RayStation is a software system for radiation therapy and medical oncology. Based on user input, RayStation proposes treatment plans. After a proposed treatment plan is reviewed and approved by authorized intended users, RayStation may also be used to administer treatments.

The system functionality can be configured based on user needs.

Device Description

RayStation is a treatment planning system for planning, analysis and administration of radiation therapy and medical oncology treatment plans. The device lets the user import patient images and data, identify treatment targets and organs at risk, create an optimal treatment plan taking into account patient anatomy, prescribe treatment dose and organ at risk sensitivity, review and approve the plan and then administer the treatment. A scientific basis for the device is the implementation of peer reviewed algorithms of plan parameter optimization and photon and particle dose calculation.

RayStation consists of multiple applications:

The main RayStation application is used for treatment planning.
The RayPhysics application is used for commissioning of treatment machines to make them available for treatment planning and used for commissioning of imaging systems.
The RayTreat application is used for sending plans to treatment delivery devices for treatment and receiving records of performed treatments.

These applications are built on a software platform, containing the radiotherapy domain model and providing GUI, optimization, dose calculation and storage services. The platform uses three Microsoft SQL databases for persistent storage of the patient, machine and clinic settings data.

The RayStation application is divided in modules, which are activated through licensing. A simplified license configuration of RayStation is marketed as RayPlan has a limited set of modules, indicated in the following table.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for RayStation 12A, based on the provided text:

Acceptance Criteria and Device Performance

Acceptance Criteria	Reported Device Performance
Support for eye planning with wedges	The SOBP distal fall-off of the central axis depth dose curve meets accuracy requirements. 95% and 98% of the computed depth dose values meet Gamma pass rates.
Automatic field in field planning	For a 3D-CRT plan, the merged beams' MU agrees with original beams' MU. Merged beams' segments maintain original shapes. MU and segment weights after split are subdivided correctly, and split beams are managed correctly in terms of ordering and ROI handling.
Brachy Therapy support for Elekta Flexitron® afterloaders	The dose engine accurately reproduces dose for a variety of sources when compared to OA along-away data. Measured doses (EQUAL-ESTRO) relate computed dose to delivered dose correctly. Comparison to an independent and TG43 compliant treatment planning system validates correct superposition of dose. Comparison to an independent Monte Carlo system provides fully independent validation of complete treatment plans.
Electron Monte Carlo dose engine update	For comparison with previous RayStation dose, the calculated doses fail for less than 2% of the data points for gamma 2%/2mm. The fraction of calculated dose data points failing comparison to BEAMnrc/egs++ has been evaluated. Two different gamma criteria for comparison with another TPS or measurement are evaluated with specified requirements on agreement level.
Overall Software Safety and Performance (Major Concern Level)	Software verification and validation demonstrate that RayStation 12A performs as intended in specified use conditions and comparably to the predicate device.

Study Information:

2. Sample sizes used for the test set and the data provenance

Eye Planning with Wedges: Specific sample size for test cases is not provided, but they cover "line doses in homogeneous phantoms using a square aperture and a wedge mounted with varying opening angles and positions." The origin is internal testing/validation.
Automatic Field in Field Planning: Specific sample size for test cases is not provided. The origin is internal testing/validation.
Brachy Therapy Support for Elekta Flexitron® afterloaders: Specific sample size for test cases is not provided. Reference doses consist of "point doses, line doses, as well as 2D and 3D doses." Origin includes published consensus data, measured doses, doses computed in two major competing TPS, and doses computed with an independent Monte Carlo software.
Electron Monte Carlo Dose Engine Update: Specific sample size for test cases is not provided. Reference doses include measured doses, doses computed in a well-established competing TPS, doses computed with earlier versions of RayStation, and doses computed in BEAMnrc/egs++. Data provenance is thus mixed, including internal comparisons, external commercial TPS, and external academic/research software.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

The document does not specify the number or qualifications of experts used to establish ground truth for any of the test sets. The ground truth for dose calculation is primarily based on:

Published consensus data
Measured doses
Comparison to other established commercial Treatment Planning Systems (TPS)
Comparison to independent Monte Carlo software

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

The document does not describe any adjudication method involving human experts for resolving discrepancies in the test sets. The comparisons are quantitative against established reference data or other computational models.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

A multi-reader multi-case (MRMC) comparative effectiveness study was not mentioned or performed. This device is a treatment planning system, not an AI-assisted diagnostic tool that would typically involve human "readers" in that context. The improvements are in the accuracy and functionality of the dose calculation and planning algorithms, not in improving human interpretation of an AI output.

