uOmnispace.MI is a software solution intended to be used for viewing, processing, evaluating and analyzing of PET, CT, MR, SPECT images. It supports interpretation and evaluation of examinations within healthcare institutions. It has the following additional indications:

u uOmnispace.MI MM Fusion application is intended to provide tools for viewing, analyzing and reporting PET, CT, MR, SPECT data with its flexible workflow and optimized layout protocols for dedicated reporting purposes on oncology, neurology, cardiology.

u uOmnispace.MI MM Oncology application is intended to provide tools to display and analyze the follow-up PET, CT, MR data, with which users can do image registration, lesion segmentation, and statistical analysis.

· uOmnispace.MI Dynamic Analysis application is intended to display PET data and anatomical data such as CT or MR, and supports to do lesion segmentation and output associated time activity curve.

u uOmnispace.MI NeuroQ application is intended to analyze the brain PET scan, give quantitative results of the relative activity of different brain regions, and make comparison of activity of normal brain regions in AC database or between two studies from the same patient, as well as provide analysis of amyloid uptake levels in the brain.

u uOmnispace.MI Emory Cardiac Toolbox application is intended to provide cardiac short axis reconstruction, browsing function. And it also performs perfusion analysis, activity analysis and cardiac function analysis of the cardiac short axis.

Device Description

The uOmnispace.MI is a post-processing software based on the uOmnispace platform (cleared in K230039) for viewing, manipulating, evaluating and analyzing PET, CT, MR, SPECT images, can run alone or with other advanced commercially cleared applications.

This proposed device contains the following applications:

uOmnispace.MI MM Fusion
uOmnispace.MI MM Oncology
. uOmnispace.MI Dynamic Analysis

Additionally, uOmnispace.MI offers the users the options to run the following third-party applications in uOmnispace.MI:

uOmnispace.MI NeuroQ ●
uOmnispace.MI Emory Cardiac Toolbox ●

AI/ML Overview

Here's an analysis of the acceptance criteria and study detailed in the provided document, addressing each of your requested points:

Acceptance Criteria and Study Details for uOmnispace.MI

1. Table of Acceptance Criteria and Reported Device Performance

For Spine Labeling Algorithm:

Acceptance Criteria	Reported Device Performance (Average Score)	Meets Criteria?
Average score higher than 4 points	4.951 points	Yes

For Rib Labeling Algorithm:

Acceptance Criteria	Reported Device Performance (Average Score)	Meets Criteria?
Average score higher than 4 points	5 points	Yes

Note: The document also states that an average score of "higher than 4 points is equivalent to the mean identification rate of spine labeling is greater than 92% (>83.3%, correctly labeled vertebrae number ≥23, total vertebrae number=25, 23/25=92%), and the mean identification rate of rib labeling is greater than 91.7%(>91.5% , correctly labeled rib number ≥22, total rib number=24, 22/24~91.7%)." This indicates the acceptance criteria are linked to established identification rates from literature, ensuring clinical relevance.

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

For Spine Labeling Algorithm:

Sample Size: 286 CT scans, corresponding to 267 unique patients.
Data Provenance:
- Countries of Origin: Asian (Chinese) data (106 samples), European data (160 samples), The United States data (20 samples).
- Retrospective/Prospective: Not explicitly stated, but typically such large datasets collected for algorithm validation are retrospective.

For Rib Labeling Algorithm:

Sample Size: 160 CT scans, corresponding to 156 unique patients.
Data Provenance:
- Countries of Origin: Asian (Chinese) data (80 samples), The United States data (80 samples).
- Retrospective/Prospective: Not explicitly stated, but likely retrospective.

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

Number of Experts: At least one "senior clinical specialist" is explicitly mentioned for final review and modification. "Well-trained annotators" performed the initial annotations. The exact number of annotators is not specified.
Qualifications of Experts:
- Annotators: Described as "well-trained annotators." Specific professional qualifications (e.g., radiologist, technician) or years of experience are not provided.
- Reviewer: "A senior clinical specialist." Specific professional qualifications or years of experience are not provided.

