HYPER DLR is an image processing function intended to be used by radiologists and nuclear medicine physicians to reduce noise of the fluorodeoxyglucose (FDG) PET images.

Device Description

HYPER DLR is a software-only device. HYPER DLR is intended to be implemented on previously cleared PET/CT devices uMI 550 (K182237) and uMI 780 (K172143). HYPER DLR serves as an alternative to the existing image smoothing options that are available on the predicate devices. HYPER DLR is an image post-processing technique which uses a pre-trained neural network to predict low noise PET image from high noise PET image. After training, the network could extract the noise component from the image, thus reducing the image noise.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study information for the HYPER DLR device, based on the provided FDA 510(k) summary:

Acceptance Criteria and Reported Device Performance

The document describes the device performance in qualitative terms and through common quantitative metrics, but does not provide a specific table of numerical acceptance criteria with corresponding performance values for clinical image evaluation. The acceptance for clinical evaluation is described as:

Acceptance Criterion (Clinical)	Reported Device Performance (Qualitative)
Image Noise	HYPER DLR performed lower image noise than Gaussian filtering. Under all evaluated scan times, HYPER DLR produces lower or equivalent image noise.
Overall Image Quality	The image quality was sufficient for clinical diagnosis. Under all evaluated scan times, HYPER DLR produces better or equivalent image quality.
Diagnostic Quality	All HYPER DLR images are of diagnostic quality.

For non-clinical (bench) testing, the document states: "Bench test showed overall image quality improvement based on the commonly used quantitative metrics. HYPER DLR can significantly improve SNR and CNR while preserving image consistency." The specific acceptance values for "significant improvement" are not detailed in this summary. The quantitative metrics evaluated include:

Peak signal to noise ratio
Structural similarity index
Pearson correlation coefficient
Signal to noise ratio (SNR)
Contrast to noise ratio (CNR)
Normalized root mean square error
Bland-Altman plot of body & brain VOI SUVmean values

Study Details

Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not explicitly stated as a number of cases or images. The document mentions "clinical image evaluation were performed for typical clinical scan times of uMI 550 and uMI 780 systems." This implies a set of clinical images, but the exact count is not provided.
- Data Provenance: Not explicitly stated. The manufacturer is Shanghai United Imaging Healthcare Co., Ltd. in China, so it's plausible the data originates from studies conducted there or affiliated sites. The document does not specify if the data was retrospective or prospective.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not explicitly stated as a specific number. The document mentions "Each image was read by board-certified nuclear medicine physicians." It implies multiple physicians but doesn't specify how many.
- Qualifications: Board-certified nuclear medicine physicians.
Adjudication method for the test set:
- The document does not explicitly describe an adjudication method for disagreements among the physicians. It states that physicians "provided an assessment," implying individual assessments that were then analyzed.
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:
- A multi-reader, multi-case study was done for clinical image evaluation, comparing HYPER DLR images with Gaussian filtered images. However, this study appears to be a standalone reader study comparing two different image processing methods, not an AI-assisted vs. non-AI-assisted human reader study. Therefore, no effect size for human reader improvement with AI assistance is reported because the study design was different. The physicians were evaluating images generated by the AI algorithm (HYPER DLR) versus images generated by conventional post-smoothing (Gaussian filtering).
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, the "Bench test" section describes standalone algorithm performance evaluation using quantitative metrics like SNR, CNR, etc. This solely assesses the algorithm's output characteristics without human interpretation.
The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- For the clinical image evaluation, the ground truth was based on the "assessment of both image noise and overall image quality" by board-certified nuclear medicine physicians. This could be interpreted as a form of expert consensus or expert opinion on image characteristics rather than a definitive "true positive/negative" ground truth for disease detection, as the device's purpose is noise reduction and image quality improvement.
- For the bench testing, the ground truth for quantitative metrics would typically be derived from the inherent properties of the phantoms/datasets used for those measurements (e.g., known signal levels, known noise levels).
The sample size for the training set:
- Not explicitly stated. The document mentions that HYPER DLR "uses a pre-trained neural network," but the size of the dataset used for this training is not disclosed in this summary.
How the ground truth for the training set was established:
- Not explicitly stated in this summary. For deep learning noise reduction, the training process often involves pairs of 'noisy' and 'clean' images, where the 'clean' image serves as the ground truth for the noise reduction task. These 'clean' images might be generated from higher dose acquisitions or simulated to represent noise-free data.

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 is in blue and includes the letters "FDA" followed by the words "U.S. Food & Drug Administration".