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

Yes, the studies described are standalone performance evaluations of the algorithm's accuracy in specific calculation tasks (dose computation for various modalities and planning features). The "device performance" described in the table above refers to the algorithm's performance against reference standards.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The ground truth used is primarily based on:

Physical Measurements: "Measured doses," "depth-dose profiles along the central axis were acquired with a plane-parallel chamber in a water tank."
Published Consensus Data: For brachytherapy, "Published consensus data."
Established Computational Models: Doses computed in well-established competing TPS, independent Monte Carlo software (BEAMnrc/egs++), and comparison to previous versions of RayStation.

8. The sample size for the training set

The document does not provide any information regarding the sample size for a training set. The descriptions focus on the validation of specific algorithms and features, which often rely on physics models and deterministic calculations rather than machine learning training sets. While "deep learning segmentation" is mentioned as a module (available in RayStation 11B and 12A), the provided validation details for the new features in 12A do not describe training data for this specific version's changes.

9. How the ground truth for the training set was established

As no training set information is provided for the features specifically validated in K222312, there is no information on how its ground truth would have been established. For the general mention of "deep learning segmentation," the text indicates "The model training is performed offline on clinical CT and structure data," but no further details on ground truth establishment for this training.

Summary

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

March 29, 2023

Image /page/0/Picture/1 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

RaySearch Laboratories AB (publ) % David Hedfors Quality and Regulatory Affairs Director Eugeniavagen 18 Stockholm, 113 68 SWEDEN

Re: K222312

Trade/Device Name: RayStation 12A Regulation Number: 21 CFR 892.5050 Regulation Name: Medical Charged-Particle Radiation Therapy System Regulatory Class: Class II Product Code: MUJ Dated: July 26, 2022 Received: August 1, 2022

Dear David Hedfors:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/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.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for

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

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

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely.

Image /page/1/Picture/5 description: The image shows the name "Lora D. Weidner" in a large, sans-serif font. The name is stacked vertically, with "Lora D." on the top line and "Weidner" on the bottom line. The text is black against a white background.

Digitally signed by Lora D. Weidner -S Date: 2023.03.29 10:20:55 -04'00'

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

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

Indications for Use

510(k) Number (if known) K222312

Device Name RayStation 12A

Indications for Use (Describe)

The system functionality can be configured based on user needs.

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}------------------------------------------------

510(k) Summary 1.

1.1 510(k) owner

RaySearch Laboratories AB (publ) Eugeniavägen 18 113 68 Stockholm Sweden

Tel: +46 8 510 530 00

1.2 Contact person

David Hedfors Quality and Regulatory Affairs Director RaySearch Laboratories AB (publ) Email: quality@raysearchlabs.com +46 722 366 110 Tel:

1.3 Preparation date

March 28th, 2023.

1.4 Trade name

The trade name is RayStation.

The marketing name is RayStation 12A and RayPlan 12A.

1.5 Common name

Radiation therapy treatment planning system

1.6 Classification name

Medical charged-particle radiation therapy system (21 CFR 892.5050, Product Code MUJ)

1.7 Predicate device

K220141 RayStation 11B

1.8 Device description

RayStation consists of multiple applications:

. The main RayStation application is used for treatment planning.
The RayPhysics application is used for commissioning of treatment machines to make ● them available for treatment planning and used for commissioning of imaging systems.
The RayTreat application is used for sending plans to treatment delivery devices for treatment and receiving records of performed treatments.

