K Number

Device Name

AI-Rad Companion Organs RT

Manufacturer

Siemens Medical Solutions U.S.A.

Date Cleared

2024-04-03

(198 days)

Product Code

QKB OKB REC SEP

Regulation Number

892.2050

Intended Use

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.

More Information

Contact

Type

Center

Panel

Date Received

Product Code

Subsequent Product Codes

Applicant Name (Manufacturer)

Device Name

Decision

Street 1

Street 2

City

State

Country Code

ZIP

Postal Code

Class Advise Committee

SSP Indicator

Third Party Reviewed

Expedited Review

Predicate Devices

K182888

Reference Devices

K182888, K220783, K231765, K211881

AI/ML (Artificial Intelligence / Machine Learning)

Yes
The intended use and device description explicitly state the use of "deep-learning-based algorithms" and "AI algorithms" for automatic contouring. The training and test set descriptions further detail the data used to train these algorithms.

Therapeutic

No.
This device is a post-processing software that automatically contours anatomical structures for use in clinical workflows, such as radiation therapy treatment planning, but it does not directly treat or diagnose.

Diagnostic

The "Intended Use / Indications for Use" states that the software is for "post-processing" and "is not intended to automatically detect or contour lesions." Additionally, the "Device Description" explicitly states, "AI-Rad Companion Organs RT is not intended to be used as a standalone diagnostic device and is not a clinical decision-making software."

SaMD (Software as a Medical Device)

Yes

The device is described as "post-processing software" and its function is to automatically contour structures from existing medical images. It explicitly states it is not a standalone diagnostic device and must be used in conjunction with other software like Treatment Planning Systems. There is no mention of any accompanying hardware component.

IVD (In Vitro Diagnostic)

Based on the provided information, this device is not an In Vitro Diagnostic (IVD).

Here's why:

Intended Use: The intended use clearly states that the software is for "post-processing software intended to automatically contour DICOM CT and MR predefined structures." It is used as input for clinical workflows like radiation therapy treatment planning. It is explicitly stated that it is "not intended to automatically detect or contour lesions" and is "not a standalone diagnostic device and is not a clinical decision-making software."
Device Description: The description reinforces that the software 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." It emphasizes that the output "must be reviewed and, where necessary, edited with appropriate software before accepting generated contours as input to treatment planning steps."
Nature of IVDs: In Vitro Diagnostics are medical devices intended to perform tests on samples taken from the human body (like blood, urine, tissue) to provide information about a person's health. This software does not perform any tests on biological samples. It processes medical images.

The software is a medical image processing tool used to assist in the planning of radiation therapy, which is a treatment, not a diagnostic process in the sense of an IVD.

PCCP (Predetermined Change Control Plan) Authorized

No
The letter does not explicitly state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.

Overview

Intended Use / Indications for Use

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.

Product codes

QKB

Device Description

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.

Mentions image processing

Yes

Mentions AI, DNN, or ML

Yes

Input Imaging Modality

DICOM CT and MR

Anatomical Site

CT: Head & Neck, Thorax, Abdomen & Pelvis, Head & Neck lymph nodes (166 OAR)
MR: Pelvis (9 OAR)

Indicated Patient Age Range

Adult use only
22 years and older

Intended User / Care Setting

trained medical professionals / clinicians

Description of the training set, sample size, data source, and annotation protocol

MR Training Data:

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

CT Training Data:

Cochlea: 215 training sets, 24 validation sets.
Thyroid: 293 training sets, 56 validation sets.
Constrictor Muscles: 335 training sets, 89 validation sets.
Chest Wall: 48 training sets, 12 validation sets.
LN Supraclavicular, Axilla Levels, Internal Mammaries: 228 training sets, 28 validation sets.
Duodenum, Bowels, Sigmoid: 332 training sets, 84 validation sets.
Stomach: 371 training sets, 92 validation sets.
Pancreas: 369 training sets, 92 validation sets.
Pulmonary Artery, Vena Cava, Trachea, Spinal Canal, Proximal Bronchus: 113 training sets, 34 validation sets.
Ventricles & Atriums: 706 training sets, 273 validation sets.
Descending Coronary Artery: 252 training sets, 45 validation sets.
Penile Bulb: 854 training sets, 213 validation sets.
Uterus: 381 training sets, 94 validation sets.

Annotation Protocol (for both 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.