4. Adjudication Method for the Test Set

The adjudication method involved a multi-step process:

Initial annotations were done by "well-trained annotators" using an interactive tool.
For rib labeling, annotators "check each other's annotation."
A "senior clinical specialist" performed a final check and modification to ensure correctness.

This indicates a multi-annotator review with a senior specialist as the final adjudicator. It is not explicitly a 2+1 or 3+1 method as such, but rather a hierarchical review process.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly described in the provided text. The performance verification focused on the standalone algorithm's accuracy against a ground truth, rather than comparing human reader performance with and without AI assistance.

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

Yes, a standalone (algorithm only) performance study was done. The entire performance verification section describes how the deep learning-based algorithms for spine and rib labeling were tested against ground truth annotations to assess their accuracy in an automated fashion. The reported scores explicitly reflect the algorithm's performance.

7. The Type of Ground Truth Used

The ground truth for both spine and rib labeling was established through expert consensus based on manual annotations, followed by review and modification by a senior clinical specialist. It is not directly pathology or outcome data.

8. The Sample Size for the Training Set

The document explicitly states: "The training data used for the training of the spine labeling algorithm is independent of the data used to test the algorithm." and "The training data used for the training of the rib labeling algorithm is independent of the data used to test the algorithm."

However, the actual sample size for the training set is not provided in the given text.

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

The document states that the training data and test data were independent. While it describes how the ground truth for the test set was established (well-trained annotators + senior clinical specialist review), it does not explicitly describe the methodology for establishing the ground truth for the training set. It can be inferred that a similar expert annotation process would have been used, but details are not provided.

Summary

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

Image /page/0/Picture/0 description: The image shows 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.

December 20, 2023

Shanghai United Imaging Healthcare Co., Ltd. Gao Xin Official Correspondent No.2258 Chengbei Road, Jiading District Shanghai, Shanghai 201807 China

Re: K233176

Trade/Device Name: uOmnispace.MI Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: LLZ Dated: September 26, 2023 Received: September 28, 2023

Dear Gao Xin:

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 (the 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 available 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.

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

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

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

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 Part 803) for devices or postmarketing safety reporting (21 CFR Part 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 Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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 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

Form Approved: OMB No. 0910-0120 Expiration Date: 07/31/2026 See PRA Statement below.

Submission Number (if known)

33176 Device Name

uOmnispace.MI

Indications for Use (Describe)

· uOmnispace.MI Dynamic Analysis application is intended to display PET data and anatomical data such as CT or MR, and supports to do lesion segmentation and output associated time activity curve.

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 dark blue with a white vertical line running through the center. The logo is simple and modern in design.

510 (k) SUMMARY

K233176

1. Date of Preparation: September 26, 2023

2. Sponsor Identification

Shanghai United Imaging Healthcare Co.,Ltd. No.2258 Chengbei Rd. Jiading District, 201807, Shanghai, China

Establishment Registration Number: 3011015597

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

3. Identification of Proposed Device

Trade Name: Medical Image Post-processing Software Common Name: Medical image management and processing system Model(s): uOmnispace.MI

Regulatory Information Classification Name: Medical image management and processing system Classification: II Product Code: LLZ Regulation Number: 21 CFR 892.2050 Review Panel: Radiology

4. Identification of Predicate Device(s)

Predicate Device 510(k) Number: K192630 Device Name: uWS-MI

Reference Device#1 510(k) Number: K173897

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

Image /page/4/Picture/1 description: The image contains the logo for United Imaging. The text "UNITED IMAGING" is stacked on top of each other and is in a bold, sans-serif font. To the right of the text is a stylized "U" symbol, which is also in a bold font. The logo is simple and modern, and the use of a bold font gives it a strong and confident look.

