(123 days)
Yes
The device explicitly states that the "RT Contouring 4.5" module uses AI/ML for its Cranial Tumor Segmentation feature, and provides details about its training and performance.
No.
This device is a software for radiation treatment planning and dose optimization, which is used to plan the treatment, not to deliver the treatment itself.
Yes
The device assists in creating patient-specific radiation treatment plans by processing medical images and using AI/ML for tumor segmentation, which are diagnostic functions.
Yes
The device is a software-only medical device because the "Device Description" explicitly states "RT Elements are computed-based software applications" and lists several "software modules." There is no mention of hardware components being part of the device itself.
No
This device is for radiation treatment planning and dose optimization using medical images (CT, MRI, PET). It does not perform tests on biological samples.
No
The provided text does not contain any explicit statement that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
The device is intended for radiation treatment planning for use in stereotactic, conformal, computer planned, Linac based radiation treatment and indicated for cranial, head and neck and extracranial lesions.
Product codes
MUJ, QIH
Device Description
RT Elements are computed-based software applications for radiation therapy treatment planning and dose optimization for linac-based conformal radiation treatments, i.e. stereotactic radiosurgery (SRS), fractionated stereotactic radiotherapy (SRT) or stereotactic ablative radiotherapy (SABR), also known as stereotactic body radiation therapy (SBRT) for use in stereotactic, conformal, computer planned, Linac based radiation treatment of cranial, head and neck, and extracranial lesions.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
• CT
• MRI
• PET
• OT (other) Image set (output of the Contrast Clearance Element)
Anatomical Site
Cranial, head and neck, extracranial
Indicated Patient Age Range
Not Found
Intended User / Care Setting
The intended users are medical professionals who perform radiation treatment planning (medical physicists, radiation oncologists, dosimetrists, physicians, etc.).
Description of the training set, sample size, data source, and annotation protocol
The algorithm was trained on MRI image data with contrast-enhancing tumors from multiple clinical sites, including a wide variety of scanner models and patient characteristics.
Description of the test set, sample size, data source, and annotation protocol
Elements AI Tumor Segmentation algorithm was tested on de-identified 3D CE-T1 MR images from 412 patients (595 scans, 1878 annotations) from multiple clinical sites in the US and Europe. All data was acquired from adult patients with one or multiple contrast-enhancing tumors. The pool contained homogenous distribution by gender (female/male) and a diversity of ethnicity groups being White/Black/Latino/Asian with the highest representation. Most of data were obtained in patients who underwent stereotactic radiosurgery using a diverse acquisition of MR protocols (mainly containing 1.5T/3T MRI scans acquired in axial scan orientation). The test data pools also included control patients without cranial tumors. ¼ of the test pool corresponded to data from three independent sites in USA. The validation was conducted quantitatively by comparing the (manual) ground-truth segmentations, the so-called annotations with the respective automatically-created segmentations. The annotations involved external/independent annotator team including US radiologists and non US radiologists which followed a well-defined data curation process.
Summary of Performance Studies
AI/ML Performance Tests for Contouring 4.5:
Study Type: Quantitative validation – comparison to ground-truth annotations.
Sample size: 412 patients (595 scans, 1878 annotations).
Performance Metrics: Dice, Precision, Recall.
Key Results: Achieved acceptance criteria of Dice ≥ 0.7, Recall ≥ 0.8 and Precision ≥ 0.8 for the lower bound of the respective 95 % confidence intervals. Successful validation for images containing up to 30 cranial metastases, each showing a diameter of at least 3 mm, and images with primary cranial tumors that are at least 10 mm in diameter.
Key Metrics
Mean Dice: 0.75 [0.74; 0.76]
Mean Precision: 0.86 [0.85; 0.88]
Mean Recall: 0.85 [0.83; 0.87]
Predicate Device(s)
Reference Device(s)
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 892.5050 Medical charged-particle radiation therapy system.
(a)
Identification. A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.(b)
Classification. Class II. When intended for use as a quality control system, the film dosimetry system (film scanning system) included as an accessory to the device described in paragraph (a) of this section, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.
