AI-Rad Companion Organs RT is a post-processing software intended to automatically contour DICOM CT imaging data using deep-learning-based algorithms.

Contours that are generated by AI-Rad Companion Organs RT may be used as input for clinical workflows including external beam radiation therapy treatment planning. AI-Rad Companion Organs RT must be used in conjunction with appropriate software such as Treatment Planning Systems and Interactive Contouring applications, to review, edit, and accept contours generated by AI-Rad Companion Organs RT.

The output of AI-Rad Companion Organs RT in the format of RTSTRUCT objects are intended to be used by trained medical professionals.

The software is not intended to automatically detect or contour lesions. Only DICOM images of adult patients are considered to be valid input.

Device Description

AI-Rad Companion Organs RT is a post-processing software used to automatically contour DICOM CT imaging data using deep-learning-based algorithms. AI-Rad Companion Organs RT contouring workflow supports CT input data and produces RTSTRUCT outputs. The configuration of the organ database and organ templates defining the organs and structures to be contoured based on the input DICOM data is managed via a configuration interface. Contours that are generated by AI-Rad Companion Organs RT may be used as input for clinical workflows including external beam radiation therapy treatment planning.

The output of AI-Rad Companion Organs RT, in the form of RTSTRUCT objects, are intended to be used by trained medical professionals. The output of AI-Rad Companion Organs RT must be used in conjunction with appropriate software such as Treatment Planning Systems and Interactive Contouring applications, to review, edit, and accept contours generated by AI-Rad Companion Organs RT application.

At a high-level, AI-Rad Companion Organs RT includes the following functionality:

Automated contouring of Organs at Risk (OAR) workflow
a. Input -DICOM CT
b. Output DICOM RTSTRUCT
Organ Templates configuration (incl. Organ Database)
Web-based preview of contouring results to accept or reject the generated contours

AI/ML Overview

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

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the AI-Rad Companion Organs RT are implicitly tied to demonstrating performance comparable to the predicate device, AccuContour, specifically in terms of contouring accuracy.

Metric	Acceptance Criteria (based on AccuContour)	Reported Device Performance (AI-Rad Companion Organs RT VA20)
DICE Coefficient	0.85 – 0.95	MED: 0.85
95% Hausdorff Distance	≤ 3.5 mm	MED: 2.0 mm

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

Test Set Sample Size: 113 cases
Data Provenance: Retrospective CT data previously acquired for RT treatment planning from multiple clinical sites across North America and Europe. The subcohort analysis also included CT data from multiple vendors (GE, Siemens, Phillips).

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

The document states: "Ground truth annotations were established following RTOG and clinical guidelines using manual annotation." It does not specify the number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience"). However, the phrase "following RTOG and clinical guidelines using manual annotation" implies establishment by qualified medical professionals experienced in radiation therapy contouring.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1). It only states that ground truth annotations were established via "manual annotation" following guidelines. This suggests a single expert or a consensus process without a detailed breakdown of the adjudication procedure in the provided text.

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 reported as being done in this document. The study focuses on the standalone performance of the AI algorithm against a manual ground truth and a comparison to a predicate device's reported performance, not on how human readers' performance improves with or without AI assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done

Yes, a standalone performance study of the algorithm was done. The reported DICE coefficient and Hausdorff Distance values directly assess the algorithm's output against the ground truth without human intervention in the contouring process itself. The "output of AI-Rad Companion Organs RT... are intended to be used by trained medical professionals" who "review, edit, and accept contours generated by AI-Rad Companion Organs RT," but the performance metrics provided are for the initial automated contouring.

7. The Type of Ground Truth Used

The ground truth used was expert consensus / manual annotation following RTOG and clinical guidelines.

8. The Sample Size for the Training Set

The document does not specify the sample size for the training set. It only discusses the validation set (113 cases).

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

The document does not specify how the ground truth for the training set was established. It only describes the ground truth establishment for the test/validation set: "Ground truth annotations were established following RTOG and clinical guidelines using manual annotation."

