AI-Rad Companion Organs RT is a post-processing software intended to automatically contour DICOM CT and MR predefined structures using deep-leaming-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 are intended to be used by trained medical professionals.

The software is not intended to automatically detect or contour lesions.

Device Description

AI-Rad Companion Organs RT provides automatic segmentation of pre-defined structures such as Organs-at-risk (OAR) from CT or MR medical series, prior to dosimetry planning in radiation therapy. AI-Rad Companion Organs RT is not intended to be used as a standalone diagnostic device and is not a clinical decision-making software.

CT or MR series of images serve as input for AI-Rad Companion Organs RT and are acquired as part of a typical scanner acquisition. Once processed by the AI algorithms, generated contours in DICOM-RTSTRUCT format are reviewed in a confirmation window, allowing clinical user to confirm or reject the contours before sending to the target system. Optionally, the user may select to directly transfer the contours to a configurable DICOM node (e.g., the TPS, which is the standard location for the planning of radiation therapy).

The output of AI-Rad Companion Organs RT must be reviewed and, where necessary, edited with appropriate software before accepting generated contours as input to treatment planning steps. The output of AI-Rad Companion Organs RT is intended to be used by qualified medical professionals. The qualified medical professional can perform a complementary manual editing of the contours or add any new contours in the TPS (or any other interactive contouring application supporting DICOM-RT objects) as part of the routine clinical workflow.

AI/ML Overview

Here's a summary of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) summary for AI-Rad Companion Organs RT:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria and reported performance are detailed for both MR and CT contouring algorithms.

MR Contouring Algorithm Performance

Validation Testing Subject	Acceptance Criteria	Reported Device Performance (Average)
MR Contouring Organs	The average segmentation accuracy (Dice value) of all subject device organs should be equivalent or better than the overall segmentation accuracy of the predicate device. The overall fail rate for each organ/anatomical structure is smaller than 15%.	Dice [%]: 85.75% (95% CI: [82.85, 87.58])ASSD [mm]: 1.25 (95% CI: [0.95, 2.02])Fail [%]: 2.75%
	(Compared to Reference Device MRCAT Pelvis (K182888))	AI-Rad Companion Organs RT VA50 – all organs: 86% (83-88) AI-Rad Companion Organs RT VA50 – common organs: 82% (78-84) MRCAT Pelvis (K182888) – all organs: 77% (75-79)

CT Contouring Algorithm Performance

Validation Testing Subject	Acceptance Criteria	Reported Device Performance (Average)
Organs in Predicate Device	All the organs segmented in the predicate device are also segmented in the subject device. The average (AVG) Dice score difference between the subject and predicate device is smaller than 3%.	(The document states "equivalent or had better performance than the predicate device" implicitly meeting this, but does not give a specific numerical difference.)
New Organs for Subject Device	Baseline value defined by subtracting the reference value using 5% error margin in case of Dice and 0.1 mm in case of ASSD. The subject device in the selected reference metric has a higher value than the defined baseline value.	Regional Averages:Head & Neck: Dice 76.5%Head & Neck lymph nodes: Dice 69.2%Thorax: Dice 82.1%Abdomen: Dice 88.3%Pelvis: Dice 84.0%

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

MR Contouring Algorithm Test Set:
- Sample Size: N = 66
- Data Provenance: Retrospective study, data from multiple clinical sites across North America & Europe. The document further breaks this down for different sequences:
  - T1 Dixon W: 30 datasets (USA: 15, EU: 15)
  - T2 W TSE: 36 datasets (USA: 25, EU: 11)
  - Manufacturer: All Siemens Healthineers scanners.
CT Contouring Algorithm Test Set:
- Sample Size: N = 414
- Data Provenance: Retrospective study, data from multiple clinical sites across North American, South American, Asia, Australia, and Europe. This dataset is distributed across three cohorts:
  - Cohort A: 73 datasets (Germany: 14, Brazil: 59) - Siemens scanners only
  - Cohort B: 40 datasets (Canada: 40) - GE: 18, Philips: 22 scanners
  - Cohort C: 301 datasets (NA: 165, EU: 44, Asia: 33, SA: 19, Australia: 28, Unknown: 12) - Siemens: 53, GE: 59, Philips: 119, Varian: 44, Others: 26 scanners

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

The ground truth annotations were "drawn manually by a team of experienced annotators mentored by radiologists or radiation oncologists."
"Additionally, a quality assessment including review and correction of each annotation was done by a board-certified radiation oncologist using validated medical image annotation tools."
The exact number of individual annotators or experts is not specified beyond "a team" and "a board-certified radiation oncologist." Their specific experience level (e.g., "10 years of experience") is not given beyond "experienced" and "board-certified."

