions for Use. All participants of the study reported the product was easy to use, fast and technically reliable (no bugs).

Literature Review:

The reviewed literature and breakdown of patient population across several US sites have shown that the predicate FerriScan has been used to monitor in transfusion dependent thalassemia patients and patients with sickle cell disease receiving blood transfusions. These studies published in the scientific literature support the broadening of the indications from the predicate.

Repeatability Study:

Repeatability of FerriSmart was assessed in a study of 60 subjects who were scanned twice and had LIC measured each time using both FerriScan Analysis System and FerriSmart Analysis System. The data give information on the precision of FerriSmart.

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

Below 3 mg Fe/g dry tissue, FerriSmart has a repeatability that is consistent with that of FerriScan. Above 3 mg Fe/g dry tissue, the upper and lower 95% limits of repeatability ratios of 1.26 (95% CI 1.24-1.28) and 0.79 (95% CI 0.78 – 0.81) are acceptable since they correspond to a standard error on a single measurement of approximately 9% which is somewhat better than the standard error on a measurement of LIC by biopsy which ranges from about 19% in the absence of liver fibrosis to greater than 40% in end stage liver disease (Kreeftenberg et al. 1984; Emond et al. 1999).

Clinical Study:

The clinical study had 971 datasets from multiple makes and models of scanner for:

1. Assessing the performance of the FerriSmart IQC module;
Assessing the bias and limits of agreement between FerriSmart and FerriScan 2. measurements of LIC on multiple scanners;
Assessing the diagnostic performance of FerriSmart for predicting FerriScan LIC results 3. above various clinically relevant LIC thresholds on multiple scanners.

The sensitivities and specificities results are presented in the Table below.

Sensitivities and specificities of FerriSmart for predicting FerriScan LIC values greater than severalclinically relevant thresholds.
LIC threshold(mg Fe/g drytissue)	Clinical relevance	Sensitivity(95% CI)(%)	Specificity(95% CI)(%)
1.8	The upper 95% limit of normal LIC (Bassett et al. 1986).	96 (94 - 97)	80 (73 - 87)
3.0	Threshold below which deferasirox treatment fornon-transfusion dependent thalassemia (NTDT)patients should be interrupted (FDA 2013).	96 (94 - 97)	95 (92 - 98)
3.2	Historical phenotypic definition of iron overloadfor patients with hereditary hemochromatosis. Suggested lower limit of optimal range for LICsfor chelation therapy in transfusional Feoverload (Olivieri and Brittenham 1997).	94 (92 - 96)	95 (92 - 98)
5.0	Threshold above which iron chelation withdeferasirox can be considered for patients withNTDT (FDA 2013).	91 (89 - 94)	97 (95 - 99)
7.0	Suggested upper limit of optimal range for LICsfor transfusional Fe overload and threshold forincreased risk of iron-induced complications(Olivieri and Brittenham 1997). Threshold above which deferasirox dose shouldbe increased (to a maximum of 20 mg/kg/day)above the starting dose of 10 mg/kg /day inpatients with NTDT (FDA 2013).	92 (90 - 95)	97 (95 - 98)
15.0	Threshold for greatly increased risk for cardiacdisease and early death in patients withtransfusional iron overload (Olivieri andBrittenham 1997) Baseline LIC above which increase of	89 (85 - 93)	98 (98 - 99)

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

deferasirox dose to 20 mg/kg/day should be considered after first 4 weeks of therapy for NTDT patients (FDA 2013).

Bias: The bias between the FerriScan is negligible below 3 mg Fe/g dry tissue, and clinically acceptable above that threshold. However it is to be noted that FerriSmart and FerriScan should not be considered interchangeable.

Reproducibility: A validation study of the predicate demonstrated no statistical significant biases in calibration among 5 MRI scanners of different makes and models. As such, the measure of the limits of agreement between FerriSmart and the predicate includes any components of bias between sites.