Summary

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

November 6, 2020

Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health and 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.

Siemens Medical Solutions USA, Inc. % Ms. Lauren Bentley Senior Manager, Regulatory Affairs 40 Liberty Blvd. Mail Code 65-3 MALVERN PA 19355

Re: K193562

Trade/Device Name: AI-Rad Companion Organs RT Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: Class II Product Code: QKB Dated: September 29, 2020 Received: September 30, 2020

Dear Ms. Bentley:

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/cfpmp/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 devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see

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

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 medical devices and radiation-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}------------------------------------------------

Image /page/2/Picture/0 description: The image contains the logo for Siemens Healthineers. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the text is a graphic of several orange dots arranged in a circular pattern.

DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration

Form Approved: OMB No. 0910-0120 Expiration Date: 06/30/2020 See PRA Statement below.

Indications for Use

510(k) Number (if known)

K193562

Device Name AI-Rad Companion Organs RT

Indications for Use (Describe)

AI-Rad Companion Organs RT is a post-processing software intended to automatically contour DICOM CT imaging data using deep-learning-based algorithms.

The output of AI-Rad Companion Organs RT in the format of RTSTRUCT objects are intended to be used by trained medical professionals.

The software is not intended to automatically detect or contour lesions. Only DICOM images of adult patients are considered to be valid input.

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)	☑ Prescription Use (Part 21 CFR 801 Subpart D)	☐ Over-The-Counter Use (21 CFR 801 Subpart C)
☑ 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."

FORM FDA 3881 (7/17)	Page 1 of 1	PSC Publishing Services (301) 443-6740 EF
----------------------	-------------	-------------------------------------------

Siemens Medical Solutions USA, Inc

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

Image /page/3/Picture/0 description: The image contains the logo for Siemens Healthineers. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the word "Healthineers" is a graphic of orange dots.

510(k) SUMMARY FOR AI-RAD COMPANION ORGANS RT

Submitted by: Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard Malvern, PA 19355 Prepared: September 29, 2020 K193562

This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of Safe Medical Devices Act of 1990 and 21 CFR §807.92.

1. Submitter

Importer/Distributor	Siemens Medical Solutions USA, Inc.40 Liberty BoulevardMalvern, PA 19355Mail Code: 65-1ARegistration Number: 2240869
Manufacturing Site	Siemens Healthcare GmbHHenkestrasse 127Erlangen, Germany 91052Registration Number: 3002808157

2. Contact Person

Lauren Bentley Senior Regulatory Affairs Manager Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard Mail Code: 65-3 Malvern, PA 19355 Phone: +1 (610) 241 - 6736 Email: lauren.bentley(@siemens-healthineers.com

3. Device Name and Classification

Product Name:	AI-Rad Companion Organs RT
Trade Name:	AI-Rad Companion Organs RT
Classification Name:	Picture Archiving and Communication System
Classification Panel:	Radiology
CFR Section:	21 CFR §892.2050
Device Class:	Class II
Product Code:	QKB

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

Image /page/4/Picture/1 description: The image contains the logo for Siemens Healthineers. The word "SIEMENS" is in teal, and the word "Healthineers" is in orange. To the right of the word "SIEMENS" is a graphic of orange dots.

4. Predicate Device

Product Name:	AccuContour
Propriety Trade Name:	AccuContour
510(k) Number:	K191928
Clearance Date:	February 28, 2020
Classification Name:	Picture archiving and communications system
Classification Panel:	Radiology
CFR Section:	21 CFR §892.2050
Device Class:	Class II
Product Code:	QKB
Recall Information:	There have been no recalls for this device

5. Indications for Use

AI-Rad Companion Organs RT is a post-processing software intended to automatically contour DICOM CT imaging data using deep-learning-based algorithms.

The output of AI-Rad Companion Organs RT in the format of RTSTRUCT objects are intended to be used by trained medical professionals.

The software is not intended to automatically detect or contour lesions. Only DICOM images of adult patients are considered to be valid input.