Description of the test set, sample size, data source, and annotation protocol

MR Validation Testing Data:

Sample Size: N=66
Data Origin: Multiple clinical sites across North America & Europe.
T1 Dixon W (N=30): USA: 15, EU: 15. Age: 22 years and older. Manufacturer: Siemens Healthineers. Annotated Organs: Body, Femoral Head Right, Femoral Head Left. Slice Thickness: = 70: 4, Unknown: 110. Manufacturer: Siemens: 73. Body Region: Head & Neck: 24, Thorax & Abdomen: 20, Pelvis: 29. Slice Thickness: 3: 1.
Cohort B (N=40): 4 clinical sites (Canada: 40). Sex: Male: 19, Female: 21. Age: 70: 12. Manufacturer: GE: 18, Philips: 22. Body Region: Head & Neck: 40. Slice Thickness: 3: 3.
Cohort C (N=301): 25 clinical sites (NA: 165, EU: 44, Asia: 33, SA: 19, Australia: 28, Unknown: 12). Sex: Male: 53, Female: 50, Unknown: 198. Age: 70: 12. Manufacturer: Siemens: 53, GE: 59, Philips: 119, Varian: 44, Others: 26. Body Region: Head & Neck: 50, Thorax: 81, Abdomen: 115, Pelvis: 55. Slice Thickness: 3: 15.
Annotation Protocol: Ground truth annotations were established following RTOG and clinical guidelines using manual annotation.

Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)

Study Type: Retrospective performance studies.
MR Contouring Algorithm Performance:

Sample Size: N=66
Key Metrics: Dice coefficient and Absolute Symmetric Surface Distance (ASSD). Failure rate.
Acceptance Criteria: 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%.
Performance Results (Subject device):
- Dice [%] Avg: 85.75, Std: 6.48, 95 % CI Bootstrap: [82.85, 87.58]
- ASSD [mm] Avg: 1.25, Std: 1.28, 95 % CI Bootstrap: [0.95, 2.02]
- Fail [%]: 2.75
Comparison to Reference Device (MRCAT Pelvis K182888):
- AI-Rad Companion Organs RT VA50 – all organs: Dice % Average 86 (95% CI 83-88)
- AI-Rad Companion Organs RT VA50 – common organs: Dice % Average 82 (95% CI 78-84)
- MRCAT Pelvis (K182888) – all organs: Dice % Average 77 (95% CI 75-79)
Detailed Organ Performance (N=36 where applicable):
- Bladder: Dice 91.32 (Std 6.85), ASSD 0.91 (Std 1.82)
- Rectum: Dice 84.87 (Std 6.21), ASSD 1.32 (Std 1.64)
- Anal Canal: Dice 75.78 (Std 7.43), ASSD 1.19 (Std 0.65)
- Penile Bulb: Dice 82.29 (Std 6.89), ASSD 0.55 (Std 0.46)
- Seminal Vesicle: Dice 66.08 (Std 18.65), ASSD 2.06 (Std 3.63)
- Prostate: Dice 84.76 (Std 5.32), ASSD 0.94 (Std 0.62)
- Femur Right (N=30): Dice 94.29 (Std 2.21), ASSD 1.1 (Std 0.45)
- Femur Left (N=30): Dice 94.38 (Std 2.88), ASSD 1.06 (Std 0.52)
- Body (N=30): Dice 98.01 (Std 1.88), ASSD 2.12 (Std 1.74)

CT Contouring Algorithm Performance:

Sample Size: N=414
Key Metrics: Dice coefficient and Absolute Symmetric Surface Distance (ASSD).
Acceptance Criteria:
- For organs in Predicate Device: All organs segmented in predicate are also in subject device. Average Dice score difference between subject and predicate device smaller than 3%.
- For New Organs for Subject Device: Baseline value defined by subtracting reference value using 5% error margin for Dice and 0.1 mm for ASSD. Subject device in selected reference metric has higher value than defined baseline value.
Performance Summary (Subject device CT contouring):
- Head & Neck: Avg Dice 76.5, Std 12.8, 95% CI [70.9, 80.8]
- Head & Neck lymph nodes: Avg Dice 69.2, Std 9.5, 95% CI [65.7, 72.5]
- Thorax: Avg Dice 82.1, Std 8.4, 95% CI [79.6, 83.9]
- Abdomen: Avg Dice 88.3, Std 8.3, 95% CI [80.9, 92.2]
- Pelvis: Avg Dice 84.0, Std 6.5, 95% CI [80.7, 86.7]
Detailed Performance Evaluation of new organs in subject device (sample sizes vary by organ):
- Duodenum (N=76): Dice 77.3, ASSD 2.6
- Large Bowel (N=102): Dice 89.6, ASSD 2.1
- Sigmoid (N=74): Dice 79.9, ASSD 3.8
- Small Bowel (N=76): Dice 88.5, ASSD 1.3
- Uterus (N=25): Dice 87.8, ASSD 1.7
- Penile Bulb (N=30): Dice 74, ASSD 1.7
- Left Cochlea (N=25): Dice 74.8, ASSD 0.6
- Right Cochlea (N=25): Dice 79.9, ASSD 0.3
- Inferior Pharyngeal Constrictor Muscle (N=30): Dice 78.2, ASSD 0.8
- Middle Pharyngeal Constrictor Muscle (N=30): Dice 67.2, ASSD 0.9
- Superior Pharyngeal Constrictor Muscle (N=30): Dice 66.1, ASSD 0.8
- Thyroid (N=30): Dice 84.4, ASSD 0.7
- Pancreas (N=31): Dice 68.4, ASSD 3.5
- Stomach (N=31): Dice 90.7, ASSD 2
- Left Anterior Descending Coronary Artery (N=57): Dice 47.6, ASSD 4.1
- Left Atrium (N=57): Dice 86.1, ASSD 1.8
- Left Ventricle Endocardium (N=57): Dice 83.6, ASSD 2.3
- Left Ventricle (N=57): Dice 85.9, ASSD 2.7
- Right Atrium (N=57): Dice 79.5, ASSD 2.7
- Right Ventricle (N=57): Dice 83.4, ASSD 2.3
- Left Chest Wall (N=28): Dice 92.3, ASSD 1
- Right Chest Wall (N=28): Dice 92.6, ASSD 0.9
- Inferior Vena Cava (N=27): Dice 76.2, ASSD 2
- Proximal Bronchus (N=27): Dice 84.2, ASSD 1.1
- Pulmonary Artery (N=27): Dice 80, ASSD 2.3
- Spinal Canal (N=27): Dice 85.2, ASSD 1.3
- Superior Vena Cava (N=27): Dice 79, ASSD 1.5
- Trachea (N=27): Dice 88.7, ASSD 1
- Left Axilla Level I (N=24): Dice 81.5, ASSD 2.6
- Left Axilla Level II (N=24): Dice 79.2, ASSD 1.8
- Left Axilla Level III (N=24): Dice 75.4, ASSD 1.5
- Left Internal Mammary (N=24): Dice 58.6, ASSD 1.9
- Left Supraclavicular (N=24): Dice 79.5, ASSD 2
- Right Axilla Level I (N=24): Dice 80, ASSD 3
- Right Axilla Level II (N=24): Dice 77.6, ASSD 2
- Right Axilla Level III (N=24): Dice 75.9, ASSD 1.6
- Right Internal Mammary (N=24): Dice 62.6, ASSD 1.6
- Right Supraclavicular (N=24): Dice 79.7, ASSD 2

Key Results: The results of the subject device (AI-Rad Companion Organs RT SW VA50A) were equivalent or had better performance than the predicate device (AI-Rad Companion Organs RT SW VA40A). 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).

Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)

Dice Coefficient (Dice [%]), Absolute Symmetric Surface Distance (ASSD [mm]), Fail rate (Fail [%]).

Predicate Device(s)

K221305

Reference Device(s)

K182888, K220783, K231765, K211881

Predetermined Change Control Plan (PCCP) - All Relevant Information

Not Found

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).

Summary

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

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

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."

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 Boulevard
Malvern, PA 19355
Mail Code: 65-3
Registration Number: 2240869 |
|----------------------|-------------------------------------------------------------------------------------------------------------------------------------|
| Manufacturing Site | Siemens Healthcare GmbH
Henkestrasse 127
Erlangen, Germany 91052
Registration 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

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

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

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
Device
Manufacturer	Siemens	Siemens	Philips Medical
Systems MR Finland
Device Name	AI-Rad Companion
Organs RT	AI-Rad Companion
Organs 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 & Pelvis
Head & Neck lymph nodes
(166 OAR)
MR: Pelvis (9 OAR)	CT: Head & Neck,
Thorax, Abdomen & Pelvis
Head & 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.

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.

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.

