K222312 · RaySearch Laboratories AB (PUBL) · MUJ · Mar 29, 2023 · Radiology
Device Facts
Record ID
K222312
Device Name
RayStation 12A
Applicant
RaySearch Laboratories AB (PUBL)
Product Code
MUJ · Radiology
Decision Date
Mar 29, 2023
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 892.5050
Device Class
Class 2
Attributes
AI/ML, Software as a Medical Device, Therapeutic
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Proton ocular treatment dose calculation
Monte Carlo dose calculation engine
95% and 98% of computed depth dose values with Gamma pass rates
—
—
—
—
—
Field in field radiation therapy planning
—
Merged beams' MU shall agree with original beams' MU; segments shall keep original shapes
—
—
—
—
—
HDR brachytherapy dose calculation
TG43 formalism dose calculation
—
—
—
—
—
—
Electron beam dose calculation
Monte Carlo dose calculation engine
Calculated doses shall fail for less than 2% of the data points for gamma 2%/2mm
—
—
—
—
—
Indications for Use
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 Story
RayStation 12A is a treatment planning system (TPS) for radiation therapy and medical oncology. It ingests patient images (CT, PET, MR) and clinical data to identify targets and organs at risk. Users define treatment parameters, and the system uses peer-reviewed algorithms for plan optimization and dose calculation (photon, proton, electron, brachytherapy). It supports automated planning, deformable registration, and adaptive replanning. The system is used in clinical settings by authorized medical staff (physicians, physicists, dosimetrists). Output includes optimized treatment plans, dose distributions, and machine control data, which are reviewed and approved by clinicians before being sent to delivery devices (e.g., linear accelerators, afterloaders) via the RayTreat application. The device facilitates precise radiation delivery, potentially improving therapeutic outcomes while sparing healthy tissue.
Clinical Evidence
Bench testing only. No clinical data. Validation included software verification and validation per FDA guidance for "Major" level of concern software. Dose engine accuracy was validated by comparing computed doses against measured doses, consensus data, and independent Monte Carlo software (BEAMnrc/egs++). Gamma pass rates and depth-dose profiles were used as primary metrics to confirm equivalence to the predicate and clinical adequacy.
Technological Characteristics
Software-based TPS running on standard Windows PCs. Uses Microsoft SQL databases for data storage. Supports DICOM RT. Dose calculation engines include point kernel superposition (Collapsed Cone), Monte Carlo (photon, proton, electron), and TG43 (brachytherapy). Complies with IEC 61217, IEC 62083, IEC 62304, IEC 62366-1, ISO 14971, and IEC 60601-2-68.
Indications for Use
Indicated for patients prescribed external beam radiation therapy or medical oncology treatment. Used for planning, analysis, and administration of treatment plans.
Regulatory Classification
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.
{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)
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.
| 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 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.
{4}------------------------------------------------
| Planning activity | Module | Available in<br>RayPlan |
|-------------------------|------------------------------|-------------------------|
| 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
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.
#### 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 to<br>RayStation 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) and<br>Windows Server 2012 R2 (or higher). |
| Target population | Substantially Equivalent | RayStation 11B and RayStation 12A are intended for the<br>same target population and anatomical sites; persons that |
| Anatomical sites | Substantially Equivalent | have been prescribed an external beam radiation therapy or<br>medical oncology treatment. |
| Human factors | Substantially Equivalent | In terms of human factors, the systems are considered<br>equivalent. The user interfaces are almost identical. |
| Standards met | Substantially Equivalent | Both systems comply with the following FDA-recognized<br>consensus standards: IEC 61217:2011, IEC 62083, IEC<br>62304:2015, IEC 62366-1:2015, ISO 14971:2019 and with<br>IEC 60601-2-68:2014 standard. |
| Image types | Substantially Equivalent | RayStation 11B and RayStation 12A both support CT, PET<br>and MR images for identifying patient organs and contouring. |
| Reporting aspects | Substantially Equivalent | When evaluating and approving treatment plans, all necessary<br>data is presented to the user and available in print in both<br>systems. |
| Image storing | Substantially Equivalent | None of the systems is intended for long term storage of<br>images or other patient data. |