6. Device Description

At a high-level, AI-Rad Companion Organs RT includes the following functionality:

1. Automated contouring of Organs at Risk (OAR) workflow
- a. Input -DICOM CT
- b. Output DICOM RTSTRUCT
1. Organ Templates configuration (incl. Organ Database)
1. Web-based preview of contouring results to accept or reject the generated contours

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

7. Substantially Equivalent (SE) Comparison and Technological Characteristics

The indented use of the predicate device and the subject device are equivalent. The main difference is that AI-Rad Companion Organs RT is a dedicated solution for auto-contouring, minimizing the need of user interaction, while AccuContour additionally provides (among other features) manual contouring capabilities, treatment evaluation and treatment adaption.

The subject device, AI-Rad Companion Organs RT, is substantially equivalent with regards to performance and some technology of the predicate. AI-Rad Companion Organs RT and AccuContour both use a deep learning algorithm to support their AI claims. Additionally, they both process CT data in DICOM format, making them vendor agnostic and create outputs which can be used by any TPS system. The deep learning algorithm within AI-Rad Companion Organs RT has been enhanced from the algorithm in syngo.via RT Image Suite (K192065). syngo.via RT Image Suite serves as a reference device within this submission and a dedicated comparison of technological characteristics is provided.

The risk analysis and non-clinical data support that both devices perform equivalently and do not raise different questions of the safety and effectiveness.

	Subject Device	PredicateDevice	Reference Device
DeviceManufacturer	Siemens	XiamenManteia LTD.	Siemens
Device Name	AI-Rad CompanionOrgans RT	AccuContour	syngo.via RT Image Suite
510(k) Number	K193562	K191928	K192065
Indications forUse	AI-Rad CompanionOrgans RT is a post-processing softwareintended to automaticallycontour DICOM CTimaging data using deep-learning-basedalgorithms.Contours that aregenerated by AI-RadCompanion Organs RTmay be used as input forclinical workflowsincluding external beamradiation therapytreatment planning. AI-Rad Companion OrgansRT must be used inconjunction withappropriate softwaresuch as TreatmentPlanning Systems andInteractive Contouring	It is used byradiationoncologydepartment toregistermultimodalityimages andsegment (non-contrast) CTimages, togenerate neededinformation fortreatmentplanning,treatmentevaluation andtreatmentadaptation.	syngo.via RT Image Suite is a3D and 4D imagevisualization, multi-modalitymanipulation andcontouring tool that helps thepreparation and responseassessment of treatments suchas, but not limited to thoseperformed with radiation (forexample, Brachytherapy,Particle Therapy, ExternalBeam Radiation Therapy).It provides tools to efficientlyview existing contours, create,edit, modify, copy contours ofregions of the body, such asbut not limited to, skinoutline, targets and organs-at-risk. It also providesfunctionalities to create andmodify simple treatmentplans. Contours, images andtreatment plans cansubsequently be exported to aTreatment Planning System.The software combines

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

Image /page/6/Picture/0 description: The image contains the logo for Siemens Healthineers. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the words is a graphic of orange dots arranged in a circular pattern.

applications, to review, following digital image processing and visualization edit, and accept contours tools: generated by AI-Rad • Multi-modality viewing and Companion Organs RT. contouring of anatomical, The output of AI-Rad functional, and multi-Companion Organs RT parametric images such as but in the format of not limited to CT, PET, RTSTRUCT objects are PET/CT, MRI, Linac Cone Beam CT (CBCT) intended to be used by images and dose distributions trained medical • Multiplanar reconstruction professionals. (MPR) thin/thick, minimum The software is not intensity projection (MIP), intended to automatically volume rendering technique detect or contour lesions. (VRT) Only DICOM images of · Freehand and semiautomatic contouring of adult patients are regions-of-interest on any considered to be valid orientation including input. oblique • Creation of contours on any type of images without prior assignment of a planning CT • Manual and semi-automatic registration using rigid and deformable registration · Supports the user in comparing, contouring, and adapting contours based on datasets acquired with different imaging modalities and at different time points · Supports the user in comparing images and contours of different patients • Supports multi-modality image fusion • Visualization and contouring of moving tumors and organs • Management of points of interest including but not limited to the isocenter • Management of simple treatment plans • Generation of a synthetic CT based on multiple predefine MR acquisitions