FDA 510(k) Clearance Letter - RT Elements 4.5
Page 1
June 17, 2025
Brainlab AG
Sadwini Suresh
QM Consultant
Olof-Palme-Str. 9
Munich, 81829
Germany
Re: K250440
Trade/Device Name: RT Elements (4.5); (Elements) Multiple Brain Mets SRS; (Elements) Cranial SRS; (Elements) Spine SRS; (Elements) Cranial SRS w/ Cones; (Elements) RT Planning Platform; (Elements) Dose Review; (Elements) Retreatment Review; Elements Segmentation [Cranial , Basal Ganglia, Head & Neck, Pelvic, Spine, Thoracic & Spine, Extracranial] RT; Elements AI Tumor Segmentation RT; Elements SmartBrush [Angio, Spine] RT; Elements Object Management RT
Regulation Number: 21 CFR 892.5050
Regulation Name: Medical Charged-Particle Radiation Therapy System
Regulatory Class: Class II
Product Code: MUJ, QIH
Dated: February 14, 2025
Received: May 19, 2025
Dear Sadwini Suresh:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of
Page 2
K250440 - Sadwini Suresh Page 2
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 (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-reporting-combination-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.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
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-devices/medical-device-safety/medical-device-reporting-mdr-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/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the
Page 3
K250440 - Sadwini Suresh Page 3
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-devices/device-advice-comprehensive-regulatory-assistance/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,
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
Enclosure
Page 4
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.
Indications for Use
Submission Number (if known)
K250440
Device Name
RT Elements (4.5);
(Elements) Multiple Brain Mets SRS;
(Elements) Cranial SRS;
(Elements) Spine SRS;
(Elements) Cranial SRS w/ Cones;
(Elements) RT Planning Platform;
(Elements) Dose Review;
(Elements) Retreatment Review;
Elements Segmentation [Cranial , Basal Ganglia, Head & Neck, Pelvic, Spine, Thoracic & Spine, Extracranial] RT;
Elements AI Tumor Segmentation RT;
Elements SmartBrush [Angio, Spine] RT;
Elements Object Management RT
Indications for Use (Describe)
The device is intended for radiation treatment planning for use in stereotactic, conformal, computer planned, Linac based radiation treatment and indicated for cranial, head and neck and extracranial 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."
Page 5
PAGE 1 OF 12
510(k) Summary
June 17, 2025
General Information
| Manufacturer | Brainlab AG; Olof-Palme Str.9; 81829, Munich, Germany |
| Establishment Registration | 8043933 |
| Trade Name | RT Elements 4.5 |
| Classification Name | System, planning, radiation therapy treatment |
| Product Code | MUJ; QIH |
| Regulation Number | 892.5050 |
| Regulatory Class | II |
| Panel | Radiology |
| Predicate Device | RT Elements (4.0); K223279 |
| Reference Device | Contouring 5.0 (part of Brainlab Elements 7.0 – K243633) |
Contact Information
| Primary Contact | Alternate Contact |
|---|---|
| Sadwini Suresh | |
| QM Consultant | |
| Phone: +49 89 99 15 68 0 | |
| Email: regulatory.affairs@brainlab.com | Chiara Cunico |
| Senior Manager Regulatory Affairs | |
| Phone: +49 89 99 15 68 0 | |
| Email: chiara.cunico@brainlab.com |
1. Indications for Use
The device is intended for radiation treatment planning for use in stereotactic, conformal, computer planned, Linac based radiation treatment and indicated for cranial, head and neck and extracranial lesions.
2. Device Description
RT Elements are computed-based software applications for radiation therapy treatment planning and dose optimization for linac-based conformal radiation treatments, i.e. stereotactic radiosurgery (SRS), fractionated stereotactic radiotherapy (SRT) or stereotactic ablative radiotherapy (SABR), also known as stereotactic body radiation therapy (SBRT) for use in stereotactic, conformal, computer planned, Linac based radiation treatment of cranial, head and neck, and extracranial lesions.