4. Adjudication Method for the Test Set

The document implies a consensus/adjudication process: "a quality assessment including review and correction of each annotation was done by a board-certified radiation oncologist." This suggests that initial annotations by the "experienced annotators" were reviewed and potentially corrected by a higher-level expert. The specific number of reviewers for each case (e.g., 2+1, 3+1) is not explicitly stated, but it was at least a "team" providing initial annotations followed by a "board-certified radiation oncologist" for quality assessment/correction.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, the document does not describe a Multi-Reader Multi-Case (MRMC) comparative effectiveness study evaluating how much human readers improve with AI vs. without AI assistance. The validation studies focused on the standalone performance of the algorithm against expert-defined ground truth.

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

Yes, the performance validation described in section 10 ("Performance Software Validation") is a standalone (algorithm only) performance study. The metrics (Dice, ASSD, Fail Rate) compare the algorithm's output directly to the established ground truth. The device produces contours that must be reviewed and edited by trained medical professionals, but the validation tests the AI's direct output.

7. The Type of Ground Truth Used

The ground truth used was expert consensus/manual annotation. It was established by "manual annotation" by "experienced annotators mentored by radiologists or radiation oncologists" and subsequently reviewed and corrected by a "board-certified radiation oncologist." Annotation protocols followed NRG/RTOG guidelines.

8. The Sample Size for the Training Set

MR Contouring Algorithm Training Set:
- T1 VIBE/Dixon W: 219 datasets
- T2 W TSE: 225 datasets
- Prostate (T2W): 960 datasets
CT Contouring Algorithm Training Set: The training dataset sizes vary per organ group:
- Cochlea: 215
- Thyroid: 293
- Constrictor Muscles: 335
- Chest Wall: 48
- LN Supraclavicular, Axilla Levels, Internal Mammaries: 228
- Duodenum, Bowels, Sigmoid: 332
- Stomach: 371
- Pancreas: 369
- Pulmonary Artery, Vena Cava, Trachea, Spinal Canal, Proximal Bronchus: 113
- Ventricles & Atriums: 706
- Descending Coronary Artery: 252
- Penile Bulb: 854
- Uterus: 381

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

For both training and validation data, the ground truth annotations were established using the "Standard Annotation Process." This involved:
- Annotation protocols defined following NRG/RTOG guidelines.
- Manual annotations drawn by a team of experienced annotators mentored by radiologists or radiation oncologists using an internal annotation tool.
- A quality assessment including review and correction of each annotation by a board-certified radiation oncologist using validated medical image annotation tools.
The document explicitly states that the "training data used for the training of the algorithm is independent of the data used to test the algorithm."

Summary

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

April 3, 2024

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 U.S.A. % Kira Morales Regulatory Affairs Manager 40 Liberty Blvd. MALVERN, PA 19355

Re: K232899

Trade/Device Name: AI-Rad Companion Organs RT Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QKB Dated: March 1, 2024 Received: March 4, 2024

Dear Kira Morales:

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/cdrb/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).

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

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

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 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,

Loran Weidner

Lora D. Weidner, Ph.D. Assistant Director Radiation Therapy Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

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

Indications for Use

510(k) Number (if known) K232899

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 and MR predefined structures using deep-leaming-based algorithms.

The output of AI-Rad Companion Organs RT are intended to be used by trained medical professionals.

The software is not intended to automatically detect or contour lesions.

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 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.

510(k) SUMMARY FOR AI-Rad Companion Organs RT

Submitted by: Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard Malvern, PA 19355 Date Prepared: April 2, 2024

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: 65-3Registration Number: 2240869
Manufacturing Site	Siemens Healthcare GmbHHenkestrasse 127Erlangen, Germany 91052Registration Number: 3002808157

2. Contact Person

Kira Morales Senior Regulatory Affairs Specialist Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard Malvern, PA 19335 Phone: +1 (484) 901 - 9471 Email: kira.morales@siemens-healthineers.com

3. Device Name and Classification

Product Name:	AI-Rad Companion Organs RT
Common Name:	Medical Imaging Software
Classification Name:	Medical Image Management and Processing System

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

Image /page/4/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.