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

Segmentation Feature & Technological Characteristics
Algorithm	Deep Learning	Deep Learning	Atlas-based, machinelearning and deep-learningbased contouring
Segmentation ofOrgan at Risk inthe AnatomicRegions	Head & Neck, Thorax,Abdomen & Pelvis	Head & Neck, Thorax,Abdomen &Pelvis	Head & Neck, Thorax,Abdomen & Pelvis
CompatibleModality	CT Images	Non-ContrastCT	CT Images
CompatibleScanner Models	No Limitation onscanner model,DICOM compliancerequired.	No Limitationon scannermodel,DICOM 3.0compliancerequired.	No Limitation on scannermodel, DICOMcompliance required.
CompatibleTreatmentPlanning System	No Limitation on TPSmodel, DICOMcompliance required.	No Limitationon TPS model,DICOM 3.0compliancerequired.	No Limitation on TPSmodel, DICOM 3.0compliance required.
Contraindications	-Adult use only	-Adult use only-Not intendedto be used as astand-alonediagnosticdevice	There are no knownspecific situations thatcontraindicate the use ofthis device.
TargetPopulation	AI-Rad CompanionOrgans RT is designedfor use only in adultpopulations.AI-Rad CompanionOrgans RT is designedfor any patient forwhom relevantmodality scans areavailable. Morespecifically, thesoftware is validatedon previously acquiredCT DICOM volumesfor radiation therapytreatment planning,including, head and	Any patienttype for whomrelevantmultimodalityimages andsegment (non-contrast) CTimages areavailable.	Any patient type for whomthe relevant modality scandata is available.
	neck, thorax, abdomen,and pelvis.
Clinicalcondition thedevice isintended todiagnose, treat ormanage	Limited to patientspreviously selected forRadiation Therapy.	Limited topatientspreviouslyselected forRadiationTherapy.However,AccuContourcan be used fortreatmentevaluation andtreatmentadaptation.	Limited to patientspreviously selected forRadiation Therapy.
SoftwareArchitecture	AI-Rad Companion(Engine) architectureenabling thedeployment of AI RadCompanion Organs RTin the Cloud. The UI isprovided using a web-based interface.	Cloud and/orServer based	Client-server architecturewhere the server processesand renders the data. Clientprovides the UI forinteractive image viewingand processing
DeploymentFeature	Cloud Deployment	CloudDeploymentand Server	On-premise/standalonedeployment
Organ Templates	Creating, editing anddeletion of organtemplates. Customizepredefined structuredatabase with mappingto internationalnomenclature schemes.	No informationpubliclyavailable.	Creating, editing anddeletion of structuretemplates. Customizepredefined structuredatabase with mapping tointernational nomenclatureschemes.
Automatedworkflow	AI-Rad CompanionOrgans RTautomaticallyprocesses input imagedata and sends theresults as DICOM-RTStructure Sets to auser-configurabletarget node.	AccuContourautomaticallyprocesses inputimage data	Rapid Results workflowfeature allows theconfiguration of automaticorgan contouring andoptionally send DICOM-RT files to a targetDICOM-Node for furtherprocessing.
Contourvisualization andediting feature	AI-Rad CompanionOrgans RT providesbasic result preview ofautomatic	AccuContourprovides basicresult previewof automatic	syngo.via RT Image Suiteprovides advanced contourvisualization feature of
	segmentation results,and no editing featureof the automaticsegmented contour.	segmentationresults. Manualcontouring ispossible.	contours and manualediting feature
SegmentationPerformance	The target performancewas validated using113 cases distributed totwo cohorts. CohortA-Clinical RoutineTreatment PlanningCT (Siemens; Headand Neck, Thorax andAbdomen Pelvis) andCohort B-MultiVendor Coverage (GEand Phillips; Head andNeck).To objectively evaluatethe target performance.the DICE coefficient,the absolute symmetricsurface distance(ASSD) and the failrate was evaluated.The segmentationperformance of thesubject and referencedevice were equivalentas well as the overallperformance comparedto the predicate device.	Thesegmentationperformancewas validatedusing datasetsfrom Chinaand the USAusing threemajor vendors(GE, Siemensand Phillips).Thesegmentationaccuracy isevaluatedusing DICEcoefficient.	The target performance wasvalidated using 32 caseswith various fields of view.To objectively evaluate thetarget performance, theDICE coefficient & theabsolute symmetric surfacedistance (ASSD) wereevaluated. Thesegmentation performanceof the subject and predicatedevice were equivalent.
User Interface -Results Preview(Confirmation)	Basic visualizationfunctionality oforiginal data andgenerated contours	Basic resultpreview ofautomaticsegmentationresults. Manualcontouring ispossible.	Standard visualization tools(window levels, MPR,MIP, VRT). Manualcontouring is possible.
User InterfaceConfiguration	Configuration UI	Configurationmenu	syngo.via GUI
Human Factors	Design to be used bytrained clinicians.	Design to beused by trainedclinicians.	Design to be used bytrained clinicians.