Device Name: syngo.via MI Workflows

Reference Device#2 510(k) Number: K183170 Device Name: uWS-CT

5. Device Description

This proposed device contains the following applications:

uOmnispace.MI MM Fusion
uOmnispace.MI MM Oncology
. uOmnispace.MI Dynamic Analysis

Additionally, uOmnispace.MI offers the users the options to run the following third-party applications in uOmnispace.MI:

uOmnispace.MI NeuroQ ●
uOmnispace.MI Emory Cardiac Toolbox ●

6. Indications for use

uOmnispace.MI MM Fusion is intended to provide tools for viewing, analyzing and reporting PET, CT, MR, SPECT data with its flexible workflow and optimized layout protocols for dedicated reporting purposes on oncology, neurology, and cardiology.
. uOmnispace.MI MM Oncology application is intended to provide tools to display and analyze the follow-up PET, CT, and MR data, with which users can do image registration, lesion segmentation, and statistical analysis.
. uOmnispace.MI Dynamic Analysis application is intended to display PET data and anatomical data such as CT or MR, and supports to do lesion segmentation and output associated time activity curve.
. uOmnispace.MI NeuroQ application is intended to analyze the brain PET scan, give quantitative results of the relative activity of different brain regions, and make comparison of activity of normal brain regions in AC database or between two studies from the same patient, as well as provide analysis of amyloid uptake levels in the brain.

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

Image /page/5/Picture/1 description: The image shows the logo for United Imaging. The logo consists of the words "UNITED IMAGING" in a bold, sans-serif font, stacked on top of each other. 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 use of a bold font gives it a strong and confident look.

uOmnispace.MI Emory Cardiac Toolbox application is intended to provide cardiac . short axis reconstruction, browsing function. And it also performs perfusion analysis, activity analysis and cardiac function analysis of the cardiac short axis.

7. Summary of Technological Characteristics

The technology characteristics of the uOmnispace.MI, reflected in this 510(k) submission are substantially equivalent to those of the predicate devices.

The following tables compare the features, principles of operation, fundamental scientific technology and intended use of uOmnispace.MI when compared to the predicate devices.

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

Item	Proposed DeviceuOmnispace.MI	Predicate DeviceuWS-MI (K192630)	Remark
General
Device ClassificationName	Medical image management and processing system	Medical image management and processing system	Same
Product Code	LLZ	LLZ	Same
Regulation Number	21 CFR 892.2050	21 CFR 892.2050	Same
Device Class	II	II	Same
Classification Panel	Radiology	Radiology	Same
AdvancedApplication	Yes	Yes	Same
Indications for use	uOmnispace.MI is a software solution intended to be used for viewing, processing, evaluating and analyzing of PET, CT, MR, SPECT images. It supports interpretation and evaluation of examinations within healthcare institutions. It has the following additional indications:uOmnispace.MI MM Fusion application is intended to provide tools for viewing, analyzing and reporting PET, CT, MR, SPECT data with its flexible workflow and optimized layout protocols for dedicated reporting purposes on oncology, neurology, cardiology.uOmnispace.MI The MM Oncology application is intended to provide tools to display and analyze the	uWS-MI is a software solution intended to be used for viewing, manipulation, communication, and storage of medical images. It supports interpretation and evaluation of examinations within healthcare institutions. It has the following additional indications:The Oncology application is intended to provide tools to display and analyze the follow-up PET/CT data, with which users can do image registration, lesion segmentation, and statistical analysis.The Dynamic Analysis application is intended to display PET data and anatomical data such as CT or MR, and supports to do lesion segmentation	The indication for use of the proposed device is expanded and replenished. The proposed device includes more applications and functions which are discussed in the following chapters. The difference will not impact the safety and effectiveness of the device.
Item	Proposed Device	Predicate Device	Remark
	uOmnispace.MI	uWS-MI (K192630)
	follow-up PET, CT, MR data, with which users cando image registration, lesion segmentation, andstatistical analysis.	and output associated time-activity curve.
	uOmnispace.MI Dynamic Analysis application isintended to display PET data and anatomical datasuch as CT or MR, and supports to do lesionsegmentation and output associated time activitycurve.	NeuroQ application is intended to analyze thebrain PET scan, give quantitative results of therelative activity of 240 different brain regions, andmake comparison of activity of normal brainregions in AC database or between two studiesfrom the same patient, as well as provide analysisof amyloid uptake levels in the brain.
	uOmnispace.MI NeuroQ application is intended toanalyze the brain PET scan, give quantitative resultsof the relative activity of different brain regions, andmake comparison of activity of normal brainregions in AC database or between two studies fromthe same patient, as well as provide analysis ofamyloid uptake levels in the brain.	Emory Cardiac Toolbox application is intended toprovide cardiac short axis reconstruction,browsing function. And it also performs perfusionanalysis, activity analysis and cardiac functionanalysis of the cardiac short axis.
	uOmnispace.MI Emory Cardiac Toolboxapplication is intended to provide cardiac short axisreconstruction, browsing function. And it alsoperforms perfusion analysis, activity analysis andcardiac function analysis of the cardiac short axis.

