K Number
K222755
Device Name
uMR 680
Date Cleared
2023-02-16

(157 days)

Product Code
Regulation Number
892.1000
Reference & Predicate Devices
Predicate For
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The uMR 680 system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces sagittal, transverse, coronal, and oblique cross sectional images, and that display internal anatomical structure and/or function of the head, body and extremities. These images and the physical parameters derived from the images when interpreted by a trained physician yield information that may assist the diagnosis. Contrast agents may be used depending on the region of interest of the scan.

Device Description

The uMR 680 is a 1.5T superconducting magnetic resonance diagnostic device with a 70cm size patient bore. It consists of components such as magnet, RF power amplifier, RF coils, gradient power amplifier, gradient coils, patient table, spectrometer, computer, equipment cabinets, power distribution system, internal communication system, and vital signal module etc. The uMR 680 Magnetic Resonance Diagnostic Device is designed to conform to NEMA and DICOM standards.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the DeepRecon algorithm found in the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance (DeepRecon)

Evaluation ItemAcceptance CriteriaReported Device Performance (Test Result)Results
Image SNRDeepRecon images achieve higher SNR compared to the images without DeepRecon (NADR)NADR: 137.03; DeepRecon: 186.87PASS
Image UniformityUniformity difference between DeepRecon images and NADR images under 5%0.03%PASS
Image ResolutionDeepRecon images achieve 10% or higher resolution compared to the NADR images15.57%PASS
Image ContrastIntensity difference between DeepRecon images and NADR images under 5%1.0%PASS
Structure MeasurementMeasurements on NADR and DeepRecon images of same structures, measurement difference under 5%0%PASS

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

  • Sample Size for Test Set: 68 US subjects.
  • Data Provenance: The test data was collected from various clinical sites in the US during separate time periods and on subjects different from the training data. The data specifically indicates demographic distributions for US subjects across various genders, age groups, ethnicities, and BMI groups.

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

The document mentions that "DeepRecon images were evaluated by American Board of Radiologists certificated physicians." It does not specify the exact number of experts used, nor does it provide details on their years of experience as an example. However, it does state their qualification: American Board of Radiologists certificated physicians.

4. Adjudication Method for the Test Set

The document does not explicitly state the adjudication method (e.g., 2+1, 3+1, none) used for the expert evaluation of the test set. It only mentions that "The evaluation reports from radiologists verified that DeepRecon meets the requirements of clinical diagnosis. All DeepRecon images were rated with equivalent or higher scores in terms of diagnosis quality." This suggests a qualitative review, but the specific consensus method is not detailed.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly described in the provided text in terms of quantifying human reader improvement with AI assistance. The expert evaluation focused on whether DeepRecon images met clinical diagnosis requirements and were rated equivalent or higher in quality, rather than measuring a specific effect size of AI assistance on human reader performance.

6. Standalone (Algorithm Only) Performance

Yes, a standalone (algorithm only) performance evaluation was done. The "Acceptance Criteria and Reported Device Performance" table directly shows the performance metrics (Image SNR, Uniformity, Resolution, Contrast, Structure Measurement) of the DeepRecon algorithm itself, compared to images without DeepRecon (NADR). This indicates a standalone assessment of the algorithm's output characteristics.

7. Type of Ground Truth Used for the Test Set

For the quantitative metrics (SNR, uniformity, resolution, contrast, structure measurement), the "ground truth" for comparison appears to be images without DeepRecon (NADR) as a baseline, or potentially direct measurements on those images.

For the qualitative assessment by radiologists, the ground truth was expert opinion/consensus by American Board of Radiologists certificated physicians regarding clinical diagnosis quality.

8. Sample Size for the Training Set

The training set for DeepRecon consisted of data from 264 volunteers. This resulted in a total of 165,837 cases.

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

For the training dataset, the ground truth was established by collecting multiple-averaged images with high-resolution and high SNR. These high-quality images were used as the reference against which the input images (generated by sequentially reducing the SNR and resolution of the ground-truth images) were trained. All data included for training underwent manual quality control.