| Network / remote<br>connections and<br>capabilities | Substantially Equivalent | Both systems are capable of network transfer of patient data<br>using the DICOM protocol. RayStation 12A and RayStation<br>11B are designed for desktop use and for remote access using<br>standard virtualization techniques. Remote connection to the<br>system is verified in detail and equivalent to local connection. |
{6}------------------------------------------------
| Cybersecurity | Substantially Equivalent | Both systems are compliant with the requirements listed in<br>the FDA guideline 1825 "Content of Premarket Submissions<br>for Management of Cybersecurity in Medical Devices". |
|---------------|--------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|---------------|--------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Feature | Description | Present in<br>RayStation<br>11B<br>(K220141) | Present in<br>RayStation<br>12A | Significantly<br>changed? |
|----------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------|---------------------------------|------------------------------------------------------------------------------------|
| 3D<br>visualization | Displays the patient geometry and<br>structures in three dimensions, with the<br>possibility to rotate the patient image. If<br>available, the dose distribution and beam<br>modifiers are shown as well. | Yes | Yes | No |
| Adaptive<br>replanning | The process of replanning the treatment<br>for a patient, based on information about<br>e.g. patient geometry, biology and dose<br>delivery acquired during treatment. | Yes | Yes | No |
| Beam<br>commissioning | Modeling of the radiation beam using a<br>limited set of measurements on the clinical<br>beam for commissioning treatment<br>machines to make them available for<br>treatment planning. | Yes | Yes | No |
| Beam design | Definition of beam orientations, apertures<br>and various beam modifiers in order to<br>manually create a treatment plan. | Yes | Yes | No |
| Beam set-up | Manual or automatic definition of<br>isocenter, selection of treatment unit from<br>the set of commissioned treatment<br>machines, and specification of<br>gantry/couch/collimator angles. | Yes | Yes | Yes, new<br>functionality<br>Automatic<br>Field in Field<br>planning was<br>added. |
| Beam's eye<br>view | Displays the beam's eye view of the<br>patient structures, fluence and beam<br>modifier settings for any beam. | Yes | Yes | No |
| Brachy<br>planning | Tools for planning of HDR brachytherapy<br>treatments. Includes channel<br>reconstruction and optimization and<br>editing of dwell times. | Yes | Yes | Yes. Now<br>supports<br>Elekta<br>Flexitron<br>afterloaders. |
| CyberKnife<br>planning | CyberKnife planning is completely<br>integrated in RayStation. This includes<br>optimization of high quality treatment<br>plans collimated with MLC, fixed cones<br>or iris cones, as well as support for all<br>CyberKnife Synchrony techniques for<br>target tracking and real time motion<br>synchronization. | Yes | Yes | No |
| Deformable<br>registration | Establishing a point-to-point mapping<br>between two images using a deformation<br>model. Used for mapping of dose and<br>structures between images. | Yes | Yes | No |
| DICOM RT<br>export | Export of images, structure set, plan, and<br>dose according to the DICOM RT<br>standard. | Yes | Yes | No |
| DICOM RT<br>import | Import of images, structure set, plan, and<br>dose according to the DICOM RT<br>standard. | Yes | Yes | No |
| Dose<br>calculation<br>electrons | For electron beams RayStation calculates<br>dose by the Monte Carlo technique. The<br>electron beam phase space is generated in<br>run time by sampling from a phase space<br>model where the electrons are created at<br>the secondary scattering foil. Both the<br>electron transport through the treatment<br>head and the in-patient dose computation<br>is performed using the Monte Carlo<br>algorithm.<br><br>In versions prior to RayStation 11A, the<br>transport through the treatment head has<br>been handled by a Monte Carlo algorithm<br>developed by RaySearch, while the in-<br>patient transport and dose computation has<br>been the responsibility of the plug-in dose<br>engine VMC++. In RayStation 12A, the<br>VMC++ dose engine has been exchanged<br>with an in-patient Monte Carlo transport<br>and dose scoring algorithm fully<br>developed by RaySearch. Additionally,<br>some minor improvements have been<br>made to the treatment head transport, but<br>this part is essentially the same as in<br>RayStation 11B.<br><br>There are substantial similarities between<br>the replaced VMC++ code and the<br>EGSnrc code and these two Monte Carlo<br>dose engines agrees on sub-percent level<br>[1][2]. The dose engine developed by<br>RaySearch is similar to the EGSnrc, as has<br>been described in references 11, 12, 17, 24<br>and 108 in the 008 RSL-D-RS-12A-REF-<br>EN-1.0-2022-06-23 RayStation 12A<br>Reference Manual. Therefore, we<br>conclude that the electron dose engine<br>used in RayStation 12A (fully developed<br>by RaySearch) is substantially equivalent<br>to the electron dose engine used in<br>RayStation 11B (in-patient dose<br>computation handled by VMC++). | Yes | Yes | Yes |