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

Planning activity	Module	Available inRayPlan
Automated planning	Plan explorer	No
Automated planning	Automated breast planning	No
Automated planning	Fallback planning	No
Automated planning	Fallback protocol management	No
Patient data management	Patient data management	Yes
Patient modeling	Image registration	Yes
Patient modeling	Structure definition	Yes
Patient modeling	Deformable registration	No
Patient modeling	Eye modeling	No
Plan design	Virtual simulation	Yes
Plan design	Plan setup	Yes
Plan design	3D-CRT beam design	Yes
Plan design	Electron beam design	Yes
Plan design	Proton beam design	No
Plan design	Brachy planning	Yes
Plan optimization	Plan optimization	Yes
Plan optimization	Multi criteria optimization	No
Plan evaluation	Plan evaluation	Yes
Plan evaluation	Robust evaluation	No
Plan evaluation	Biological evaluation	No
QA preparation	QA preparation	Yes
Treatment adaptation	Dose tracking	No
Treatment adaptation	Adaptive replanning	No

In each planning activity the user can perform some operations that are considered to form a basic task or planning activity in oncology. Together, the planning activities cover a complete treatment planning use case. Each planning activity consists of one or more modules; each corresponding to a coherent group of functionalities. A module may include one or several workspaces, where each workspace holds an optimized layout of regions populated with GUI components that are needed to get through the use case of the module.

The device to be marketed, RayStation 12A, contains modified features compared to version RayStation 11B as indicated below:

Support for eye planning with wedges
- A wedge can be used to improve the conformity of dose distribution and spare risk O organs. The wedge is not patient specific, meaning that the user must choose a wedge from a predefined set of wedges for the treatment machine. Each wedge in the machine model is associated with an identifying name, a physical opening angle, and a material.
Automatic field in field planning ●

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

A uniform dose can be achieved on a selected target using automatically generated 3Do CRT fields/segments. Starting from a number of beams (usually 2 or 3) and an initial segment for each beam the action sequentially adds a given number of segments to each beam, choosing apertures and segment weights so that the final dose is approximately uniform on the target. The apertures of the inner segments always have openings that are subsets of the openings of the respective initial segments.
Brachy therapy support for Elekta Flexitron® afterloaders
- The connectivity to the Elekta Flexitron® afterloader is validated for the brachy planning O in RayStation using the TG43 formalism.
Electron Monte Carlo dose engine update .
- O The previously used plug-in for in-patient transport for the electron Monte Carlo dose engine (VMC++) was replaced by a fully integrated electron Monte Carlo dose engine. In the development of the new dose engine, improvements have been made to increase the accuracy for small cutout sizes.

1.9 Indications for Use

The system functionality can be configured based on user needs.

1.10 Technological characteristics summary

The following comparison table summarized the technological characteristics. In the table below, RayStation 12A is compared to the predicate device RayStation 11B.

Item	Compared toRayStation 11B	Comment
Hardware platform	Substantially Equivalent	Both systems use standard office PCs as hardware platform.
Operating system	Substantially Equivalent	Both systems use Windows 10 Professional (or higher) andWindows Server 2012 R2 (or higher).
Target population	Substantially Equivalent	RayStation 11B and RayStation 12A are intended for thesame target population and anatomical sites; persons that
Anatomical sites	Substantially Equivalent	have been prescribed an external beam radiation therapy ormedical oncology treatment.
Human factors	Substantially Equivalent	In terms of human factors, the systems are consideredequivalent. The user interfaces are almost identical.
Standards met	Substantially Equivalent	Both systems comply with the following FDA-recognizedconsensus standards: IEC 61217:2011, IEC 62083, IEC62304:2015, IEC 62366-1:2015, ISO 14971:2019 and withIEC 60601-2-68:2014 standard.
Image types	Substantially Equivalent	RayStation 11B and RayStation 12A both support CT, PETand MR images for identifying patient organs and contouring.
Reporting aspects	Substantially Equivalent	When evaluating and approving treatment plans, all necessarydata is presented to the user and available in print in bothsystems.
Image storing	Substantially Equivalent	None of the systems is intended for long term storage ofimages or other patient data.
Network / remoteconnections andcapabilities	Substantially Equivalent	Both systems are capable of network transfer of patient datausing the DICOM protocol. RayStation 12A and RayStation11B are designed for desktop use and for remote access usingstandard virtualization techniques. Remote connection to thesystem is verified in detail and equivalent to local connection.