Classification Panel: CFR Section: Device Class: Product Code:

4. Predicate Device

Product Name: Common Name: 510(k) Number: Clearance Date: Classification Name: Classification Panel: CFR Section: Device Class: Primary Product Code: Recall Information:

5. Reference Devices

Product Name: Common Name: 510(k) Number: Clearance Date: Classification Name: Classification Panel: CFR Section: Device Class: Primary Product Code:

Product Name:

Common Name: 510(k) Number: Clearance Date: Classification Name: Classification Panel: CFR Section: Device Class: Primary Product Code:

Product Name:

Common Name: 510(k) Number: Clearance Date: Classification Name: Radiology 21 CFR §892.2050 Class II OKB

AI-Rad Companion Organs RT Medical Imaging Software K221305 October 14, 2022 Medical Image Management and Processing System Radiology 21 CFR §892.2050 Class II OKB N/A

MRCAT Pelvis

Medical Imaging Software K182888 April 30, 2019 Medical charged-particle radiation therapy system Radiology 21 CFR §892.2050 Class II MUJ

RT Image Suite

Medical Imaging Software K220783 September 7, 2022 Medical charged-particle radiation therapy system Radiology 21 CFR §892.2050 Class II MUJ

Contour Protégé AI

Medical Imaging Software K231765 November 8, 2023 Medical image management and processing system

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

Image /page/5/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.

Classification Panel: Radiology 21 CFR §892.2050 CFR Section: Device Class: Class II Primary Product Code: OKB Product Name: AI Segmentation Common Name: Medical Image Segmentation Software 510(k) Number: K211881

Clearance Date: Classification Name: Classification Panel: CFR Section: Device Class: Primary Product Code:

September 2, 2021 Medical charged-particle radiation therapy system Radiology 21 CFR §892.2050 Class II MUJ

6. Indications for Use

AI-Rad Companion Organs RT is a post-processing software intended to automatically contour DICOM CT and MR pre-defined structures using deep-learning-based algorithms.

The outputs of AI-Rad Companion Organs RT are intended to be used by trained medical professionals.

The software is not intended to automatically detect or contour lesions.

7. Device Description

{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 cluster of orange dots arranged in a circular pattern.

8. Substantially Equivalent (SE) and Technological Characteristics

The indented use of the predicate device and the subject device are equivalent. The two main difference compared to the predicate, AI-Rad Companion Organs RT (K221305):

MR Contouring Algorithms ●
- o T1 Model for 3 target organs
- o T2 Model for 6 target organs
. Update CT contouring algorithm for 38 new organs

AI-Rad Companion Organs RT VA50 and AI-Rad Companion Organs RT VA40 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 MR contouring has only been validated for Siemens Healthineers' scanner data. The deep learning CT algorithm within AI-Rad Companion Organs RT VA50 has been enhanced from the algorithm in AI-Rad Companion Organs RT VA40 (K221305). All models contained within AI-Rad Companion Organs RT VA50 and AI-Rad Companion Organs RT VA40 (K221305) are locked and cannot be modified by the user.

The subject device, AI-Rad Companion Organs RT, is substantially equivalent with regards to the software features, functionalities, and core algorithms. The performance of the new MR contouring algorithm within AI-Rad Companion Organs RT VA50 is comparable to the algorithm in MRCAT Pelvis (K182888). The performance of the new CT contouring algorithms have been validated against FDA/CE cleared devices or from literature.