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

Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

February 16, 2023

Shanghai United Imaging Intelligence Co., Ltd. % Xin GAO Regulatory Affairs Specialist No. 2258 Chengbei Road, Jiading District Shanghai, Shanghai 201807 CHINA

Re: K222755

Trade/Device Name: uMR 680 Regulation Number: 21 CFR 892.1000 Regulation Name: Magnetic resonance diagnostic device Regulatory Class: Class II Product Code: LNH Dated: January 11, 2023 Received: January 17, 2023

Dear Xin GAO:

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

{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,

Daniel M. Krainak, Ph.D. Assistant Director Magnetic Resonance and Nuclear Medicine Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known) K222755

Device Name uMR 680

Indications for Use (Describe)

The uMR 680 system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces sagittal, transverse, coronal, and oblique cross sectional images, and that display internal anatomical structure and/or function of the head, body and extremities. These images and the physical parameters derived from the images when interpreted by a trained physician yield information that may assist the diagnosis. Contrast agents may be used depending on the region of interest of the scan.

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/1 description: The image contains the logo for United Imaging. The logo consists of the words "UNITED IMAGING" stacked on top of each other in a bold, sans-serif font. To the right of the text is a stylized "U" symbol, which is also in a bold, sans-serif font. The color of the logo is a dark teal.

510 (k) SUMMARY

K222755

    1. Date Prepared [21 CFR 807.92(a)(1)]
      February 15, 2023

2. General Information [21 CFR 807.92(a)(1)]

Manufacturer:Shanghai United Imaging Healthcare Co., Ltd
2258 Chengbei Rd., Jiading District, Shanghai, 201807

Xin GAO Contact Person: Regulatory Affairs Specialist Tel: +86 (21) 67076888-5386 Fax: +86-021-67076889 Email: xin.gao@united-imaging.com

3. Trade Name, Common Name, Classification [21 CFR 807.92(a)(2)]

Trade Name:uMR 680
Common Name:Magnetic Resonance Diagnostic Device
Model:uMR 680
Product Code:LNH
Regulation Number:892.1000
Device Class:II

4. Identification of Predicate Devices(s) [21 CFR 807.92(a)(3)]

The identification of predicates device within this submission is as follow:

Predicate Device Manufacturer: Shanghai United Imaging Healthcare Co., Ltd Magnetic Resonance Diagnostic Device Device Name: Product Code: LNH Device Class: II Regulation Number: 21 CFR 892.1000 FDA 510 (k) #: K201540

5. Device Description [21 CFR 807.92(a)(4)]

The uMR 680 is a 1.5T superconducting magnetic resonance diagnostic device with a 70cm size patient bore. It consists of components such as magnet, RF power amplifier, RF coils, gradient power amplifier, gradient coils, patient table,

Page 1 of 11

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

Image /page/4/Picture/1 description: The image contains the logo for United Imaging. The logo consists of the words "UNITED IMAGING" stacked on top of each other in a bold, sans-serif font. To the right of the text is a stylized symbol that resembles the letter "U" with a horizontal line through the middle. The color of the logo is a dark teal or gray.

spectrometer, computer, equipment cabinets, power distribution system, internal communication system, and vital signal module etc. The uMR 680 Magnetic Resonance Diagnostic Device is designed to conform to NEMA and DICOM standards.

6. Intended Use [21 CFR 807.92(a)(5)]

The uMR 680 system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces sagittal, transverse, coronal, and oblique cross sectional imag es, and spectroscopic images, and that display internal anatomical structure and/or fu nction of the head, body and extremities.

These images and the physical parameters derived from the images when interpreted by a trained physician vield information that may assist the diagnosis. Contrast agen ts may be used depending on the region of interest of the scan.

7. Technological Characteristic [21 CFR 807.92(a)(6)]

The differences from the predicate device are discussed in the comparison table in this submission as below.