Shanghai United Imaging Healthcare Co., Ltd. % Shumei Wang QM & RA VP No. 2258 Chengbei Road, Jiading Industrial District Shanghai, Shanghai 201807 CHINA

August 4, 2020

Re: K193210

Trade/Device Name: HYPER DLR Regulation Number: 21 CFR 892.1200 Regulation Name: Emission computed tomography system Regulatory Class: Class II Product Code: KPS Dated: June 24, 2020 Received: June 29, 2020

Dear Shumei Wang:

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 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for

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

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 (QS) 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) K193210

Device Name HYPER DLR

Indications for Use (Describe)

HYPER DLR is an image processing function intended to be used by radiologists and nuclear medicine physicians to reduce noise of the fluorodeoxyglucose (FDG) PET images.

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}------------------------------------------------

Image /page/3/Picture/1 description: The image contains the logo for United Imaging. The logo consists of the words "UNITED" and "IMAGING" stacked on top of each other in a bold, sans-serif font. To the right of the text is a stylized "U" shape, which is dark gray. The logo is simple and modern in design.

510 (k) SUMMARY

K193210

1. Date of Preparation June 24, 2020

2. Sponsor Identification

Shanghai United Imaging Healthcare Co.,Ltd.

No.2258 Chengbei Rd. Jiading District, 201807, Shanghai, China

Contact Person: Shumei Wang Position: QM&RA VP Tel: +86-021-67076888-6776 Fax: +86-021-67076889 Email: shumei.wang(@united-imaging.com

3. Identification of Proposed Device

Trade Name: HYPER DLR Common Name: Emission Computed Tomography System Model(s): HYPER DLR

Regulatory Information Regulation Number: 21 CFR 892.1200 Regulation Name: Emission Computed Tomography System Regulatory Class: II Product Code: KPS Review Panel: Radiology

4. Identification of Predicate Device(s)

Predicate Device 1:

510(k) Number: K172143 Device Name: Emission Computed Tomography System Model(s): uMI 780

Regulatory Information Regulation Number: 21 CFR 892.1200 Regulation Name: Emission Computed Tomography System Regulatory Class: II Product Code: KPS, JAK Review Panel: Radiology

Predicate Device 2:

510(k) Number: K182237 Device Name: Emission Computed Tomography System Model(s): uMI 550

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

Image /page/4/Picture/1 description: The image shows the logo for United Imaging. The words "UNITED IMAGING" are stacked on top of each other in a bold, sans-serif font. To the right of the words is a stylized "U" shape, which is also in a bold font. The logo is simple and modern, and the colors are muted.

Regulatory Information Regulation Number: 21 CFR 892.1200 Regulation Name: Emission Computed Tomography System Regulatory Class: II Product Code: KPS, JAK Review Panel: Radiology

ડ. Device Description:

6. Indications for Use

HYPER DLR is an image processing function intended to be used by radiologists and nuclear medicine physicians to reduce noise of the fluorodeoxyglucose (FDG) PET images.

Comparison of Technological Characteristics with the Predicate Devices 7.

A comparison between the technological characteristics of proposed and predicate devices is provided as below.

ITEM	Predicate Device 1uMI 780 (K172143)including a post-smoothing functionfor PET imagereconstruction	Predicate Device 2uMI 550 (K182237)including a post-smoothing functionfor PET imagereconstruction	Proposed DeviceHYPER DLR	NOTE
Image Processing Location	Onsite on the facility PET/CT reconstruction computer.	Onsite on the facility PET/CT reconstruction computer.	Onsite on the facility PET/CT reconstruction computer.	Same
Operating system	Windows	Windows	Windows	Same
Workflow	Support online & offline	Support online & offline	Support online & offline	Same
Protocols	Standard scanner protocols	Standard scanner protocols	Standard scanner protocols	Same
Algorithm description	The post-smoothing function uses Gaussian filtering to reduce the noise in	The post-smoothing function uses Gaussian filtering to reduce the noise in	The software employs a convolutional neural network	Gaussian filtering suppresses the high frequency

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

Image /page/5/Picture/1 description: The image shows the logo for United Imaging. The words "UNITED IMAGING" are in bold, sans-serif font, stacked on top of each other. To the right of the words is a stylized "U" symbol, which is also in bold. The color of the text and symbol is a dark teal.

the PET images. The	the PET images. The	based method to	component of
Gaussian filteringworks by using the3D Gaussiandistribution as apoint-spreadfunction. And thefiltering process isachieved byconvolving theGaussian filter withthe reconstructedPET image.	Gaussian filteringworks by using the3D Gaussiandistribution as apoint-spreadfunction. And thefiltering process isachieved byconvolving theGaussian filter withthe reconstructedPET image.	re-generate thevalue for eachpixel. Thenetwork extractsthe noisecomponent fromthe image, whileretains the otherusefulcomponents suchas image details.	the image,which includesnoise and imagedetails. On thecontrary,convolutionalneural networkis able todistinguish thenoisecomponent andthe imagedetails, and onlyremoves thenoisecomponent fromthe image.