Table 1 Substantial equivalent discussion for hasic functions

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

Table 2 Substantial equivalent discussion for MM Fusion

Application	Function name	Proposed device	Predicate	Reference	Remark
		uOmnispace.MI	device	device#2:

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

		uWS-MI(K192630)	uWS-CT(K183170)
MM Fusion	Image Fusion	Yes	/	Same
	Study Comparison	Yes	/	Same
	3D Visualization	Yes	/	Same
Registration	Manual Registration	Yes	/	Same
	Dot Registration	Yes	/	Same
	Auto Registration	Yes	/	Same
	Default Layout and Customized Layout	Yes	/	Functional Substantial EquivalentNote1
	Position Correction	Yes	/	Same
LesionSegmentation	Fix threshold segmentation	Yes	/	Same
	Percentage thresholdsegmentation	Yes	/	Same
	Adaptive thresholdsegmentation	Yes	/	Same
		CT Liver Segmentation	/	Yes
	CT Lung Segmentation	/	Yes	Same
	Rib Labeling	/	Yes	Functional Substantially EquivalentNote 2
	Spine Labeling	/	Yes	Functional Substantially EquivalentNote 3
	Save/Film/Report	Yes	/	Same

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

Application	Function name	Proposed deviceuOmnispace.MI	PredicatedeviceuWS-MI(K192630)	Referencedevice#2:uWS-CT(K183170)	Referencedevice#3:syngo.via MIWorkflows(K173897)	Remark
MMOncology	Registration	Manual Registration	Yes	Yes	/	/	Same
	Registration	Auto Registration	Yes	Yes	/	/	Same
	One-Step Evaluation		Yes	Yes	/	/	Same
	LesionSegmentation	Fix thresholdsegmentation	Yes	Yes	/	/	Same
		Percentage thresholdsegmentation	Yes	Yes	/	/	Same
		Adaptive thresholdsegmentation	Yes	Yes	/	/	Same
		Lung nodulesegmentation	Yes	Yes	/	/	Same
		Liver tumorsegmentation	Yes	Yes	/	/	Same
		Lymph nodesegmentation	Yes	Yes	/	/	Same
		Spread	Yes	Yes	/	/	Same
	CT liver Segmentation		Yes	/	Yes	/	Same
	CT lung Segmentation		Yes	/	Yes	/	Same
	Rib Labeling		Yes	/	Yes	/	Functional SubstantialEquivalent.Note 4
	Spine Labeling		Yes	/	Yes		Functional SubstantialEquivalent

Table 3 Substantial equivalent discussion for MM Oncology

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

					Note 5
	Statistical Analysis	Yes	Yes	/	Same
	Reference VOI	Yes	Yes	/	Same
ResponseAssessment	PERCIST	Yes	Yes	/	Same
	RECIST1.0	Yes	Yes	/	Same
	RECIST1.1	Yes	/	Yes	Same
	Deauville Score	Yes	/	Yes	Same
	Save	Yes	Yes	/	Same