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	Predicate Device	Reference Device
DeviceManufacturer	Siemens	Siemens	Philips MedicalSystems MR Finland
Device Name	AI-Rad CompanionOrgans RT	AI-Rad CompanionOrgans RT	MRCAT Pelvis
510(k) Number	TBD	K221305	K182888
processing software	processing software	Ingenia 1.5T and 3.0T
intended to	intended to	MR systems. Intended
automatically contour	automatically contour	Use: MRCAT imaging
DICOM CT and MR	DICOM CT imaging	is intended to provide
pre-defined structures	data using deep-	the operator with
using deep-learning-	learning-based	information of tissue
based algorithms.	algorithms.	properties for radiation
Contours that are	Contours that are	attenuation estimation
generated by AI-Rad	generated by AI-Rad	purposes in photon
Companion Organs RT	Companion Organs RT	external beam
may be used as input	may be used as input	radiotherapy treatment
for clinical workflows	for clinical workflows	planning. Indications
including external	including external	for use: MRCAT
beam radiation therapy	beam radiation therapy	Pelvis is indicated for
treatment planning.	treatment planning. AI-	radiotherapy treatment
AI-Rad Companion	Rad Companion	planning of soft tissue
Organs RT must be	Organs RT must be	cancers in the pelvic
used in conjunction	used in conjunction	region.
with appropriate	with appropriate
software such as	software such as
Treatment Planning	Treatment Planning
Systems and	Systems and
Interactive Contouring	Interactive Contouring
applications, to review,	applications, to review,
edit, and accept	edit, and accept
contours generated by	contours generated by
AI-Rad Companion	AI-Rad Companion
Organs RT.	Organs RT.
The outputs of AI-Rad	The output of AI-Rad
Companion Organs RT	Companion Organs RT
are intended to be used	in the format of
by trained medical	RTSTRUCT objects
professionals.	are intended to be used
The software is not	by trained medical
intended to	professionals.
automatically detect or	The software is not
contour lesions	intended to
	automatically detect or
	contour lesions. Only
	DICOM images of
Algorithm
Segmentation of Organ at Risk in the Anatomic Regions	Deep Learning	Deep Learning	Machine-learning
Compatible Modality	CT & MR Images	CT Images	MR
Compatible Scanner Models	CT: Head & Neck,Thorax, Abdomen & PelvisHead & Neck lymph nodes(166 OAR)MR: Pelvis (9 OAR)	CT: Head & Neck,Thorax, Abdomen & PelvisHead & Neck lymph nodes(128 OAR)	Male and female pelvis, with soft-tissue cancer in the anatomical pelvic region below L1 vertebra, including (post-operative) prostate, rectum, anus, bladder and cervix
Compatible Treatment Planning System	No Limitation on scanner model for CT.Siemens Healthineers' data only for MR.DICOM compliance required.	No Limitation on scanner model,DICOM compliance required.	Ingenia 1.5T and 3.0T MR-RT, Ingenia Ambition 1.5T MR-RT and Ingenia Elition 3.0T MR-RT
Contraindications	No Limitation on TPS model, DICOM compliance required.	No Limitation on TPS model, DICOM compliance required.	No Limitation on TPS model, DICOM compliance required.
Target Population	Adult use only	Adult use only	Adult use only
	AI-Rad Companion Organs RT is designed for use only in adult populations.AI-Rad Companion Organs RT is designed for any patient for whom relevant modality scans are available.	AI-Rad Companion Organs RT is designed for use only in adult populations.AI-Rad Companion Organs RT is designed for any patient for whom relevant modality scans are available. More specifically, the software is validated on previously acquired CT DICOM volumes for radiation therapy treatment planning, including, head and	No information publicly available
	adult patients are considered to be valid input.

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

Image /page/7/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.

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

Image /page/8/Picture/0 description: The image shows 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.

	neck, thorax, abdomen, and pelvis.
Clinicalcondition thedevice isintended todiagnose, treat ormanage	Limited to patientspreviously selected forRadiation Therapy.	Limited to patientspreviously selected forRadiation Therapy.	No informationpublicly available
SoftwareArchitecture	AI-Rad Companion(Engine) architectureenabling thedeployment of AI RadCompanion Organs RTusing Edge and in theCloud. The UI isprovided using a web-based interface.	AI-Rad Companion(Engine) architectureenabling thedeployment of AI RadCompanion Organs RTusing Edge and in theCloud. The UI isprovided using a web-based interface.	No informationpublicly available
DeploymentFeature	Edge & CloudDeployment	Edge & CloudDeployment	No informationpublicly available
Organ Templates	Creating, editing anddeletion of organtemplates. Customizepredefined structuredatabase with mappingto internationalnomenclature schemes.	Creating, editing anddeletion of organtemplates. Customizepredefined structuredatabase with mappingto internationalnomenclature schemes.	No informationpublicly available
Automatedworkflow	AI-Rad CompanionOrgans RTautomaticallyprocesses input imagedata and sends theresults as DICOM-RTStructure Sets to auser-configurabletarget node.	AI-Rad CompanionOrgans RTautomaticallyprocesses input imagedata and sends theresults as DICOM-RTStructure Sets to auser-configurabletarget node.	Automatic contouring
Contourvisualization andediting feature	AI-Rad CompanionOrgans RT providesbasic result preview ofautomaticsegmentation results,and no editing featureof the automaticsegmented contour.	AI-Rad CompanionOrgans RT providesbasic result preview ofautomaticsegmentation results,and no editing featureof the automaticsegmented contour.	No informationpublicly available
SegmentationPerformance	MR: The targetperformance wasvalidated using 66cases to validate theoverall performance ofthe MR contouring.CT: The targetperformance wasvalidated using 414cases distributed tothree cohorts.Both: To objectivelyevaluate the targetperformance, the DICEcoefficient, theabsolute symmetricsurface distance(ASSD) and the failrate was evaluated.The segmentationperformance of thesubject was equivalentto the overallperformance comparedto the predicate,reference device andcomparable literature& devices.	The target performancewas validated using157 cases distributed totwo cohorts. Cohort Ais clinical routinetreatment planning CTand it is split into twosub-cohort and CohortB is PET-CT data. Toobjectively 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.	The mean and standarddeviation Dicecoefficients, along withthe lower 95thpercentile confidencebound were calculated.
User Interface -Results Preview(Confirmation)	Basic visualizationfunctionality oforiginal data andgenerated contours	Basic visualizationfunctionality oforiginal data andgenerated contours	No informationpublicly available
User InterfaceConfiguration	Configuration UI	Configuration UI	No informationpublicly available
AutomatedWorkflow to TPS	Results send toConfirmation UI &Optional bypassing ofConfirmation UI toTPS	Results send toConfirmation UI &Optional bypassing ofConfirmation UI toTPS	No informationpublicly available
Human Factors	Design to be used bytrained clinicians.	Design to be used bytrained clinicians.	Designed to be used bytrained clinicians