ITEMThis submissionuMR 680Predicate DeviceuMR 570Remark
General
Product CodeLNHLNHSame
RegulationNo.21 CFR 892.100021 CFR 892.1000Same
ClassIIIISame
IndicationsFor UseThe uMR 680 system is indicatedfor use as a magnetic resonancediagnostic device (MRDD) thatproduces sagittal, transverse,coronal, and oblique crosssectional images, andspectroscopic images, and thatdisplay internal anatomicalstructure and/or function of thehead, body and extremities.These images and the physicalparameters derived from theimages when interpreted by atrained physician yieldinformation that may assist thediagnosis. Contrast agents may beused depending on the region ofinterest of the scan.The uMR 570 system is indicatedfor use as a magnetic resonancediagnostic device (MRDD) thatproduces sagittal, transverse,coronal, and oblique crosssectional images, andspectroscopic images, and thatdisplay internal anatomicalstructure and/or function of thehead, body and extremities.These images and the physicalparameters derived from theimages when interpreted by atrained physician yieldinformation that may assist thediagnosis. Contrast agents may beused depending on the region ofinterest of the scan.Same
Magnet system
Field Strength1.5 Tesla1.5 TeslaSame
ITEMThis submissionuMR 680Predicate DeviceuMR 570Remark
Type ofMagnetSuperconductingSuperconductingSame
Patient-accessibleboredimensions70cm70cmSame
Type ofShieldingActively shielded, OIStechnologyActively shielded, OIStechnologySame
MagnetHomogeneity1.40ppm @ 50cm DSV0.90ppm @ 45cm DSV0.45ppm @ 40cm DSV0.190ppm @ 30cm DSV0.120ppm @ 20cm DSV0.040ppm @ 10cm DSV1.40ppm @ 50cm DSV0.90ppm @ 45cm DSV0.72ppm @ 40cm DSV0.420ppm @ 30cm DSV0.240ppm @ 20cm DSV0.040ppm @ 10cm DSVNote 1
Max gradientamplitude45mT/m45mT/mSame
Max slew rate200T/m/s200T/m/sSame
ShieldingactiveactiveSame
CoolingwaterwaterSame
Resonantfrequencies63.87 MHz63.87 MHzSame
Number oftransmitchannels11Same
Number ofreceivechannelsUp to 96Up to 48Note 2
Amplifierpeak powerper channel18 kW20 kWNote 3
Head & NeckCoil -16NoYesNote 4
Head & NeckCoil -24YesNoNote 5
Spine Coil -24NoYesNote 6
Spine Coil -32YesNoNote 7
Body ArrayCoil - 6NoYesNote 8
Body ArrayCoil - 12YesYesSame
Body ArrayCoil - 24YesNoNote 8
ITEMThis submissionuMR 680Predicate DeviceuMR 570Remark
Breast Coil -10YesYesSame
Knee Coil -12YesYesSame
LowerExtremityCoil - 24YesYesSame
Shoulder Coil- 12YesYesSame
Small LoopCoilYesYesSame
Wrist Coil -12YesYesSame
Cardiac Coil -24YesYesSame
Foot & AnkleCoil - 24YesYesSame
Temporomandibular JointCoil - 4YesYesSame
Head Coil -24NoYesNote 9
Head Coil -12NoYesNote 9
Carotid Coil -8YesYesSame
Flex CoilLarge - 4NoYesNote 10
Flex CoilLarge - 8YesNoNote 10
Flex CoilSmall - 4NoYesNote 11
Flex CoilSmall - 8YesNoNote 11
Infant Coil-24YesNoNote 12
SuperFlexLarge - 12YesNoNote 13
SuperFlexSmall - 12YesNoNote 14
SuperFlexBody - 24YesNoNote 15
Patient tablePatient Table:250 kgDockable Patient Table:310kgPatient Table:250 kgNo
Maximumsupportedpatient weightSameNote 16
ITEMThis submissionuMR 680Predicate DeviceuMR 570Remark
Vital SignalGatingSupportECG/Respiratory/Pulse signal triggering the scanSupportECG/Respiratory/Pulse signal triggering the scanSame

Table 1 Comparison of Hardware configuration

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

Image /page/5/Picture/1 description: The image shows the logo for United Imaging. The logo consists of the words "UNITED IMAGING" in bold, sans-serif font, stacked on top of each other. To the right of the text is a stylized "U" shape, formed by two vertical lines connected by a horizontal line at the top, with a curved bottom.

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

Image /page/6/Picture/1 description: The image contains the logo for United Imaging. The logo consists of the words "UNITED IMAGING" in bold, sans-serif font, stacked on top of each other. To the right of the text is a stylized "U" shape, also in a bold font, with a white line running vertically and horizontally through the center of the "U".