Table 4 Substantial equivalent discussion for Dynamic Analysis

Application	Function name	Proposed device	Predicate device	Remark
		uOmnispace.MI	uWS-MI (K192630)
Dynamic Analysis	Automatic cine	Yes	Yes	Same
	ROI Drawing	Yes	Yes	Same
	Data Recombination	Yes	Yes	Same
	Curve Analysis	Yes	Yes	Same
	Table Quantization Statistics	Yes	Yes	Same
	Save	Yes	Yes	Same
	Print (Filming)	Yes	Yes	Same
Registration	Manual Registration	Yes	Yes	Same
	Dot Registration	Yes	Yes	Same
	Auto Registration	Yes	Yes	Same
LesionSegmentation	Fix threshold segmentation	Yes	Yes	Same
	Percentage thresholdsegmentation	Yes	Yes	Same
	Adaptive thresholdsegmentation	Yes	Yes	Same

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

Note 1: Compared to predicate device optimizes image layout that adds more default layout and adjusts the interaction of customized layout. This difference between the reference device doesn't impact the safety and effectiveness of the subject device.

Note 2: Compared to predicate device optimizes a new algorithm based on deep learing. This algorithm supports the same function as uWS-CT (K183170 cleared). This difference between the reference device device doesn't impact the safety and effectiveness of the subject device.

Note 3: Compared to predicate device optimizes a new algorithm based on deep learing. This algorithm supports the same function as uWS-CT (K183170 cleared). This difference between the reference device doesn't impact the safety and effectiveness of the subject device.

Note 4: Compared to predicate device optimizes a new algorithm based on deep learning. This algorithm suports the same finction as uWS-CT (K183170 cleared). This difference between the reference device device doesn't impact the safety and effectiveness of the subject device.

Note 5: Compared to predicate device optimizes a new algorithm based on deep learning This algorithm supports the same function as uWS-CT (K183170 cleared). This difference between the reference device and the reference device doesn't impact the safety and effectiveness of the subject device.

{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 symbol that resembles the letter "U" with a vertical line running through the center, creating a negative space that suggests the letter "I". The color of the text and symbol is a dark teal.

Performance Data 8.

The following performance data were provided in support of the substantial equivalence determination.

Biocompatibility

Not Applicable to the proposed device, because the device is stand-alone software.

Electrical Safety and Electromagnetic Compatibility (EMC)

Not Applicable to the proposed device, because the device is stand-alone software.

Software Verification and Validation

Software verification and validation testing was provided to demonstrate safety and efficacy of the proposed device. This includes a hazard analysis, and the potential hazards have been classified as a moderate level of concern (LOC). Those documentations include:

· Software Description
· Device Hazard Analysis
· Software Requirements Specification (SRS)
· Software Architecture Design Chart
· Software Development Environment Description
· Software Verification and Validation
· Cybersecurity Documents

Animal Study

No animal study was required.

Clinical Studies

No clinical study was required.

Performance Verification

● Design of the performance verification test

The identification rate is a commonly used evaluation metric to evaluate the labelling performance [1-3], which is defined as the ratio of correctly identified vertebrae/rib to the total number of vertebrae/rib.

As for spine labeling, the mean identification rate of the five top-performing algorithms are 83.3% [2]. For rib labeling, the mean identification rate (labelaccuracy) of a SOTA algorithm is 91.5% [3]. If the proposed device algorithm can

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

Image /page/13/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 also in bold. The color of the text and the "U" shape is a dark teal.

achieve comparable performance, it is considered that the proposed device algorithm meets the clinical requirements.

We set a 5-point scoring criteria, and the acceptance criteria was that the average score of the proposed device results is higher than 4 points is equivalent to the mean identification rate of spine labeling is greater than 92% (>83.3%, correctly labeled vertebrae number ≥23, total vertebrae number=25, 23/25=92%), and the mean identification rate of rib labeling is greater than 91.7%(>91.5% , correctly labeled rib number ≥22, total rib number=24, 22/24~91.7%). So, the setting of evaluation criteria in this way can meet clinical requirements.