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

Cybersecurity	Substantially Equivalent	Both systems are compliant with the requirements listed inthe FDA guideline 1825 "Content of Premarket Submissionsfor Management of Cybersecurity in Medical Devices".
---------------	--------------------------	--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Feature	Description	Present inRayStation11B(K220141)	Present inRayStation12A	Significantlychanged?
3Dvisualization	Displays the patient geometry andstructures in three dimensions, with thepossibility to rotate the patient image. Ifavailable, the dose distribution and beammodifiers are shown as well.	Yes	Yes	No
Adaptivereplanning	The process of replanning the treatmentfor a patient, based on information aboute.g. patient geometry, biology and dosedelivery acquired during treatment.	Yes	Yes	No
Beamcommissioning	Modeling of the radiation beam using alimited set of measurements on the clinicalbeam for commissioning treatmentmachines to make them available fortreatment planning.	Yes	Yes	No
Beam design	Definition of beam orientations, aperturesand various beam modifiers in order tomanually create a treatment plan.	Yes	Yes	No
Beam set-up	Manual or automatic definition ofisocenter, selection of treatment unit fromthe set of commissioned treatmentmachines, and specification ofgantry/couch/collimator angles.	Yes	Yes	Yes, newfunctionalityAutomaticField in Fieldplanning wasadded.
Beam's eyeview	Displays the beam's eye view of thepatient structures, fluence and beammodifier settings for any beam.	Yes	Yes	No
Brachyplanning	Tools for planning of HDR brachytherapytreatments. Includes channelreconstruction and optimization andediting of dwell times.	Yes	Yes	Yes. NowsupportsElektaFlexitronafterloaders.
CyberKnifeplanning	CyberKnife planning is completelyintegrated in RayStation. This includesoptimization of high quality treatmentplans collimated with MLC, fixed conesor iris cones, as well as support for allCyberKnife Synchrony techniques fortarget tracking and real time motionsynchronization.	Yes	Yes	No
Deformableregistration	Establishing a point-to-point mappingbetween two images using a deformationmodel. Used for mapping of dose andstructures between images.	Yes	Yes	No
DICOM RTexport	Export of images, structure set, plan, anddose according to the DICOM RTstandard.	Yes	Yes	No
DICOM RTimport	Import of images, structure set, plan, anddose according to the DICOM RTstandard.	Yes	Yes	No
Dosecalculationelectrons	For electron beams RayStation calculatesdose by the Monte Carlo technique. Theelectron beam phase space is generated inrun time by sampling from a phase spacemodel where the electrons are created atthe secondary scattering foil. Both theelectron transport through the treatmenthead and the in-patient dose computationis performed using the Monte Carloalgorithm.In versions prior to RayStation 11A, thetransport through the treatment head hasbeen handled by a Monte Carlo algorithmdeveloped by RaySearch, while the in-patient transport and dose computation hasbeen the responsibility of the plug-in doseengine VMC++. In RayStation 12A, theVMC++ dose engine has been exchangedwith an in-patient Monte Carlo transportand dose scoring algorithm fullydeveloped by RaySearch. Additionally,some minor improvements have beenmade to the treatment head transport, butthis part is essentially the same as inRayStation 11B.There are substantial similarities betweenthe replaced VMC++ code and theEGSnrc code and these two Monte Carlodose engines agrees on sub-percent level[1][2]. The dose engine developed byRaySearch is similar to the EGSnrc, as hasbeen described in references 11, 12, 17, 24and 108 in the 008 RSL-D-RS-12A-REF-EN-1.0-2022-06-23 RayStation 12AReference Manual. Therefore, weconclude that the electron dose engineused in RayStation 12A (fully developedby RaySearch) is substantially equivalentto the electron dose engine used inRayStation 11B (in-patient dosecomputation handled by VMC++).	Yes	Yes	Yes