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

Image /page/7/Picture/1 description: The image contains the logo for United Imaging. The logo consists of the words "UNITED IMAGING" in bold, sans-serif font, stacked on top of each other. To the right of the text is a stylized "U" shape, which is formed by two vertical lines connected by a horizontal line in the middle. The logo is simple and modern in design.

Note 1The homogeneity of the magnet is equal or better at typical DSVs thus the clinicalscanning of the proposed device is not limited compared to the predicate device.
Note 2More receive channels allow the proposed device to use new high-channel count andbigger coverage receive coils.
Note 3The RF Amplifier power is just one of the influence factors to affect the B1 field,other influence factors such as efficiency of transmitting coil, damping oftransmitting chain, the distance between coil and target location will also affect theintensity of B1 field, and the intensity of B1 field can be adjusted by differentsequences. Generally the target B1 field is achieved by system calibrationprocedures and the required RF power is always less than the maximum RFAmplifier power output, so this difference from predicate device will not affect thesystem effectiveness, and the system safety is explained in device description andverified by the third party safety report.
Note 4Compared to the predicate device, the proposed device removes Head & Neck Coil -16 but adds Head & Neck Coil -24. The intended use of Head & Neck Coil -24 isequivalent to previously cleared Head & Neck Coil -16. More coil elements in thenew coil allow larger coverage for bigger patient.
Note 5The intended use of Head & Neck Coil -24 is equivalent to previously cleared Head& Neck Coil -16. More coil elements in the new coil allow larger coverage forbigger patient.
Note 6Compared to the predicate device, the proposed device removes Spine Coil - 24 butadds Spine Coil - 32. The intended use of Spine Coil - 32 is equivalent to previouslycleared Spine Coil - 24. More coil elements in the new coil allow larger coverage forbigger patient.
Note 7The intended use of Spine Coil - 32 is equivalent to previously cleared Spine Coil -24. More coil elements in the new coil allow larger coverage for bigger patient.
Note 8Compared to the predicate device, the proposed device removes Body Array Coil-6but adds Body Array Coil-24. The intended use of Body Array Coil-24 is equivalentto previously cleared Body Array Coil-6. More coil elements in the new coil allowlarger coverage for bigger patient.
Note 9Compared to the predicate device, the proposed device removes Head Coil – 12 andHead Coil - 24. The intended use of Head Coil can be overridden by Head & NeckCoil -24, so this difference from predicate device will not affect the systemeffectiveness.
Note 10Compared to the predicate device, the proposed device removes Flex Coil Large - 4but adds Flex Coil Large - 8. The intended use of Flex Coil Large - 8 is equivalent topreviously cleared Flex Coil Large - 4. More coil elements in the new coil allowlarger coverage for bigger patient.
Note 11Compared to the predicate device, the proposed device removes Flex Coil Small - 4but adds Flex Coil Small - 8. The intended use of Flex Coil Small - 8 is equivalent topreviously cleared Flex Coil Small - 4. More coil elements in the new coil allowlarger coverage for bigger patient.
Note 12The proposed device adds Infant Coil-24 to facilitate the exam of infant.
Note 13The intended use of SuperFlex Large - 12 is essentially identical to previouslycleared Flex Coil Large - 8. The differences are the number of channels of the coil

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

Image /page/8/Picture/1 description: The image contains the logo for United Imaging. The text "UNITED IMAGING" is displayed in bold, sans-serif font, stacked vertically. To the right of the text is a stylized "U" symbol, which is dark teal in color. The symbol is composed of a vertical line that extends from the top to the bottom, with a horizontal line at the top, and a curved base.

and the material used on the surface of the coil. More coil elements in the new coil
can better cover the scanning parts and the flexible material is beneficial to wrap the
scanning parts.
Note 14The intended use of SuperFlex Small - 12 is essentially identical to previously
cleared Flex Coil Small - 8. The differences are the number of channels of the coil
and the material used on the surface of the coil. More coil elements in the new coil
can better cover the scanning parts and the flexible material is beneficial to wrap the
scanning parts.
Note 15The intended use of SuperFlex Body - 24 is essentially identical to previously
cleared Body Array Coil - 12. The differences are the number of channels of the coil
and the material used on the surface of the coil. More coil elements in the new coil
can better cover the scanning parts and the flexible material is beneficial to wrap the
scanning parts.
Note 16The proposed device adds Dockable Patient Table to facilitate patient transfer and
have a higher load capacity.