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

Image /page/8/Picture/0 description: The image contains the logo for Siemens Healthineers. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the words is a graphic of orange dots.

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

Image /page/9/Picture/0 description: The image shows the logo for Siemens Healthineers. The word "SIEMENS" is in teal, and the word "Healthineers" is in orange. To the right of the words is a graphic of orange dots.

Traditional 510(k) Submission: AI-Rad Companion Organs RT

Table 3: Indications for Use and Segmentation Feature Comparison

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

8. Nonclinical Bench Testing

Non-clinical tests were conducted to assess the functionality of AI-Rad Companion Organs RT. Software validation and bench testing have been conducted to assess the performance claims as well as the claim of substantial equivalence to the predicate device.

AI-Rad Companion Organs RT has been tested to meet the requirements of conformity to multiple industry standards. Non-clinical performance testing demonstrates that AI-Rad Companion Organs RT complies with the FDA guidance document, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (May 11, 2005) as well as with the following voluntary FDA recognized Consensus Standards listed in Table 4 below.

RecognitionNumber	ProductArea	Title of Standard	ReferenceNumber andDate	StandardsDevelopmentOrganization
5-114	General	Medical Devices –Application of usabilityengineering to medicaldevices [includingCorrigendum 1 (2016)]	62366-1:2015-02	IEC
5-40	General	Medical Devices –application of riskmanagement to medicaldevices	14971:2007	ISO
13-79	Software/Informatics	Medical device software –software life cycleprocesses [IncludingAmendment 1 (2016)]	62304:2006/A1:2016	AAMIANSIIEC
12-300	Radiology	Digital Imaging andCommunications inMedicine (DICOM) Set	PS 3.1 – 3.20(2016)	NEMA
12-261	Radiology	Information Technology –Digital Compression andcoding of continuous -tonestill images: Requirementsand Guidelines [including:Technical Corrigendum1(2005)]	10918-1 1994-02-15	ISOIEC

Table 4: Voluntary Consensus Standards

Verification and Validation

Software documentation for a Major Level of Concern software, per FDA's Guidance Document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" issued on May 11, 2005, is also included as part of this submission. The performance data demonstrates continued conformance with special controls for medical devices containing software. Non-clinical tests were conducted on the subject device during product development.

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

SIEMENS Healthineers

Software bench testing in the form of Unit, System and Integration tests were performed to evaluate the performance and functionality of the new features and software updates. All testable requirements in the Requirement Specifications and the Risk Analysis have been successfully verified and traced in accordance with the Siemens Healthineers DH product development process. Human factor usability validation is addressed in system testing and usability validation test records. Software verification and regression testing have been performed successfully to meet their previously determined acceptance criteria as stated in the test plans.