	The supporting testing confirmsequivalence between the RayStation 11Band RayStation 12A dose engines.Regression tests performed during theelectron dose engine validation betweenthe two versions are within tolerancelimits which shows a similar level ofaccuracy between the two dose engines.Acceptance criteria for comparison withprevious RayStation dose: The calculateddoses shall fail for less than 2% of the datapoints for gamma 2%/2mm.References:
	Society (Cat. No.00CH37143), Chicago,IL, USA, 2000, pp. 1490-1493 vol.2, doi:10.1109/IEMBS.2000.898024.[2] Kawrakow I, Fippel M, Friedrich K.3D electron dose calculation using aVoxel based Monte Carlo algorithm(VMC). Med Phys. 1996 Apr;23(4):445-57. doi: 10.1118/1.597673. PMID:9157256.
Dosecalculationphotons	For photon beams RayStation calculatesdose by the point kernel superpositionmethod (a.k.a. Collapsed Cone) or aMonte Carlo algorithm for radiationtransport. The incident energy fluence ismodeled as a superposition of a primaryenergy fluence and a scatter energyfluence. The dose contribution fromcontamination electrons is calculated by apencil beam algorithm.	Yes	Yes	No
Dosecalculationproton	For proton beams RayStation uses eitherthe pencil beam algorithm with the Fermi-Eyges formalism, or a Monte Carloalgorithm for radiation transport. Forpassive beams the beam model accountsfor the collimator and compensator block.For scanning beams the beam modelaccounts for the spot phase spaceincluding effects of air-scatter and beampaths through magnetic deflectionelements. The user defined block apertureis taken into account in spot selection andoptimization. In addition to this therelative biological effect (RBE) of protonbeams is taken into account, resulting in aphoton equivalent dose.	Yes	Yes	No
Dosecalculationbrachy	For brachy plans RayStation calculatesdose based on the TG43 formalism.	Yes	Yes	No
Dose display(2D)	Displays the patient geometry withstructures superimposed on the image datatogether with the dose distribution intransversal, sagittal, and coronaldirections.	Yes	Yes	No
Dose tracking	Dose tracking scenarios includingdeformable registration of one CT orCBCT to another and subsequentdeformation and accumulation of dose.	Yes	Yes	No
Eye planning	Tools for specifying a highly detailedgeometrical model of the eye based onmeasurements from ultrasound andsurgery. Support for positioning oftantalum clips. Import and visualization offundus images. Creation and dosecomputation of proton plans with gazeangle-based treatment directions.	Yes	Yes	Yes, Nowsupports eyeplanning withwedges.
Fallbackplanning	Automatic generation of fallback plansusing alternative treatment machines andtreatment techniques. User-definedprotocols specifies the setup of thefallback plans which are automaticallygenerated from the protocols andoptimized using dose mimickingfunctions.	Yes	Yes	No
Imageconversion	Conversion of CBCT images to syntheticCT images that can be used for moreaccurate dose calculations.	Yes	Yes	No
Inverseplanning	The user can define optimization settingssuch as optimization tolerance andmaximum number of iterations as well assegmentation settings on the multileafcollimator and the Pencil Beam Scanningspot pattern. An interface for controllingthe optimization process is provided andthe progress of optimization is displayedin a view. The system generates controlpoints for step-and shoot MLC plans,Sliding Window plans (DMLC), rotationalplans (VMAT), 3DCRT plans, Wave Arcplans, TomoTherapy plans and protonPencil Beam Scanning plans, using thedefined optimization problem. The inverseplanning can be carried out either througha conventional inverse approach or byusing multi-criteria optimization (photonsand protons only).	Yes	Yes	No
LET evaluation	Computation and evaluation of dose-averaged LET (Linear Energy Transfer) for proton plans. LET is an additional physical quantity that can be used to assess the radiobiological effect of the proton radiation.	Yes	Yes	No
Machine database	Microsoft SQL database for storage of beam model parameters, machine constraints and dose curves with dosimetric data for treatment units.	Yes	Yes	No
MR based planning	Allowing MR-images as planning images and base dose computation on material override ROIs.	Yes	Yes	No