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.
Clinical
condition the
device is
intended to
diagnose, treat or
manage	Limited to patients
previously selected for
Radiation Therapy.	Limited to patients
previously selected for
Radiation Therapy.	No information
publicly available
Software
Architecture	AI-Rad Companion
(Engine) architecture
enabling the
deployment of AI Rad
Companion Organs RT
using Edge and in the
Cloud. The UI is
provided using a web-
based interface.	AI-Rad Companion
(Engine) architecture
enabling the
deployment of AI Rad
Companion Organs RT
using Edge and in the
Cloud. The UI is
provided using a web-
based interface.	No information
publicly available
Deployment
Feature	Edge & Cloud
Deployment	Edge & Cloud
Deployment	No information
publicly available
Organ Templates	Creating, editing and
deletion of organ
templates. Customize
predefined structure
database with mapping
to international
nomenclature schemes.	Creating, editing and
deletion of organ
templates. Customize
predefined structure
database with mapping
to international
nomenclature schemes.	No information
publicly available
Automated
workflow	AI-Rad Companion
Organs RT
automatically
processes input image
data and sends the
results as DICOM-RT
Structure Sets to a
user-configurable
target node.	AI-Rad Companion
Organs RT
automatically
processes input image
data and sends the
results as DICOM-RT
Structure Sets to a
user-configurable
target node.	Automatic contouring
Contour
visualization and
editing feature	AI-Rad Companion
Organs RT provides
basic result preview of
automatic
segmentation results,
and no editing feature
of the automatic
segmented contour.	AI-Rad Companion
Organs RT provides
basic result preview of
automatic
segmentation results,
and no editing feature
of the automatic
segmented contour.	No information
publicly available
Segmentation
Performance	MR: The target
performance was
validated using 66
cases to validate the
overall performance of
the MR contouring.
CT: The target
performance was
validated using 414
cases distributed to
three cohorts.
Both: To objectively
evaluate the target
performance, the DICE
coefficient, the
absolute symmetric
surface distance
(ASSD) and the fail
rate was evaluated.
The segmentation
performance of the
subject was equivalent
to the overall
performance compared
to the predicate,
reference device and
comparable literature
& devices.	The target performance
was validated using
157 cases distributed to
two cohorts. Cohort A
is clinical routine
treatment planning CT
and it is split into two
sub-cohort and Cohort
B is PET-CT data. To
objectively evaluate
the target performance,
the DICE coefficient,
the absolute symmetric
surface distance
(ASSD) and the fail
rate was evaluated.
The segmentation
performance of the
subject and reference
device were equivalent
as well as the overall
performance compared
to the predicate device.	The mean and standard
deviation Dice
coefficients, along with
the lower 95th
percentile confidence
bound were calculated.
User Interface -
Results Preview
(Confirmation)	Basic visualization
functionality of
original data and
generated contours	Basic visualization
functionality of
original data and
generated contours	No information
publicly available
User Interface
Configuration	Configuration UI	Configuration UI	No information
publicly available
Automated
Workflow to TPS	Results send to
Confirmation UI &
Optional bypassing of
Confirmation UI to
TPS	Results send to
Confirmation UI &
Optional bypassing of
Confirmation UI to
TPS	No information
publicly available
Human Factors	Design to be used by
trained clinicians.	Design to be used by
trained clinicians.	Designed to be used by
trained clinicians

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

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.

| Recognition
Number | Product
Area | Title of Standard | Reference
Number and
Date | Standards
Development
Organization |
|-----------------------|--------------------------|-------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------|------------------------------------------|
| 5-129 | General | Medical Devices –
Application of usability
engineering to medical
devices | 62366-1 Ed
1.1 2020-06
CV | IEC |
| 5-125 | General | Medical Devices –
application of risk
management to medical
devices | 14971:2019-
12 | ISO |
| 13-79 | Software/
Informatics | Medical device software –
software life cycle
processes [Including
Amendment 1 (2016)] | 62304 Ed 1.1
2015-06 CV | AAMI
ANSI
IEC |
| 12-349 | Radiology | Digital Imaging and
Communications in
Medicine (DICOM) Set | PS 3.1 – 3.20
2022d | NEMA |
| 5-134 | General | Medical devices – symbols
to be used with information
to be supplied by the
manufacturer - Part 1:
General Requirements | 15223-1
Fourth edition
2021-07 | ISO
IEC |
| 13-97 | Software/
Informatics | Health software – Part 1:
General requirements for
product safety | 82304-1
Edition 1.0
2016-10 | IEC |

Table 2: List of recognized standards

Verification and Validation

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).

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 % CI
Bootstrap	Avg	Std	95 % CI
Bootstrap	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 – common
organs	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 (%) | | | | ASSD (mm) | | | | |
|-----------------|--------------|----------|-------|-------|---------------|-----------|------|------|------|-------------|
| | | 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) |

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: 15
EU:15	USA: 25
EU: 11
Age	22 years and older	22 years and older
Manufacturer	Siemens Healthineers	Siemens Healthineers
Annotated Organs	Body
Femoral Head Right
Femoral Head Left	Anal Canal, Prostate, Rectum, Penile
Bulb, Seminal Vesicle, Bladder
Slice Thickness	= 70: 4
Unknown: 110
*unknown due to data
minimization on
customer site	70: 12	70: 12
Manufacturer	Siemens: 73	GE: 18
Philips: 22	Siemens: 53
GE: 59
Philips: 119
Varian: 44
Others: 26
Body Region	Head & Neck: 24
Thorax & Abdomen: 20
Pelvis: 29	Head & Neck: 40	Head & Neck: 50
Thorax: 81
Abdomen: 115
Pelvis: 55
Slice Thickness	3: 1	3: 3

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

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

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).