Table 2 provides the new application software features of the proposed device in comparison to the predicate device.

ITEMThissubmissionuMR 680PredicateDeviceuMR 570Remark
Imaging Features
Non-uniformityCorrectionYesYesNon-uniformity correction is used forcorrecting image intensity non-uniformity caused by transmit field orreceive field.
Distortion CorrectionYesYesDistortion correction is used forcorrecting the distortion caused by thenon-linear gradient field in imagedomain.
Image FilterYesYesImage filter is used for denoising,enhancement and edge smoothness.
WFIYesYesWFI is short for water fat imaging andseparates water and fat signal accordingto chemical shift effect.
SWIYesYesSusceptibility Weighted Imaging (SWI)uses high-pass filter to generate localphase map, then it is multiplied onto themagnitude data to generate SWI image.
PCYesYesPC combines two images with flowencoding and without flow encoding toachieve angiography imaging.
GETIYesYesGETI is short for gradient echo trainimaging. It combines multi-echo imagesby sum-of-square to generate hybridT2* contrast.
ADCYesYesApparent diffusion coefficient (ADC)fits logarithm-linear least squares modelto represent water molecular diffusionmotion by DWI technique.
FACTYesYesFACT is short for fat analysis andcalculation technique and substantiallyequivalent to WFI. It not only separateswater and fat signal and quantifies fatfraction and R2* mapping according tochemical shift effect and T2* effect.
PSIRYesYesPSIR is substantially equivalent to FFTreconstruction and acquire real imagefrom two TI(time-inversion) imageswhich is benefit for more stablecontrast.
cDWIYesYescDWI is substantially equivalent toDWI and generates fitting b-value frommultiple acquisition b values.
Inline T1/T2* MapYesYesInline T1/T2* Map is substantiallyequivalent to T1/T2* Map processed bypost-processing module. The map resultdisplays inline without extra operationby post-processing module.
Inline T2 MapYesNoInline T2 Map is substantiallyequivalent to T2 Map processed bypost-processing module. The map resultdisplays inline without extra operationby post-processing module.
SWI+YesYesSWI+ is substantially equivalent to SWIand acquires multi-echo to achieve moreinformation than SWI.
Arterial SpinLabeling (ASL)YesYesASL is substantially equivalent to FSEand uses extra arterial spin labelingpreparation and imaging processing forcerebral blood flow (CBF) imagingwithout contrast agent.
Flow Quantification(FQ)YesNoFQ is substantially equivalent to GREand uses extra flow encoding andimaging processing for flowquantification.
Cardiac T1 MappingYesNoCardiac T1 mapping is substantiallyequivalent to GRE and uses multiple TIacquisitions with IR preparation andimaging processing for cardiac T1mapping.
Cardiac T2 MappingYesNoCardiac T2 mapping is substantiallyequivalent to GRE and uses multipleT2-prep duration preparationacquisitions and imaging processing forcardiac T2 mapping.
Cardiac T2*MappingYesNoCardiac T2* mapping is substantiallyequivalent to GRE and uses multiple TEacquisitions and imaging processing forcardiac T2* mapping.
DeepReconYesNoDeepRecon is a deep-learning basedimage processing algorithm for image
YesNode-noising and K-space-interpolationbased image super-resolution.
QScanQScan is short for quiet scan. It doesn'tchange the sequence mechanism andonly optimizes gradient waveform toreduce MR scan acoustic noise.
Workflow Features
EasyScanYesNoEasyScan feature allows automatic slicepositioning for Head, cardiac, c-spine, t-spine, l-spine, shoulder, abdomen andknee imaging. The positioning can alsobe adjusted manually by user. The finalpositioning effect is equivalent tomanual operation without EasyScanfeature.
Function
Remote AssistanceYesNoRemote Assistance intends for remotesupport and service.
MR conditionalimplant modeYesNoIn MR conditional implant mode, usercan set the safety conditions of the MRconditional implant, and uMR 680system ensure the scanning complieswith the conditions.
Spectroscopy Sequences
Liver SpectroscopyYesNoLiver spectroscopy is substantiallyequivalent to Spectroscopy and usesmulti-echo acquisition and post-processing instead of single echo for fatquantification of liver.
ProstateSpectroscopyYesNoProstate spectroscopy is substantiallyequivalent to Spectroscopy and usescharacteristic metabolites detection postprocessing for prostate spectroscopy.
Breast SpectroscopyYesNoBreast spectroscopy is substantiallyequivalent to Spectroscopy and usescharacteristic metabolites detection postprocessing for breast spectroscopy.

