(240 days)
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.
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.
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.
§ 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.