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

Image /page/10/Picture/0 description: The image shows the Siemens Healthineers logo. The word "SIEMENS" is in teal, and the word "Healthineers" is in orange. To the right of the words is an orange graphic of a series of dots.

Table 1: Indications for Use and Segmentation Feature Comparison

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

SIEME Healthineers

The conclusions from all verification and validation data suggests that these enhancements are equivalent with respect to safety and effectiveness of the predicate device. These modifications do not change the intended use of the product. Siemens is of opinion that AI-Rad Companion Organs RT VA50 is substantially equivalent to the currently marketed device, AI-Rad Companion Organs RT (K221305).

9. Nonclinical Tests

Non-clinical tests were conducted to test 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 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 2.

RecognitionNumber	ProductArea	Title of Standard	ReferenceNumber andDate	StandardsDevelopmentOrganization
5-129	General	Medical Devices –Application of usabilityengineering to medicaldevices	62366-1 Ed1.1 2020-06CV	IEC
5-125	General	Medical Devices –application of riskmanagement to medicaldevices	14971:2019-12	ISO
13-79	Software/Informatics	Medical device software –software life cycleprocesses [IncludingAmendment 1 (2016)]	62304 Ed 1.12015-06 CV	AAMIANSIIEC
12-349	Radiology	Digital Imaging andCommunications inMedicine (DICOM) Set	PS 3.1 – 3.202022d	NEMA
5-134	General	Medical devices – symbolsto be used with informationto be supplied by themanufacturer - Part 1:General Requirements	15223-1Fourth edition2021-07	ISOIEC
13-97	Software/Informatics	Health software – Part 1:General requirements forproduct safety	82304-1Edition 1.02016-10	IEC

Table 2: List of recognized standards

Verification and Validation

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

Image /page/12/Picture/0 description: The image shows 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 pattern.

Software documentation level, per FDA's Guidance Document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" issued on June 14, 2023, 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.

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 recommendations 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.

10. Performance Software Validation

To validate the AI-Rad Companion Organs RT software from clinical perspective, the autocontouring algorithms underwent a scientific evaluation. The results of clinical data-based software validation for the subject device AI-Rad Companion Organs RT (SW VA50A) demonstrated equivalent performance in comparison to the predicate device (SW VA40A, K221305). The performance of the enhanced CT organ contouring algorithm is comparable to the predicate device and comparable reference literature and cleared devices. The performance of the MR contouring algorithms is compared to the reference device, MRCAT Pelvis (K182888). A complete scientific evaluation report is provided in support of the device modifications.

MR Contouring Algorithm Performance

The performance of the AI-Rad Companion Organs RT has been validated in a retrospective performance study on MR data previously acquired (N= 66, data from multiple clinical sites across North America & Europe). Ground truth annotations were established following RTOG and clinical guidelines using manual annotation. The dice coefficient and the absolute symmetric surface distance (ASSD), were determined to quantify the similarity between the automatically contoured OAR and the manually delineated contours (ground truth). We also introduce the failure rate in this section. The results of subject device were equivalent or had better performance than the predicate device.

To have a fair comparison between reference and subject device, we compute the average Dice coefficient only for common organs available in both devices (Prostate, Bladder, Rectum, Penile Bulb and Seminal Vesicle).

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

Image /page/13/Picture/0 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 words is a graphic of several orange dots.