| | | | | |
| | The supporting testing confirms<br>equivalence between the RayStation 11B<br>and RayStation 12A dose engines.<br>Regression tests performed during the<br>electron dose engine validation between<br>the two versions are within tolerance<br>limits which shows a similar level of<br>accuracy between the two dose engines.<br>Acceptance criteria for comparison with<br>previous RayStation dose: The calculated<br>doses shall fail for less than 2% of the data<br>points for gamma 2%/2mm.<br>References:<br> | | | |
| | Society (Cat. No.00CH37143), Chicago,<br>IL, USA, 2000, pp. 1490-1493 vol.2, doi:<br>10.1109/IEMBS.2000.898024.<br>[2] Kawrakow I, Fippel M, Friedrich K.<br>3D electron dose calculation using a<br>Voxel based Monte Carlo algorithm<br>(VMC). Med Phys. 1996 Apr;23(4):445-<br>57. doi: 10.1118/1.597673. PMID:<br>9157256. | | | |
| Dose<br>calculation<br>photons | For <b>photon</b> beams RayStation calculates<br>dose by the point kernel superposition<br>method (a.k.a. Collapsed Cone) or a<br>Monte Carlo algorithm for radiation<br>transport. The incident energy fluence is<br>modeled as a superposition of a primary<br>energy fluence and a scatter energy<br>fluence. The dose contribution from<br>contamination electrons is calculated by a<br>pencil beam algorithm. | Yes | Yes | No |
| Dose<br>calculation<br>proton | For <b>proton</b> beams RayStation uses either<br>the pencil beam algorithm with the Fermi-<br>Eyges formalism, or a Monte Carlo<br>algorithm for radiation transport. For<br>passive beams the beam model accounts<br>for the collimator and compensator block.<br>For scanning beams the beam model<br>accounts for the spot phase space<br>including effects of air-scatter and beam<br>paths through magnetic deflection<br>elements. The user defined block aperture<br>is taken into account in spot selection and<br>optimization. In addition to this the<br>relative biological effect (RBE) of proton<br>beams is taken into account, resulting in a<br>photon equivalent dose. | Yes | Yes | No |
| Dose<br>calculation<br>brachy | For brachy plans RayStation calculates<br>dose based on the TG43 formalism. | Yes | Yes | No |
| Dose display<br>(2D) | Displays the patient geometry with<br>structures superimposed on the image data<br>together with the dose distribution in<br>transversal, sagittal, and coronal<br>directions. | Yes | Yes | No |
| Dose tracking | Dose tracking scenarios including<br>deformable registration of one CT or<br>CBCT to another and subsequent<br>deformation and accumulation of dose. | Yes | Yes | No |
| Eye planning | Tools for specifying a highly detailed<br>geometrical model of the eye based on<br>measurements from ultrasound and<br>surgery. Support for positioning of<br>tantalum clips. Import and visualization of<br>fundus images. Creation and dose<br>computation of proton plans with gaze<br>angle-based treatment directions. | Yes | Yes | Yes, Now<br>supports eye<br>planning with<br>wedges. |
| Fallback<br>planning | Automatic generation of fallback plans<br>using alternative treatment machines and<br>treatment techniques. User-defined<br>protocols specifies the setup of the<br>fallback plans which are automatically<br>generated from the protocols and<br>optimized using dose mimicking<br>functions. | Yes | Yes | No |
| Image<br>conversion | Conversion of CBCT images to synthetic<br>CT images that can be used for more<br>accurate dose calculations. | Yes | Yes | No |
| Inverse<br>planning | The user can define optimization settings<br>such as optimization tolerance and<br>maximum number of iterations as well as<br>segmentation settings on the multileaf<br>collimator and the Pencil Beam Scanning<br>spot pattern. An interface for controlling<br>the optimization process is provided and<br>the progress of optimization is displayed<br>in a view. The system generates control<br>points for step-and shoot MLC plans,<br>Sliding Window plans (DMLC), rotational<br>plans (VMAT), 3DCRT plans, Wave Arc<br>plans, TomoTherapy plans and proton<br>Pencil Beam Scanning plans, using the<br>defined optimization problem. The inverse<br>planning can be carried out either through<br>a conventional inverse approach or by<br>using multi-criteria optimization (photons<br>and 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.<br><br>The model-based segmentation technique allows for semi-automatic delineation of structures by matching 3D shape models of the structures to new image data.<br><br>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.<br><br>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.…
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.