Table 2 Comparison of the new Application Software Features

Page 6 of 11

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

Image /page/9/Picture/1 description: The image contains the logo for United Imaging. The text "UNITED IMAGING" is displayed in bold, sans-serif font. To the right of the text is a stylized "U" shape, which is bisected by a vertical white line. The logo is simple and modern in design.

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

Image /page/10/Picture/1 description: The image contains the logo for United Imaging. The logo consists of the words "UNITED IMAGING" in bold, sans-serif font, stacked on top of each other. To the right of the text is a stylized symbol that resembles a shield or a letter "U" with a vertical line running through the center. The color of the text and the symbol is a dark teal or blue-gray.

8. Substantial Equivalence [21 CFR 807.92(b)(1) and 807.92(b)(2)]

Summary of Non-Clinical Tests:

The following testing was conducted on the uMR 680 Magnetic Resonance Diagnostic Device as the predicate device:

  • A ES60601-1:2005/(R)2012, Medical Electrical Equipment - Part 1: General Requirements For Basic Safety And Essential Performance
  • A IEC 60601-1-2 Edition 4.0 2014-02, Medical Electrical Equipment - Part 1-2: General Requirements For Basic Safety And Essential Performance - Collateral Standard: Electromagnetic Disturbances - Requirements And Tests
  • 60601-2-33 Ed. 3.2:2015 Medical Electrical Equipment - Part 2-33: Particular

Page 8 of 11

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

Image /page/11/Picture/1 description: The image contains the logo for United Imaging. The text "UNITED IMAGING" is displayed in a bold, sans-serif font, stacked on two lines. To the right of the text is a stylized, geometric shape that resembles the letter "U" with a horizontal line across the top, creating a negative space in the shape of an "I".

Requirements For The Basic Safety And Essential Performance Of Magnetic Resonance Equipment For Medical Diagnostic

  • A IEC 60825-1 Edition 2.0 2007-03, Safety Of Laser Products - Part 1: Equipment Classification, And Requirements [Including: Technical Corrigendum 1 (2008), Interpretation Sheet 1 (2007), Interpretation Sheet 2 (2007)]
  • A ISO 10993-5 Third Edition 2009-06-01, Biological Evaluation Of Medical Devices - Part 5: Tests For In Vitro Cytotoxicity
  • A ISO 10993-10 Third Edition 2010-08-01, Biological Evaluation Of Medical Devices - Part 10: Tests For Irritation And Skin Sensitization
  • IEC 62464-1 Edition 2.0: 2018-12, Magnetic resonance equipment for medical imaging Part 1: Determination of essential image quality parameters.

  • A MS 1-2008(R2020), Determination of Signal-to-Noise Ratio (SNR) in Diagnostic Magnetic Resonance Images
  • MS 2-2008(R2020), Determination of Two-Dimensional Geometric Distortion in A Diagnostic Magnetic Resonance Images
  • A MS 3-2008(R2020). Determination of Image Uniformity in Diagnostic Magnetic Resonance Images
  • A MS 4-2010, Acoustic Noise Measurement Procedure for Diagnosing Magnetic Resonance Imaging Devices
  • MS 5-2018, Determination of Slice Thickness in Diagnostic Magnetic A Resonance Imaging
  • MS 6-2008(R2014), Determination of Signal-to-Noise Ratio and Image Uniformity for Single-Channel Non-Volume Coils in Diagnostic MR Imaging

  • A MS 8-2016, Characterization Of The Specific Absorption Rate For Magnetic Resonance Imaging Systems
  • A MS 9-2008(R2020), Standards Publication Characterization of Phased Array Coils for Diagnostic Magnetic Resonance Images
  • A MS 14-2019, Characterization of Radiofrequency (RF) Coil Heating in Magnetic Resonance Imaging Systems

Summary of Clinical Tests:

  • Sample clinical images were provided to support the ability of uMR 680 to A generate diagnostic quality images in accordance with the MR guidance on premarket notification submissions.