Validation Testing Subject	Acceptance Criteria
MR Contouring Organs	The average segmentation accuracy (Dice value) of all subject device organs should be equivalent or better than the overall segmentation accuracy of the predicate device The overall fail rate for each organ/anatomical structure is smaller than 15%

Table 3: Acceptance Criteria of AIRC Organs RT VA50

AI-Rad Companion Organs RT VA50A(MR Contouring)
Dice [%]			ASSD [mm]			Fail [%]
Avg	Std	95 % CIBootstrap	Avg	Std	95 % CIBootstrap	2.75
85.75	6.48	[82.85, 87.58]	1.25	1.28	[0.95, 2.02]

Table 4: Performance results of subject device

	Dice % Average	95% CI
AI-Rad Companion Organs RT VA50 – all organs	86	(83-88)
AI-Rad Companion Organs RT VA50 – commonorgans	82	(78-84)
MRCAT Pelvis (K182888) – all organs	77	(75-79)

Table 5: Performance results of subject device compared to the reference device

Organ Name	No.Study	Dice (%)
		AVG	STD	MED	95%CI	AVG	STD	MED	95%CI
Bladder	36	91.32	6.85	93.48	(87.69 92.87)	0.91	1.82	0.43	(0.54 2.09)
Rectum	36	84.87	6.21	86.61	(82.56 86.67)	1.32	1.64	0.74	(0.97 2.23)
Anal Canal	36	75.78	7.43	77.43	(73.17 78.04)	1.19	0.65	1.01	(1.0 1.44)
Penile Bulb	36	82.29	6.89	82.61	(79.82 84.46)	0.55	0.46	0.41	(1.27 4.77)
Seminal Vesicle	36	66.08	18.65	72.97	(57.19 71.3)	2.06	3.63	1.1	(1.27 4.77)
Prostate	36	84.76	5.32	85.68	(82.59 86.44)	0.94	0.62	0.78	(0.78 1.27)
Femur Right	30	94.29	2.21	94.63	(92.94 94.82)	1.1	0.45	1.03	(0.99 1.37)
Femur Left	30	94.38	2.88	95.01	(92.68 95.09)	1.06	0.52	0.99	(0.94 1.36)
Body	30	98.01	1.88	98.89	(97.0 98.49)	2.12	1.74	1.2	(1.6 2.88)

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

Image /page/14/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.

Average

1.25 87.48 (82.85 87.58) 1.28 0.85 2.02) 85.75 6.48 (0.95

Table 6: Detailed Performance Results

	T1 Dixon W	T2 W TSE
# of Datasets	30	36
Data Origin	USA: 15EU:15	USA: 25EU: 11
Age	22 years and older	22 years and older
Manufacturer	Siemens Healthineers	Siemens Healthineers
Annotated Organs	BodyFemoral Head RightFemoral Head Left	Anal Canal, Prostate, Rectum, PenileBulb, Seminal Vesicle, Bladder
Slice Thickness	< 4mm	< 4mm
Field Strength	1.5T: 193.0T: 11	1.5T: 143.0T: 22

Table 7: Validation Testing Data Information

	T1 VIBE/Dixon W	T2 W TSE	Prostate (T2W)
# of Datasets	219	225	960
Data Origin	USA: 59EU:160	USA: 225	USA & EU
Age	22 years and older	22 years and older	62 (average)
Manufacturer	Siemens Healthineers	Siemens Healthineers	Siemens Healthineers
Annotated	Body	Anal Canal, Rectum,	Prostate
Organs	Femoral Head Right	Penile Bulb, Seminal
	Femoral Head Left	Vesicle, Bladder
Field	1.5T: 59	1.5T: 83	1.5T & 3.0T
Strength	3.0T: 160	3.0T: 142

Table 8: Training Dataset Characteristics

CT Contouring Algorithm Performance

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=414, data from multiple clinical sites across the North American, South American, Asia, Australia and Europe). Ground truth annotations were established following RTOG and clinical guidelines using manual annotation. The mean and standard deviation Dice coefficients, along with the lower 95th percentile confidence bound, were calculated for each organ in the subject device. The results of subject device were equivalent or had better performance than the predicate device. To encountered for different datasets, variation in annotation, we first calculate the

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

Image /page/15/Picture/0 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 words is a graphic of orange dots.

average of multiple references or the average of anatomical region for the specific organ or anatomical region. We then define the baseline value by subtracting the reference value using 5% error margin in case of Dice and 0.1 mm in case of ASSD.

The performance results of the subject device for the new CT organs is comparable to the reference literature & cleared devices. Here equivalence for the new organs is defined such that the selected reference metric has a higher value than the defined baseline. For existing organs, the average (AVG) Dice score difference between the subject device and predicate device is smaller than 3%.

Validation Testing Subject	Acceptance Criteria
Organs in Predicate Device	All the organs segmented in the predicate device are also segmented in the subject device The average (AVG) Dice score difference between the subject and predicate device is smaller than 3%
New Organs for Subject Device	Baseline value defined by subtracting the reference value using 5% error margin in case of Dice and 0.1 mm in case of ASSD The subject device in the selected reference metric has a higher value than the defined baseline value.