Page 6
PAGE 2 OF 12
The device consists of the following software modules:
| Software | Description |
|---|---|
| Multiple Brain Mets SRS 4.5 | Multiple Brain Mets SRS provides optimized planning and display for cranial multi-metastases radiation treatment planning. |
| Cranial SRS 4.5 | Cranial SRS provides optimized planning and display for cranial radiation treatment planning. |
| Spine SRS 4.5 | Spine SRS provides optimized planning and display for spine metastases. |
| Cranial SRS w/ Cones 4.5 | Cranial SRS w/ Cones provides planning and display for functional diseases (e.g. trigeminal neuralgia) or cranial lesion radiation treatment. |
| RT Contouring 4.5 | RT Contouring contains features to outline, refine, combine and manipulate structures in patient image data for planning of cranial and extracranial radiotherapy treatments. The Cranial Tumor Segmentation feature uses AI/Ml. The algorithm was trained on MRI image data with contrast-enhancing tumors from multiple clinical sites, including a wide variety of scanner models and patient characteristics. |
| RT QA 4.5 | RT QA contains features for patient specific quality assurance. Use RT QA to recalculate patient treatment plans on a phantom to verify that the patient treatment plan fulfills the planning requirements. |
| Dose Review 4.5 | Dose Review contains features for review of isodose lines, review of DVHs, dose comparison and dose summation. |
| Brain Mets Retreatment Review 4.5 | Retreatment Review allows the preparation and analysis of the next treatment by providing a 3D visualization of all previously treated and new metastases and review options for the summed dose of previous treatment plans. |
| Physics Administration 7.5 | The Physics Administration is a tool that allows to administer measured beam data and machine profiles for RT Elements software. The Software can be used to define and edit Hounsfield to electron density conversion tables. |
3. Substantial Equivalence
Page 7
PAGE 3 OF 12
| Topic/ Feature | Predicate Device (RT Elements 4.0 - K223279) | Subject Device (RT Elements 4.5) |
|---|---|---|
| Indications For Use | The device is intended for radiation treatment planning for use in stereotactic, conformal, computer planned, Linac based radiation treatment and indicated for cranial, head and neck and extracranial lesions. | The device is intended for radiation treatment planning for use in stereotactic, conformal, computer planned, Linac based radiation treatment and indicated for cranial, head and neck and extracranial lesions. |
| Applications/Elements included | • Multiple Brain Mets SRS | |
| • Cranial SRS | ||
| • Spine SRS | ||
| • Cranial SRS w/ Cones | ||
| • RT QA – Recalculation | ||
| • RT QA – Patient Specific QA | ||
| • RT QA – Beam Model Verification | ||
| • Dose Review | ||
| • Brain Mets Retreatment Review | ||
| • Physics Administration | ||
| • Phantom Definition | ||
| • Tissue Model | • Multiple Brain Mets SRS | |
| • Cranial SRS | ||
| • Spine SRS | ||
| • Cranial SRS w/ Cones | ||
| • RT QA – Recalculation | ||
| • RT QA – Patient Specific QA | ||
| • RT QA – Beam Model Verification | ||
| • Dose Review | ||
| • Brain Mets Retreatment Review | ||
| • Physics Administration | ||
| • Phantom Definition | ||
| • Tissue Model | ||
| • SmartBrush (RT; RT Spine; Angio) | ||
| • Object Management | ||
| Operating Principle | The device is composed by software only and can be controlled via mouse and keyboard. The software is displayed on a computer screen. |
The input of the Brainlab RT Elements are co-registered DICOM image sets with segmented objects.
The output is a DICOM RT dose plan for further processing and finally to control the radiation delivery to a patient using a linear accelerator. | The device is composed by software only and can be controlled via mouse and keyboard. The software is displayed on a computer screen.
Based on co-registered DICOM image sets, the software can create 3D structures or objects which are further used for the creation of RT dose plans.
The output is a DICOM RT dose plan for further processing and finally to control the radiation delivery to a patient using a linear accelerator. |
Page 8
PAGE 4 OF 12
| Topic/ Feature | Predicate Device (RT Elements 4.0 - K223279) | Subject Device (RT Elements 4.5) |
|---|---|---|
| Display Resolution | • 1920 x 1200 (WUXGA) | |
| • 2560 x 1440 (WQHD) | ||