Summary of the Machine Learning Algorithm (DeepRecon):

DeepRecon is a deep-learning based image processing algorithm for image de-noising and K-space-interpolation based image super-resolution.

The training data of DeepRecon were collected from 264 volunteers. Each subject was scanned by UIH MRI systems for multiple body parts and clinical protocols, resulted in a total of 165.837 cases. In terms of the ground truth and input images in training dataset, the multiple-averaged images with high-resolution and high SNR were collected as the ground-truth images. The input images were generated from the

Page 9 of 11

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

Image /page/12/Picture/1 description: The image contains the logo for United Imaging. The logo consists of the words "UNITED IMAGING" stacked on top of each other in a bold, sans-serif font. To the right of the text is a stylized "U" symbol, which is dark blue and has a white vertical line running through the center.

ground-truth images by sequentially reducing the SNR and resolution of the groundtruth images. All data were manually quality controlled before included for training.

The DeepRecon has undergone performance testing on 68 US subjects with diverse demographic distributions covering various genders, age groups, ethnicities, and BMI groups (Table a).

Subjects' CharacteristicsTotal(N=68)
Gender
Male24
Female44
Age
18-2911
30-4414
45-6424
>=6519
Ethnicity
White26
Black17
Asian19
Hispanic (of any race)6
Body Mass Index (BMI)
Underweight (<18.5)2
Healthy weight (18.5-24.9)17
Overweight (25.0-29.9)25
Class1 Obesity (30.0-34.9)14
Class2 Obesity (35-39.9)5
Class3 Obesity (>=40)5

Table a. DeepRecon American Volunteers' Demographic Distribution

The independence of testing datasets were ensured by collecting testing data from various clinical sites and during separated time periods and on subjects different from the training data. Thus, the testing data have no overlap with the training data and are completely independent. The acceptance criteria for performance testing and the corresponding testing results can be found in Table b.

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

Image /page/13/Picture/1 description: The image shows the logo for United Imaging. The words "UNITED" and "IMAGING" are stacked on top of each other and are in a bold, sans-serif font. To the right of the words is a stylized "U" shape that is dark gray. The logo is simple and modern.

EvaluationItemAcceptance CriteriaTest ResultResults
Image SNRDeepRecon images achieve higherSNR compared to the imageswithout DeepRecon (NADR)NADR: 137.03DeepRecon:186.87PASS
ImageUniformityUniformity difference betweenDeepRecon images and NADRimages under 5%0.03%PASS
ImageResolutionDeepRecon images achieve 10% orhigher resolution compared to theNADR images15.57%PASS
ImageContrastIntensity difference betweenDeepRecon images and NADRimages under 5%1.0%PASS
StructureMeasurementMeasurements on NADR andDeepRecon images of samestructures, measurement differenceunder 5%0%PASS
Table b. The performance evaluation report criteria of DeepRecon

The DeepRecon has been validated to provide image de-nosing and super-resolution processing using various ethnicities, age groups, BMIs, and pathological variations. In addition, DeepRecon images were evaluated by American Board of Radiologists certificated physicians, covering a range of protocols and body parts. The evaluation reports from radiologists verified that DeepRecon meets the requirements of clinical diagnosis. All DeepRecon images were rated with equivalent or higher scores in terms of diagnosis quality.

The test results demonstrated that the device performs as expected and thus, it is substantially equivalent to the predicate devices to which it has been compared.

9. Conclusion [21 CFR 807.92(b)(3)]

In accordance with the Federal Food, Drug and Cosmetic Act, 21 CFR Part 807 and based on the information provided in this premarket notification, we concludes that uMR 680 Magnetic Resonance Diagnostic Device is substantially equivalent to the predicate device. It does not introduce new indications for use, and has the same technological characteristics and does not introduce new potential hazards or safety risks.

§ 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.