Table 3: Acceptance Criteria of AIRC Organs RT VA50

	Avg	Std	95% CI
Head & Neck	76.5	12.8	[70.9, 80.8]
Head & Neck lymphnodes	69.2	9.5	[65.7, 72.5]
Thorax	82.1	8.4	[79.6, 83.9]
Abdomen	88.3	8.3	[80.9, 92.2]

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

Image /page/16/Picture/0 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 words is a graphic of orange dots.

Pelvis	84.0	6.5	[80.7, 86.7]
--------	------	-----	--------------

Table 4: Performance summary of the subject device CT contouring

Organ Name	No.	Dice (%)
		AVG	STD	MED	95%CI	AVG	STD	MED	95%CI
Duodenum	76	77.3	10.4	79.7	[74.5, 79.3]	2.6	2	1.9	[2.2, 3.1]
Large Bowel	102	89.6	4.5	90.8	[88.7, 90.4]	2.1	2.6	1.4	[1.8, 2.9]
Sigmoid	74	79.9	10.6	82.2	[77.2, 82.1]	3.8	3.3	2.6	[3.1, 4.7]
Small Bowel	76	88.5	4.2	89.3	[87.4, 89.4]	1.3	0.7	1.1	[1.1, 1.5]
Uterus	25	87.8	4.2	87.8	[85.7, 89.1]	1.7	1.1	1.5	[1.4, 2.4]
Penile Bulb	30	74	9.1	75.5	[70.5, 77.0]	1.7	0.7	1.6	[1.4, 1.9]
Left Cochlea	25	74.8	16.1	77.8	[62.3, 78.6]	0.6	1.3	0.4	[0.3, 1.7]
Right Cochlea	25	79.9	4.8	81.7	[77.9, 81.7]	0.3	0.1	0.3	[0.3, 0.4]
Inferior PharyngealConstrictor Muscle	30	78.2	4.8	78.6	[76.4, 79.9]	0.8	0.3	0.7	[0.7, 0.9]
Middle PharyngealConstrictor Muscle	30	67.2	7.5	68.3	[64.4, 69.8]	0.9	0.3	0.8	[0.8, 1.1]
Superior PharyngealConstrictor Muscle	30	66.1	5.5	66.7	[64.1, 68.0]	0.8	0.2	0.8	[0.8, 0.9]
Thyroid	30	84.4	3.4	84.4	[83.2, 85.6]	0.7	0.2	0.7	[0.6, 0.7]
Pancreas	31	68.4	13.6	72.8	[62.9, 72.6]	3.5	2.5	2.7	[2.8, 4.6]
Stomach	31	90.7	4.2	91.6	[88.9, 92.0]	2	1.6	1.5	[1.6, 2.8]
Left AnteriorDescendingCoronary Artery	57	47.6	9.7	47.6	[45.1, 50.1]	4.1	3.8	2.9	[3.4, 5.4]
Left Atrium	57	86.1	4.8	86.9	[84.7, 87.2]	1.8	0.8	1.6	[1.6, 2.0]
Left VentricleEndocardium	57	83.6	5.3	84.5	[81.9, 84.7]	2.3	0.8	2.2	[2.1, 2.5]
Left Ventricle	57	85.9	4.1	86.8	[84.8, 86.9]	2.7	0.9	2.5	[2.5, 2.9]
Right Atrium	57	79.5	8.8	80.9	[76.6, 81.3]	2.7	1.3	2.4	[2.4, 3.1]
Right Ventricle	57	83.4	3.4	84.2	[82.5, 84.3]	2.3	0.6	2.2	[2.2, 2.5]
Left Chest Wall	28	92.3	1.5	92.3	[91.7, 92.8]	1	0.2	0.9	[0.9, 1.1]
Right Chest Wall	28	92.6	1.2	92.5	[92.1, 93.1]	0.9	0.2	1	[0.9, 1.0]
Inferior Vena Cava	27	76.2	12.6	80	[70.2, 80.1]	2	1.7	1.5	[1.6, 3.0]
Proximal Bronchus	27	84.2	5	85.6	[81.8, 85.7]	1.1	0.4	1.1	[1.0, 1.3]
Pulmonary Artery	27	80	5.7	80.3	[77.4, 81.8]	2.3	0.9	2	[2.0, 2.7]
Spinal Canal	27	85.2	7.1	87.9	[81.0, 87.1]	1.3	2.2	0.7	[0.8, 2.9]
Superior Vena Cava	27	79	6.8	80.6	[76.0, 81.2]	1.5	0.8	1.3	[1.3, 1.9]
Trachea	27	88.7	4.5	89.7	[86.6, 90.1]	1	0.5	0.8	[0.8, 1.2]
Left Axilla Level I	24	81.5	5.4	82.7	[78.8, 83.3]	2.6	1.4	2	[2.2, 3.3]
Left Axilla Level II	24	79.2	6.7	80.3	[76.2, 81.6]	1.8	0.7	1.7	[1.6, 2.2]
Left Axilla Level III	24	75.4	4.1	75.6	[73.8, 77.1]	1.5	0.4	1.5	[1.3, 1.6]
Left InternalMammary	24	58.6	8	60.5	[55.2, 61.6]	1.9	1.4	1.3	[1.4, 2.5]
Left Supraclavicular	24	79.5	8.3	81.8	[75.3, 82.2]	2	1.1	1.8	[1.7, 2.6]
Right Axilla Level I	24	80	7.1	82.3	[76.6, 82.4]	3	2.5	2.2	[2.3, 4.7]
Right Axilla Level II	24	77.6	6.9	77	[75.0, 80.4]	2	0.7	2.1	[1.7, 2.3]
Right Axilla Level III	24	75.9	7.6	77.4	[71.7, 78.3]	1.6	1	1.3	[1.4, 2.2]