Optimization functions	The optimization functions are specified in terms of objectives and constraints to form the optimization problem that is solved by the optimization engine.	Yes	Yes	No
Patient anatomy modeling	Manual and semi-automatic segmentation tools for contouring ROIs slice by slice together with semi-automated generation of the patient outline ROI.The model-based segmentation technique allows for semi-automatic delineation of structures by matching 3D shape models of the structures to new image data.With atlas-based segmentation, the user can define templates consisting of already segmented image data and use this template for segmentation of new patient images.With deep learning segmentation, the user can use trained deep learning models for automatic segmentation of new patient images. (The model training is performed offline on clinical CT and structure data.)	Yes	Yes	No
Patient database	Microsoft SQL database for storage of all patient and plan data. Not for long term storage.	Yes	Yes	No
Plan Explorer	The system computes a large set of plans according to given rules and the user is provided with tools to select good plans from these.	Yes	Yes	No
Quality assurance preparation	Tools for transferring the clinical plan to a phantom and recalculate dose. The output is the dose distribution in DICOM format or a 2D dose plane and a QA report.Predicted EPID response is retrieved by photon dose computation in a specially designed phantom.	Yes	Yes	No
RBE dosehandling	RBE (Relative Biological Effectiveness)models can be defined and commissioned.For proton treatments, the user can selectwhether to look at RBE-corrected dose orphysical dose. Dose summation is onlypossible for photon doses and RBE-corrected proton doses.	Yes	Yes	No
Robustevaluation	Tools used to answer questions of how thedose distribution would appear if thepatient setup at the time of treatment doesnot fully correspond to the planning CT. Amodel of patient uncertainties such as CTinaccuracy and setup errors is used tocompute a set of scenario doses forevaluation.	Yes	Yes	No
Robustoptimization	Optimization where a model of patientuncertainties such as CT inaccuracy, setuperrors or organ motion is used during theoptimization.	Yes	Yes	No
Scripting	Scripting gives programmatic access tofunctionality, excluding user riskmitigations. Through scripting, the clinicspecific procedures can be automated. Theoperating system and other applicationscan be accessed.	Yes	Yes	No
Supported	HFS, FFS, HFP, FFP	Yes	Yes	No
treatmentpositions	Decubitus left/right	Yes	Yes	No
	Seated position (for ions)	Yes	Yes	No
Systemintegrity tools	Hardware based license, preventingunauthorized useable copies to be made.Checksum control of binary files toprevent tampering. Data in the patient andmachine databases only available for userswith administrator rights.	Yes	Yes	No
TomoTherapyplanning	Planning for TomoTherapy machines iscompletely integrated in RayStation. Alsoprovides tools for selection of targets andimaging angles for the TomoTherapymachine to use for target tracking duringdelivery.	Yes	Yes	No
Treatmentadaptation	A general concept where the treatmentplan is adapted during the course oftreatment. Tools available today includedeformable dose accumulation, CBCTdose calculation and replanning scenarios.	Yes	Yes	No
Treatment planapproval	Approval of the preferred treatment planand referenced ROIs by authorizedmedical staff. Once a treatment plan isapproved, it is locked for any furthermodification.	Yes	Yes	No
Treatment plancreation	Treatment plan creation with specificationof plan properties such as number offractions and delivery technique.	Yes	Yes	No
Treatment planevaluation	Evaluation of a single plan. Comparisonof dose distributions and DVH curves oftwo or three plans.	Yes	Yes	No
Treatmentdelivery	An approved plan can be assigned tofractions in a treatment course and sent tothe treatment delivery device. RayTreatoffer treatment room interfaces for patientpositioning, imaging and plan delivery.	Yes	Yes	No
Undo/redo andauto recovery	The undo stack is saved to the database,enabling recovery of RayStation aftercrash. The user may redo all or selectedchanges at reopen of patient after crash.	Yes	Yes	No
VirtualSimulation	Setup of isocenter, beam arrangementsand basic aperture design. Export to lasersystems for patient marking.	Yes	Yes	No