Moreover, scoring according to the number of incorrect label is a common way to evaluate the labeling algorithm [1]. The number of incorrect label is directly related to the extra workload of the doctor, e.g. manual correction. While the purpose of the labeling algorithm is to improve the work efficiency of doctors, a more intuitive way is to score according to the number of errors in automatic label

To validate the uOmnispace.MI software from a clinical perspective, the deep learning-based spine labeling algorithm and rib labeling algorithm contained in the product underwent a scientific evaluation. The validation results for the proposed device demonstrated the good performance, the robustness and good generalization ability among different subgroups.

1. Spine labeling Algorithm

The performance testing for deep learning-based spine labeling algorithm was performed on 286 CT scans (data shown in Table 8-2) during the product development.

. Acceptance Criteria

The validation type and acceptance criteria is shown in the Table 8-1 below:

Validation Type	Acceptance Criteria
Score based on gold standard	The average score of the proposed deviceresults is higher than 4 points.

Table 8-1 Validation type and acceptance criteria

● Testing Data Information

1) Equipments and Protocols

CT data were acquired with different multidetector (16, 64, 160, 256, 320-slice) CT scanners from five major manufacturers (GE, Phillips, Siemens, Toshiba, UIH), and with tube voltage of 110 - 140 kVp. tube current of 275-1000mA. slice thickness of 0.625-2.0 mm, in-plane spacing of 0.656 - 1.172 mm.

2) Sample Size

Dataset	Patients Number	Samples Number
Testing Dataset	267	286

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

Image /page/14/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" shape, which is also in a bold font. The color of the text and the "U" shape is a dark gray.

(Note: One patient may have multiple samples, because of the differences in scanning protocols, such as slice thickness, in-plane spacing)

Clinical Subgroup Information 3)

The testing data information is summarized below.

Table 8-2. Testing data information
Information of data	286 spine CTs
Gender	Male: 68
	Female: 55
	Unknown: 163
Age	(10, 25]: 4
	(25, 40]: 16
	(40, 60]: 45
	(60, 75]: 47
	(75, 100]: 14
	Unknown: 160
Ethnicity	Asian(Chinese) data: 106
	European data: 160
	The United States data: 20

. Performance Testing Summary

For testing dataset, the average score of the proposed device results to be validated is 4.951 points and greater than 4 points. Meanwhile, the subgroup analysis shows that (Table 8-3) the proposed device algorithm has good generalization in different subgroups.

Age	Average score of the proposed device
(10, 25]	5.000
(25, 40]	5.000
(40, 60]	5.000
(60, 75]	5.000
(75, 100]	5.000
Unknown	4.914
Gender	Average score of the proposed device
Female	5.000
Male	5.000
Unknown	4.913
Ethnicity	Average score of the proposed device
Asian(Chinese) data	5.000
European data	4.913
The United States data	5.000

Table 8-3. Subgroup performance test

Standard Annotation Process ●

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

Image /page/15/Picture/1 description: The image shows the logo for United Imaging. The text "UNITED IMAGING" is displayed in bold, sans-serif font, stacked on top of each other. To the right of the text is a stylized letter "U" symbol, which is dark teal in color. The logo is simple and modern in design.

For ground truth annotations, all ground truth are annotated by well-trained annotators. The annotators use an interactive tool to observe the image, and then set annotation points near the center of vertebral body and assign anatomical labels. Finally, a senior clinical specialist will check and modify annotations to make sure the ground truth correct.

. Testing & Training Data Independence

The training data used for the training of the spine labeling algorithm is independent of the data used to test the algorithm.

Confounders

There are no confounders exist for the training methodology.

2. Rib labeling Algorithm

The performance testing for deep learning-based rib labeling algorithm was performed on 160 CT scans (data shown in Table 8-6) during the product development.

. Acceptance Criteria

The validation type and acceptance criteria is shown in the Table 8-4 below: Table8-4. Validation type and acceptance criteria

Validation Type	Acceptance Criteria
Score based on gold standard	The average score of the proposed deviceresults is higher than 4 points.

Testing Data Information .

1) Equipments and Protocols

CT data were acquired with different multidetector (16, 64, 160, 256, 320-slice) CT scanners from five major manufacturers (GE, Phillips, Siemens, Toshiba, UIH), and with tube voltage of 100-140 kVp, tube current of 275-1000 mA, slice thickness of 0.625-3.0 mm, in-plane spacing of 0.531-1.955 mm.