| • 3840 x 2048 (4K) | • 1920 x 1080 (FHD) | |
| • 1920 x 1200 (WUXGA) | ||
| • 2560 x 1440 (WQHD) | ||
| • 3840 x 2048 (4K) | ||
| Supported Operating Systems | • Windows 10 1507 | |
| • Windows 10 1607 | ||
| • Windows 10 1809 | ||
| • Windows 10 21H2 | ||
| • Windows Server 2012 R2 64-bit | ||
| • Windows Server 2016 | ||
| • Windows Server 2019 | ||
| • Windows Server 2022 | • Windows 10 1607 | |
| • Windows 10 1809 | ||
| • Windows 10 v 21H2 | ||
| • Windows Server 2016 | ||
| • Windows Server 2019 | ||
| • Windows Server 2022 | ||
| Data Input | • DICOM Images | |
| • DICOM Segmentation | ||
| • DICOM Registration | ||
| • DICOM Key Object Selection Document | ||
| • DICOM Raw (Brainlab Load/Save) | ||
| • DICOM RT Dose | ||
| • DICOM RT Structure Set | ||
| • Machine Profiles | ||
| • HuToEd-Tables | • DICOM Images | |
| • DICOM Segmentation | ||
| • DICOM Registration | ||
| • DICOM Key Object Selection Document | ||
| • DICOM Raw (Brainlab Load/Save) | ||
| • DICOM RT Dose | ||
| • DICOM RT Structure Set | ||
| • Machine Profiles | ||
| • HuToEd-Tables | ||
| Intended User Profile | The intended users are medical professionals who perform radiation treatment planning (medical physicists, radiation oncologists, dosimetrists, physicians, etc.). | The intended users are medical professionals who perform radiation treatment planning (medical physicists, radiation oncologists, dosimetrists, physicians, etc.). |
Page 9
PAGE 5 OF 12
| Topic/ Feature | Predicate Device (RT Elements 4.0 - K223279) | Subject Device (RT Elements 4.5) |
|---|---|---|
| Data Output | • DICOM Images | |
| • DICOM RT Struct | ||
| • DICOM RT Plan | ||
| • DICOM Key Object Selection Document | ||
| • DICOM RT Dose | ||
| • DICOM Raw (Brainlab Load/Save) | ||
| • DICOM Segmentation | ||
| • DICOM Registrations | ||
| • PDF Report | ||
| • ASCII Dose Export | • DICOM Images | |
| • DICOM RT Struct | ||
| • DICOM RT Plan | ||
| • DICOM Key Object Selection Document | ||
| • DICOM RT Dose | ||
| • DICOM Raw (Brainlab Load/Save) | ||
| • DICOM Segmentations | ||
| • DICOM Registrations | ||
| • PDF Report | ||
| • ASCII Dose Export | ||
| • csv files | ||
| Supported Collimators | • Multileaf Collimators | |
| • Circular Conical Collimators | • Multileaf Collimators | |
| • Circular Conical Collimators | ||
| GUI Technology | • HTML5 (only RT Preparation & RT Analysis) | |
| • WPF | • HTML5 | |
| • WPF (only Physics Administration) |
Page 10
PAGE 6 OF 12
| Topic/ Feature | Predicate Device (RT Elements 4.0 - K223279) | Subject Device (RT Elements 4.5) |
|---|---|---|
| Supported Image Modalities | • CT | |
| • MRI | ||
| • PET | • CT | |
| • MRI | ||
| • PET |
Furthermore, it is possible to load the output of the Contrast Clearance Element which is labeled as OT (other) Image set.
Background: The Contrast Clearance Analysis calculation compares two 3D MRI data sets with injected contrast agents that were taken 60 to 105 minutes apart (early and late scans). When comparing the two 3D MRI data sets, Contrast Clearance Analysis performs a voxel-by-voxel subtraction of the early MR images from the late MR images resulting in a high-resolution color-coded Treatment Response Assessment Map (TRAM). This map provides effective separation between regions of contrast accumulation (positive value in red), and regions of contrast clearance (negative values in blue). Red regions show contrast accumulation , i.e. non-tumor regions and predominantly vessel necrosis. Dark blue regions show efficient contrast clearance, i.e. predominantly morphologically active tumor regions. |
| Dose Calculation Algorithm | • Pencil Beam Algorithm
• Monte Carlo Algorithm
• Circular Cone Algorithm | • Pencil Beam (PB) Algorithm
• Monte Carlo (MC) Algorithm
• Circular Cone Algorithm |
Page 11
PAGE 7 OF 12
| Topic/ Feature | Predicate Device (RT Elements 4.0 - K223279) | Subject Device (RT Elements 4.5) |
|---|---|---|
| Performance Characteristics | Pencil Beam/Monte Carlo: better than 3% |
Circular Cone: 1%/1mm | Pencil Beam/Monte Carlo: better than 3%
Circular Cone: 1%/1mm |
| Object Changes | In the planning applications it is possible to add and remove review objects to/from a treatment plan.
In general object property changes are not possible during treatment planning. | Review objects can be added/removed in all planning applications as well as Dose Planning.