Detailed technology comparison table:

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

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

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

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

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

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

1.11 Assessment of non-clinical performance data

Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices". The software for this device was considered as a "Major" level of concern, since a failure or latent flaw in the software could directly result in serious injury or death to the patient.

Support for eye planning with wedges - Validation of the eye planning feature extended to include wedges was performed as part of the dose engine validation for proton ocular treatments. The test cases cover line doses in homogeneous phantoms using a square aperture and a wedge mounted with varying opening angles and positions. Depth dose curves with ranges and modulations are used in the validation. An interval is used for the opening angle of the wedge and for the lateral position of the opening edge of the wedge with respect to the central axis. Depth-dose profiles along the central axis were acquired with a plane-parallel chamber in a water tank. The accuracy requirements are related to:

. The SOBP distal fall-off of the central axis depth dose curve
. 95% and 98% of the computed depth dose values with Gamma pass rates

The requirements are met by the data in the validation report. The proton dose computation for proton ocular treatments in RayStation 12A has been successfully validated for accuracy in clinically relevant settings according to specification.

Automatic field in field planning - Validation of the new feature for creating field in field plans for e.g. 3DCRT plans with multiple segments in each beam was performed as part of the overall system validation.

The requirements are that

. For a 3D-CRT plan, the merged beams' MU shall agree with original beams' MU.
Merged beams' segments shall keep original shapes.
. MU and segment weights after split are subdivided correctly and that split beams are managed correctly in terms of ordering and ROI handling.

Testing shows that the segment MUs and shapes agree, beam and segment administration and handling are correct and that all beams created by the split beam action have the same Treat and Protect ROIs as the beam that was split. These tests demonstrate that RayStation 12A can safely perform field in field planning.

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

Brachy Therapy now support Elekta Flexitron® afterloaders – Validation of the HDR brachytherapy planning for Elekta Flexitron afterloaders was performed as part of the Dose Engine validation of Brachy TG43.

Computed doses have been compared with reference doses, i.e. from published consensus data sets, from measurements or from independent and well-established systems for dose computation. The reference doses consist of point doses, line doses, as well as 2D and 3D doses. The reference dose sources are

. Published consensus data
. Measured doses
Doses computed in two major competing TPS ●
. Doses computed with an independent Monte Carlo software

RayStation provides support for TG43 dose computation with user specified TG43 parameters for any applicable source. Comparison to OA along-away data ensures that the dose engine can accurately reproduce the dose for a variety of sources given that the input data is correct. Measurement from EQUAL-ESTRO relates computed dose to delivered dose for a setup with three dwell positions. Comparison to an independent and TG43 compliant treatment planning system is used to further validate the correct superposition of dose from a large number of dwell positions. Finally, the comparison to an independent Monte Carlo system decouples the dependence to the TG43 formalism and provides a fully independent validation of a complete treatment plan. The validation demonstrates that the dose computation is adequate for clinical use.

Electron Monte Carlo dose engine update – The electron dose calculation in RayStation supports LINACs using the dual foil scattering technique with applicators and cutouts. The dual foil assembly shapes the electron beam phase space in the upper part of the treatment head (i.e. towards the vacuum window). The applicator and cutout further shape the beam to yield clinically usable lateral flatness and penumbras while minimizing radiation leakage outside of the field.

The electron phase space model in RayStation is designed to model the arrangement sketched above. The implementation is parameter driven and thus generic with respect to a typical dual foil, applicator and cutout arrangement.

The validation strategy is to compare doses computed with RayStation 12A to reference doses. The different reference doses used are

. Measured doses.
. Doses computed in a well-established competing TPS.
. Doses computed with earlier versions of RayStation.
. Doses computed in BEAMnrc/egs++.

Two different gamma criteria for comparison with another TPS or measurement are evaluated for each test case, with specified requirements on level of agreement.

The fraction of the calculated dose data points for comparison with previous RayStation dose that fail has been evaluated, and the fraction of the calculated dose data points for comparison to BEAMnrc/egs++ that fail has been evaluated.

Validation of the new dose engine has been performed which demonstrates that the dose computation is adequate for clinical use.

1.11.1 Conclusion

The non-clinical data support the safety of the device and the software verification and validation demonstrate that the RayStation 12A device should perform as intended in the specified use conditions, and the performance testing demonstrates that the RayStation 12A device performs comparably to the predicate device that is currently marketed for the same intended use.

Regulation Number and Section

§ 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.