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

Image /page/17/Picture/0 description: The image shows the Siemens Healthineers logo. 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 arranged in a pattern.

Right InternalMammary	24	62.6	9.4	64.1	[56.8, 65.3]	1.6	1.4	1.1	[1.2, 2.4]
RightSupraclavicular	24	79.7	6.7	80.9	[76.2, 81.8]	2	0.9	1.7	[1.7, 2.5]

Table 5: Detailed Performance evaluation of the new organs in the subject device

	Cohort A	Cohort B	Cohort C
# of Datasets	73	40	301
# of Clinical Sites	3(Germany: 14, Brazil: 59)	4(Canada: 40)	25(NA: 165, EU: 44, Asia:33, SA: 19, Australia:28, Unknown: 12)
Sex	Male: 48Female: 25	Male: 19Female: 21	Male: 53Female: 50Unknown: 198
Age	<30 : 030 - 50: 050 - 70: 4>= 70: 4Unknown: 110*unknown due to dataminimization oncustomer site	<30: 030 - 50: 350 – 70: 25>70: 12	<30: 030 - 50: 350 – 70: 25>70: 12
Manufacturer	Siemens: 73	GE: 18Philips: 22	Siemens: 53GE: 59Philips: 119Varian: 44Others: 26
Body Region	Head & Neck: 24Thorax & Abdomen: 20Pelvis: 29	Head & Neck: 40	Head & Neck: 50Thorax: 81Abdomen: 115Pelvis: 55
Slice Thickness	<= 1: 41 – 2: 482 - 3 : 20>3: 1	<= 1: 01 - 2: 62-3:31>3: 3	<= 1: 151 - 2: 1532-3:118>3: 15

Table 7: Validation Testing Data Information

Organ Group	No. Training	No. Validation
Cochlea	215	24
Thyroid	293	56
Constrictor Muscles	335	89
Chest Wall	48	12
LN Supraclavicular, Axilla Levels,Internal Mammaries	228	28

{18}------------------------------------------------

Image /page/18/Picture/0 description: The image contains the Siemens Healthineers logo. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the words is an orange graphic of several small circles arranged in a pattern.

Duodenum, Bowels, Sigmoid	332	84
Stomach	371	92
Pancreas	369	92
Pulmonary Artery, Vena Cava, Trachea, Spinal Canal, Proximal Bronchus	113	34
Ventricles & Atriums	706	273
Descending Coronary Artery	252	45
Penile Bulb	854	213
Uterus	381	94

Table 8: Training Dataset Characteristics

Standard Annotation Process

In both the annotation process for the training and validation testing data, the annotation protocols for the OAR were defined following the NRG/RTOG guidelines. The ground truth annotations were drawn manually by a team of experienced annotators mentored by radiologists or radiation oncologists using an internal annotation tool. Additionally, a quality assessment including review and correction of each annotation was done by a board-certified radiation oncologist using validated medical image annotation tools.

Validation Testing & Training Data Independence

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

11. Clinical Tests

No clinical tests were conducted to test the performance and functionality of the modifications introduced within AI-Rad Companion Organs RT. Verification and validation of the 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. 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 14971:2019 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.

13. Conclusion

{19}------------------------------------------------

Image /page/19/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 arranged in a circular pattern.

Based on the discussion and validation testing and performance data above, the proposed device is determined to be as safe and effective as its predicate device, AI-Rad Companion Organs RT VA40 (K221305). In addition, the proposed device performs comparably to the reference device, MRCAT Pelvis (K182888).

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).