PTV (Planning Target Volume) , OAR (Organ At Risk) and other objects' properties can be changed for treatment plans (e.g., name, color and comment). The optimization result remains valid after the change. |
| Separation of optimization and final dose calculation | The final dose calculation was automatically performed at the end of the optimization. | The user can trigger the final dose calculation separately from the plan optimization (VMAT (Volumetric Modulated Arc Therapy)):
→ Possible to optimize a plan using PB or MC first and then trigger final dose calculation using fine MC parameters
→ MC coarse and MC fine dose is cached of the current state and the MC dose of the last optimization result to enable the user to easily revert to the last plan state
→ The fine and coarse MC parameters visualized in the dropdown can be defined in the Clinical Protocol. The spatial resolution and grid size used during a MC based optimization can only be changed in the Clinical Protocol |
Page 12
PAGE 8 OF 12
| Topic/ Feature | Predicate Device (RT Elements 4.0 - K223279) | Subject Device (RT Elements 4.5) |
|---|---|---|
| Interface to Art-Plan (by TheraPanacea) for extracranial workflows | Not part of the Predicate Device. | For the following extracranial workflows an interface to the cloud based 3rd party contouring system "Art-Plan" by TheraPanacea (TPC) was introduced. |
Art-Plan provides an auto-segmentation of extracranial structures which are loaded into Object Management. Therefore, Art-Plan Connect (part of Art-Plan) is installed on the same HW as the RT Elements and works as a communication gateway between the main Art Plan cloud service and the RT Elements. |
| APM (Anatomical Patient Model) | Not part of the Predicate Device. | Component of the RT Elements with a gRPC API, which serves as an algorithmic backend for medical image data processing. The API can readily be used by client applications to have access to functionalities for automatic processing of 2D and 3D medical image data (e.g. segmentations, landmarks). To provide its functionality the APM service also includes interfaces to other components of the Universal Patient Model device like UniversalAtlasPerformer and UATransferPerformer. Additional functionality is also implemented directly in the APM service (like cranial tumor segmentations).
The component is used by RT Contouring. |
Page 13
PAGE 9 OF 12
4. Performance Data
The Subject Device has been verified and validated according to Brainlab processes for product design and development. A high level explanation of the testing provided in this submission for the Subject Device is provided below. For more details, please refer to the document Verification and Performance Bench Testing Summary – RT Elements 4.5.
Software verification
Software verification has been performed on software level, verifying the software requirements through integration tests (see XToolPro Software protocols) as well as GUI tests and Unit tests. An incremental test strategy has been set up for the release candidates for changes with limited scope. In this case, an impact analysis of the modifications was performed and tests to be performed are identified and planned correspondingly.
Usability Evaluation:
Only formative usability evaluation was carried out for the Subject Device. No summative usability evaluation has been performed for RT Elements 4.5.
Performance Comparison Optimization Algorithm:
This test compared the performance of the new version to the predecessor version of Multiple Brain Mets SRS. The objective was to show that the dosimetric performance between the two versions is equivalent without compromising in treatment plan efficiency.
Comparison Of Dose Calculations To Phantom Measurements:
This verifies that RT Elements 4.5 is able to accurately compute dose distributions for treatment machines equipped with Elekta or Varian multi-leaf collimators with both dose calculation algorithms: Pencil Beam (PB) and Monte Carlo (MC).
Validation Of Reference Beam Models:
Reference Beam Models (RBM) contain Pencil Beam (PB) and Monte Carlo (MC) dose profiles that are pre-generated for different photon source sizes of a linear accelerator (linac). The test validates the dose calculations performed for Elekta and Varian linacs using 6 MV-STD, 6 MV-FFF, 10 MV-STD and 10 MV-FFF photon beams with respect to the accuracy of RBMB for PB and MC dose algorithms.
Page 14
PAGE 10 OF 12
Small Field Dose Calculation With Scatter Model Enhanced Pencil Beam:
This test verifies that RT Elements is able to accurately calculate doses for targets with an equivalent square field size smaller than 10 x 10 mm² using its Scatter Model enhanced pencil beam algorithm.
Multiple Brain Mets SRS Calculation Time:
Multiple Brain Mets SRS enables fast automatic treatment plan generation for multiple brain metastases cases. The optimization problem is solved using an inverse stochastic optimization algorithm and requires several dose calculations. This test assesses the time to complete treatment plan generation for cases with up to 15 metastases.
Varian Dynamic Jaw Tracking:
Jaws in general are used to block radiation around the opening of the multi-leaf-collimator (MLC). With Static Jaws, the smallest possible box around all MLC positions is formed by the jaws. Dynamic Jaws enable a reshaping of the box at every control point. It is expected that this will result in reduced radiation of normal tissue as those boxes can be shaped more precisely around the positions of the leaves. The aim of this test is to confirm that Varian Dynamic Jaws result in reduced normal tissue dose compared to a treatment plan without Dynamic Jaws while maintaining similar planning target volume (PTV) conformity and coverage.