2) Sample Size

Table 8-5. Sample size information of testing data

Dataset	Patients Number	Samples Number
Testing Dataset	156	160

(Note: One patient may have multiple samples, because of the differences in scanning protocols, such as slice thickness, in-plane spacing.)

3) Clinical subgroups

The clinical subgroups information of the testing data is summarized below.

Table 8-6. Testing data information

Information of data	160 CTs
Gender	Male: 110Female: 39

{16}------------------------------------------------

Image /page/16/Picture/1 description: The image contains the logo for United Imaging. The logo consists of the words "UNITED IMAGING" in a 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 bars and a horizontal bar in the middle. The logo is simple and modern, and the use of bold font and the stylized "U" shape makes it easily recognizable.

	Unknown: 11
Age	(10, 25]: 2
	(25, 40]: 14
	(40, 60]: 51
	(60, 75]: 69
	(75, 100]: 24
Ethnicity	Asian(Chinese) data: 80
	The United States data: 80

. Performance Testing Summary

For the testing dataset, the average score of the proposed device results to be validated is 5 points and greater than 4 points. Meanwhile, the subgroup analysis shows that (Table 8-12) the proposed device algorithm has good generalization in different subgroups.

Age	Average score of the proposed device
(10, 25]	5.00
(25, 40]	5.00
(40, 60]	5.00
(60, 75]	5.00
(75, 100]	5.00
Gender	Average score of the proposed device
Female	5.00
Male	5.00
Unknown	5.00
Ethnicity	Average score of the proposed device
Asian(Chinese) data	5.00
The United States data	5.00

Table 8-7. Subgroup performance test

. Standard Annotation Process

For ground truth annotations, all ground truth are annotated by well-trained annotators. A threshold based interactive tool is used to generate initial rib mask, then annotators will refine the rib mask and assign anatomical labels. After the first round annotation, they will check each other's annotation. At last, a senior clinical specialist will check and modify annotations to make sure the ground truth correct.

. Testing & Training Data Independence

The training data used for the training of the rib labeling algorithm is independent of the data used to test the algorithm.

Confounders

There are no confounders exist for the training methodology.

References:

{17}------------------------------------------------

Image /page/17/Picture/1 description: The image contains the logo for United Imaging. The logo consists of the words "UNITED IMAGING" in a bold, sans-serif font, stacked on top of each other. To the right of the text is a stylized "U" shape, which is also in a bold font. The color of the logo is a dark teal.

[1]Major, David , et al. "Automated landmarking and labeling of fully and partially scanned spinal columns in CT images." Medical Image Analysis 17.8(2013):1151-1163.

[2]C, Anjany Sekuboyina A B , et al. "VerSe : A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images." Medical Image Analysis (2021).

[3]Jin L, Gu S, Wei D, et al. "RibSeg v2: A Large-scale Benchmark for Rib Labeling and Anatomical Centerline Extraction". IEEE Transactions on Medical Imaging, 2023. DOI: 10.1109/TMI.2023.3313627.

Other Standards and Guidance

. NEMA PS 3.1 - 3.20 Digital Imaging and Communications in Medicine (DICOM) Set (2016).
ISO 14971 Medical devices - Application of risk management to medical devices (Edition 2.0, corrected version, 2007).
IEC 62304 Medical device software - Software life cycle processes (Edition 1.1, 2015).

Summary

The features described in this premarket submission are supported with the results of the testing mentioned above; the uOmnispace.MI was found to have a safety and effectiveness profile that is similar to the predicate device and reference devices.

Substantially Equivalent (SE) Conclusion 9.

The proposed device is equivalent to the predicate device with regard to safety and efficacy. This conclusion is based upon a comparison of intended use, technological characteristics, performance specification, device hazards as well as verification and validation results.

In summary, the proposed device is determined to be Substantially Equivalent (SE) to the predicate device and reference devices.

Regulation Number and Section

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).