Siemens Healthineers adheres to the cybersecurity requirements as defined the FDA Guidance "Content of Premarket Submissions for Management for Cybersecurity in Medical Devices," issued October 2, 2014 by implementing a process of preventing unauthorized access, modifications, misuse or denial of use, or the unauthorized use of information that is stored, accessed, or transferred from a medical device to an external recipient.

Performance Software Validation

To validate the AI-Rad Companion Organs RT software from clinical perspective, the autocontouring algorithm underwent a scientific evaluation. The results of clinical data-based software validation for the subject device AI-Rad Companion Organs RT demonstrated equivalent performance in comparison to the predicate device. A complete scientific evaluation report is provided in support of the device modifications.

The performance of the AI-Rad Companion Organs RT has been validated in a retrospective performance study on CT data previously acquired for RT treatment planning (N= 113, data from multiple clinical sites across the North American and Europe). Ground truth annotations were established following RTOG and clinical guidelines using manual annotation. The subject device achieved a median DICE score > 80% across all automatically contoured organs at risk with a median 95% Hausdorff (HD) value of 2.0 mm. In a subcohort analysis performance results were found to be consistent on CT data across multiple vendors. In comparison to the predicate device, AccuContour, both the DICE score and HD value were similar in nature and achieves appropriate quality not only for the unmodified organs but also for the newly supported automatically contoured organs and structures. The results of both devices are shown in the following Table. As we can see, the performance of the subject device and predicate device are comparable in DICE and Hausdorff Distance.

	DICE	95% Hausdorff Distance (HD)
AccuContour (K191928)	0.85 – 0.95	$≤$ 3.5 mm
AI-Rad Companion Organs RTVA20	MED: 0.85	MED: 2.0 mm

Table5. Performance comparison between subject device and predicate device

9. Clinical Tests

No clinical tests were conducted to test the performance and functionality of the features introduced within AI-Rad Companion Organs RT. Verification and validation of the algorithm enhancements and improvements have been performed and these modifications have been validated for their intended use. The data from these activities were used to support the subject device and the substantial equivalence argument. No animal testing has been performed on the subject device.

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

10. Safety and Effectiveness

The device labeling contains instructions for use and any necessary cautions and warnings to ensure safe and effective use of the device.

Risk management is ensured via ISO 14971:2007 compliance to identify and provide mitigation of potential hazards in a risk analysis early in the design phase and continuously throughout the development of the product. These risks are controlled via measures realized during software development, testing and product labeling.

Furthermore, the device is intended for healthcare professionals familiar with the post processing of computed tomography images in the context of radiation oncology.

11. Substantial Equivalence and Conclusion

AI-Rad Companion Organs RT is substantially equivalent to the following predicate device:

Predicate Device	FDA Clearance Number	FDA Clearance Date	Main Product Code
AccuContour	K191928	February 28, 2020	QKB

Table 6: Predicate for AI-Rad Companion Organs RT

The intended use of the predicate device and the subject device are equivalent. The two devices process the same form of CT DICOM data, are agnostic with respect to the CT machine and Treatment Planning System. The main difference is that AI-Rad Companion Organs RT is a dedicated solution for auto-contouring while AccuContour (K191928), additionally provides (among other features) manual contouring capabilities and image registration. AccuContour is used additionally for treatment evaluation and treatment adaption. From a performance perspective both devices provide automatic organ-at-risk contouring using deep learning method in head and neck, thorax, abdomen and pelvis (for both male and female) regions. Both devices are able to contour organ-at-risk using GE, Siemens and Philips scanners. Additionally, both devices have comparable DICE and HD values when compared to the ground truth. Due to the above-mentioned attributes, AI-Rad Companion Organs RT is substantially equivalent to the predicate device, AccuContour, and does not raise any additional concerns to the safety or effectiveness of the subject device.

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).