While there is an overall bias between FerriSmart and FerriScan, the bias together with the random errors on the measurements do not result in unacceptable sensitivities and specificities of FerriSmart for predicting FerriScan results above the clinically relevant LIC thresholds. Most of the sensitivities and specificities are above 90% with exceptions being a specificity of 80 % (95% CI 73 - 87 %) for detecting FerriScan LIC values above 1.8 mg Fe/g dry tissue and a sensitivity of 89 % (95% CI 85 - 93 %) for detecting FerriScan LIC values above 15.0 mg Fe/g dry tissue. The threshold of 1.8 mg Fe/g dry tissue has more relevance to scientific population studies rather than clinical management of iron overload and therefore the low specificity at this threshold does not preclude the use of FerriSmart for monitoring iron loaded patients. The threshold of 15.0 mg Fe/g dry tissue is a key threshold used in management of iron overload. The sensitivity of 89% is likely acceptable for clinical use and is comparable with the sensitivity of FerriScan for predicting biopsy LIC above 15 mg Fe /g dry tissue (85%, 95% CI 70-94%) (St. Pierre et al. 2005).

RISK ANALYSES

Risk Analyses were performed through the development of the device in accordance with EN ISO 14971:2012 – Medical Devices – Application of Risk Management to Medical Devices.

Remaining risks have been identified and mitigated.

FerriSmart sensitivity and specificity are suitable for clinical decision making. This has been presented and discussed in the submitted documentation.

Report result is overseen by the radiologist and the final decision for clinical management of the patient is made by their treating clinician.

The overall risks for FerriSmart are considered acceptable. Post-marketing surveillance processes are in place and any events will be monitored closely. The Risk Analyses will be updated as deemed necessary.

The overall benefit of providing a cost-effective, quick, reliable, and accurate liver iron measuring test surpasses the risks.

LABELLING

FerriSmart labelling is in the form of a User Manual. This Manual presents in particular:

The instructions for acceptance testing of images prior to processing: this includes verification that the data acquisition settings of the scanner are within a specified tolerance by performing a test scan prior to any patient scan, and use of an in-built

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

Input Quality Control Module in the FerriSmart system that verifies adherence to the correct scanning protocol and rejects any non-conforming images.

. The data processing quality assurance protocols: pre-analysis check of the images with the in-built Input Quality Control Module in the FerriSmart system that verifies adherence to scanning protocol and rejects any non-conforming images, and postanalysis aid for the radiologist to verify the relevance of the results with the display of the analysed images.
The sensitivity and specificity of liver iron concentration measurements.

Conclusion

The 510(k) premarket notification for FerriSmart contains adequate information and data to enable the FDA-CDRH to determine substantial equivalence to the predicate device. Differences have been explained and justified, and where necessary, additional data has been presented to support the claims. Resonance Health Analysis Services Pty Ltd believes that sufficient evidence has been presented in this Dossier to conclude that FerriSmart is safe, effective and performs as well as the predicate.

Regulation Number and Section

§ 892.1001 Liver iron concentration imaging companion diagnostic for deferasirox.

(a)
Identification. The liver iron concentration imaging companion diagnostic for deferasirox is an image processing device intended to aid in the identification and monitoring of non-transfusion-dependent thalassemia patients receiving therapy with deferasirox. The device calculates a numeric value for liver iron concentration based on magnetic resonance images acquired under controlled conditions. The calculated numeric value is used to assess the need for deferasirox treatment and for monitoring treatment in patients with non-transfusion-dependent thalassemia. The liver iron concentration imaging companion diagnostic for deferasirox is essential to the safe and effective use of deferasirox in patients with non-transfusion-dependent thalassemia.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include nonclinical and clinical performance testing demonstrating the bias, precision, repeatability, and reproducibility of liver iron concentration measurements.
(2) Labeling must include specifying:
(i) Instructions for acceptance testing of images prior to processing;
(ii) Data processing quality assurance protocols; and
(iii) The sensitivity and specificity of liver iron concentration measurements.