HYPER DLR utilizes the same hardware with the predicate devices and does not introduce any new restrictions on use. The differences do not affect the safety and the effectiveness.

Performance Data 8.

Non-Clinical Testing

Non-clinical testing including image performance tests and clinical image evaluation were conducted for the HYPER DLR during the product development. UNITED IMAGING HEALTHCARE claims conformance to the following standards and guidance:

Software

NEMA PS 3.1-3.20(2011): Digital Imaging and Communications in Medicine A (DICOM)
IEC 62304: Medical Device Software - software life cycle process
A Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices
Content of Premarket Submissions for Management of Cybersecurity in Medical Devices

Other Standards and Guidance

A ISO 14971: Medical Devices - Application of risk management to medical devices
Code of Federal Regulations, Title 21, Part 820 - Quality System Regulation
Code of Federal Regulations, Title 21, Subchapter J Radiological A Health

Software Verification and Validation

Software documentation for a Moderate Level of Concern software per FDA'

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

Image /page/6/Picture/1 description: The image contains the logo for United Imaging. The text "UNITED" is stacked on top of the text "IMAGING". To the right of the text is a stylized letter "U" that is dark blue. The logo is simple and modern.

Guidance Document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" is included as a part of this submission. The risk analysis was completed and risk control was implemented to mitigate identified hazards. The testing results show that all the software specifications have met the acceptance criteria. Verification and validation testing of the proposed

device was found acceptable to support the claim of substantial equivalence. UNITED IMAGING HEALTHCARE conforms to the Cybersecurity requirements

by implementing a process of preventing unauthorized access, modification, misuse or denial of use, or unauthorized use of information that is stored, accessed, or transferred from a medical device to an external recipient. Cybersecurity information in accordance with guidance document "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices" is included in this submission.

Performance Verification

Engineering bench testing was performed to support substantial equivalence and the product performance claims. The evaluation and analysis used the identical raw datasets obtained on UIH's uMI 780 and uMI 550, and then applies both HYPER DLR and Gaussian filtering to do image de-noising. The resultant images were then compared for:

A Peak signal to noise ratio
A Structural similarity index
Pearson correlation coefficient
A Signal to noise ratio (SNR)
A Contrast to noise ratio (CNR)
A Normalized root mean square error
A Bland-Altman plot of body & brain VOI SUVmean values

Bench test showed overall image quality improvement based on the commonly used quantitative metrics. HYPER DLR can significantly improve SNR and CNR while preserving image consistency.

Clinical Image Evaluation

The clinical image evaluation was performed by comparing HYPER DLR with Gaussian filtering. Each image was read by board-certified nuclear medicine physicians who provided an assessment of both image noise and overall image quality. The results of the evaluation indicated that HYPER DLR performed lower image noise than Gaussian filtering while the image quality was sufficient for clinical diagnosis.

Additional clinical image evaluation were performed for typical clinical scan times of uMI 550 and uMI 780 systems. Under all the evaluated scan time, clinical evaluation shows that the HYPER DLR produces lower or equivalent image noise and better or equivalent image quality compared with Gaussian filtering. And all the HYPER DLR images are of diagnostic quality.

Clinical Testing

No Clinical Study is included in this submission.

Conclusions 9.

{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 dark blue. The logo is simple and modern in design.

The changes associated with HYPER DLR do not change the indications for use from the predicate devices, and represent equivalent technological characteristic, with no impact on control mechanism, operating principle, and energy type. HYPER DLR is substantially equivalent as safety as the legally marketed predicate devices.

HYPER DLR was developed under UIH's quality management system. Design verification, along with bench testing and the clinical image evaluation demonstrate that HYPER DLR is substantially equivalent as effective as the legally marketed predicate devices.

Based on the comparison and analysis above, the proposed device has similar performance, equivalent safety and effectiveness as the predicate devices. The differences above between the proposed device and predicate devices do not affect the intended use, safety and effectiveness. And no issues are raised regarding to safety and effectiveness. The proposed device is determined to be Substantially Equivalent (SE) to the predicate devices.

Regulation Number and Section

§ 892.1200 Emission computed tomography system.

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