Elekta Dynamic Jaw Tracking:
Starting with RT Elements generation 2.5, Cranial SRS (1.5.1), Spine SRS (1.5.1) and Multiple Brain Mets SRS (2.0) support Dynamic Jaw Tracking for Elekta Agility machines. For those machines, the jaws are used to shape the form of irradiation targets in y direction, in addition to the leaves in x direction. With Dynamic Jaw Tracking, the jaws can be moved to arbitrary positions. Without Dynamic Jaw tracking, the jaws are limited to discrete positions at the leave edges. The aim of this test was to find out, whether Dynamic Jaw Tracking results in reduced normal tissue dose compared to the same plan without jaw tracking.
Collimator Optimization Spine SRS:
This test shows whether Collimator Optimization results in improved conformity and reduced normal tissue dose compared to plan generation without Collimator Optimization. The test was restricted to non-spherical targets for which a rotation of the collimator can have an effect.
AI/ML Performance Tests for Contouring 4.5:
Elements AI Tumor Segmentation can be used to semi-automatically segment supported cranial tumors (metastases, meningiomas, cranial and paraspinal nerve tumors, gliomas, glioneuronal
Page 15
PAGE 11 OF 12
and neuronal tumors) on 3D medical Contrast Enhanced T1-weighted MR images powered by the Anatomical Patient Model. The approach used was quantitative validation – comparison to ground-truth annotations.
Validation Summary:
Elements AI Tumor Segmentation algorithm was tested on de-identified 3D CE-T1 MR images from 412 patients (595 scans, 1878 annotations) from multiple clinical sites in the US and Europe. All data was acquired from adult patients with one or multiple contrast-enhancing tumors. The pool contained homogenous distribution by gender (female/male) and a diversity of ethnicity groups being White/Black/Latino/Asian with the highest representation. Most of data were obtained in patients who underwent stereotactic radiosurgery using a diverse acquisition of MR protocols (mainly containing 1.5T/3T MRI scans acquired in axial scan orientation). The test data pools also included control patients without cranial tumors. ¼ of the test pool corresponded to data from three independent sites in USA. The validation was conducted quantitatively by comparing the (manual) ground-truth segmentations, the so-called annotations with the respective automatically-created segmentations. The annotations involved external/independent annotator team including US radiologists and non US radiologists which followed a well-defined data curation process.
In accordance with best practices, measurement of recall and precision and object-specific DICE coefficient were performed to assess the similarity between both segmentations. Acceptance criteria were Dice ≥ 0.7, Recall ≥ 0.8 and Precision ≥ 0.8 for the lower bound of the respective 95 % confidence intervals. Successful validation has been completed based on images containing up to 30 cranial metastases, each showing a diameter of at least 3 mm, and images with primary cranial tumors that are at least 10 mm in diameter (for meningioma, cranial/paraspinal nerve tumors, gliomas, glioneuronal and neuronal tumors). See performance metrics in Table 1.
Table 1 Summary of test statistics
| Diagnostic Characteristics | Mean Dice | 95% Confidence Interval | Mean Precision | 95% Confidence Interval | Mean Recall | 95% Confidence Interval |
|---|---|---|---|---|---|---|
| All | 0.75 | [0.74; 0.76] | 0.86 | [0.85; 0.88] | 0.85 | [0.83; 0.87] |
| Metastases to the CNS | 0.74 | [0.73; 0.75] | 0.85 | [0.83; 0.87] | 0.84 | [0.82; 0.86] |
Page 16
PAGE 12 OF 12
| Diagnostic Characteristics | Mean Dice | 95% Confidence Interval | Mean Precision | 95% Confidence Interval | Mean Recall | 95% Confidence Interval |
|---|---|---|---|---|---|---|
| Meningiomas | 0.76 | [0.73; 0.79] | 0.89 | [0.84; 0.94] | 0.90 | [0.85; 0.94] |
| Cranial and paraspinal nerve tumors | 0.89 | [0.88; 0.90] | 0.97 | [0.93; 1.0] | 0.97 | [0.93; 1.0] |
| Gliomas and glio-/neuronal tumors | 0.81 | [0.76; 0.86] | 0.95 | [0.88; 1.0] | 0.85 | [0.74; 0.94] |
5. Conclusion
The comparison of the Subject Device with the predicate device shows that RT Elements 4.5 has similar functionality, intended use and technological characteristics as the predicate device. Based on the comparison to the predicate and the performance testing conducted, the Subject Device is considered substantially equivalent to the predicate device.