(64 days)
RayStation is a software system designed for treatment planning and analysis of radiation therapy. The treatment plaus provide treatment unit set-up parameters and estimates of dose distributions expected during the proposed treatment, and may be used to administer treatments after review and approval by the intended user.
The system functionality can be configured based on user needs.
The intended users of RayStation shall be clinically qualified radiation therapy staff trained in using the system.
RayStation 3.5 is a treatment planning system. i.e. a software program for planning and analysis of radiation therapy plans. Typically, a treatment plan is created by importing patient from a CT scanner, defining regions of interest either manually or semi-automatically, deciding on a realment setup and objectives, optimizing the treatment parameters, comparing rival plans to find the best compromise, computing the clinical dose distribution, approving the plan and exporting it.
This 510(k) submission for RayStation 3.5 focuses on demonstrating substantial equivalence to predicate devices (RayStation 2.5, DCM 2.0, and Proton Vision 7.0) rather than establishing specific acceptance criteria and proving performance against them in a traditional sense for a novel AI device. The document primarily describes the device's functionality and its verification through testing against its own internal specifications, which were developed from the predicate devices' specifications.
Here's an analysis based on the provided text, addressing the requested information to the best extent possible given the nature of the submission:
1. Table of Acceptance Criteria and Reported Device Performance
The submission does not outline explicit, quantitative acceptance criteria for device performance in a table format that would typically be seen for an AI diagnostic device. Instead, the "acceptance criteria" are implied by the verification and validation (V&V) activities ensuring the device performs as well as or substantially equivalent to its predicate devices.
The reported device performance is described qualitatively as "successful verification and validation" and that "RayStation 3.5 is as safe and effective, and performs as well as the predicate devices."
| Feature/Functionality Verified | Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|---|
| General Technology (RayStation 3.5 vs. RayStation 2.5) | Performs as safely, effectively, and with the same basic design and requirements as RayStation 2.5. | "Successful verification and validation of RayStation 3.5 therefore support the substantial equivalence of the two RayStation versions." "RayStation 3.5 is as safe and effective, and performs as well as the predicate devices." |
| Electron Planning (RayStation 3.5 vs. DCM 2.0) | Performs calculations using Voxel Monte Carlo (VMC++) algorithm with electron beam model, supporting treatment planning with electron energies from 4 to 25 MeV, and calculation of asymmetric and non-coplanar fields, equivalent to DCM 2.0. | "The verification performed for electron planning verifies the functionality for... Treatment planning with electron energies from 4 to 25 MeV... Dose calculation for 3D radiotherapy treatment with combined modality plans... Calculation of asymmetric and non-coplanar fields. This is the same functionality as included in the predicate device DCM 2.0. The test results thereby support a determination of substantial equivalence." |
| Proton Planning (RayStation 3.5 vs. Proton Vision 7.0) | Calculates and displays prospective or verification treatment plans for proton therapy, provides tools for proton energy range estimation, proton dose calculation, and dosimetric plan review, equivalent to Proton Vision 7.0. | "The verification performed for proton planning verifies the functionality for... Proton planning treatment plan calculation... Proton energy range estimation... Proton dose calculation. This is the same functionality as included in the predicate device Proton Vision 7.0. The test results thereby support a determination of substantial equivalence." |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the sample size (e.g., number of patient cases) used for the test set. It refers generally to "verification" and "test results" and that "The test specification of RayStation 3.5 is a further developed version of the test specification of RayStation 2.5."
There is no information provided regarding data provenance (e.g., country of origin, retrospective or prospective nature).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
The document does not mention the use of experts to establish ground truth for a test set. The verification seems to be against the expected output of the algorithms and comparison to the predicate devices' established performance, rather than against an expert-derived ground truth.
4. Adjudication Method for the Test Set
As there's no mention of experts establishing ground truth, there is no adjudication method (e.g., 2+1, 3+1) described.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size
No MRMC comparative effectiveness study was mentioned in the provided text. The submission focuses on the technical equivalence of the software's functionality, not on human reader performance with or without the device.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, the studies described are standalone performance evaluations of the algorithms and functionalities within RayStation 3.5. The verification reports on the system's ability to perform calculations (dose, energy range, plan generation) and display plans correctly. The overall device is a "software program for planning and analysis of radiation therapy," implying an algorithm-only evaluation for its core functions.
7. The Type of Ground Truth Used
The ground truth implicitly used for the verification tests is the expected output of the algorithms based on established physics models (Voxel Monte Carlo for electrons, and general proton dose calculation models) and the functionality of the predicate devices. It's not expert consensus, pathology, or outcomes data, but rather adherence to computational accuracy and functional specifications derived from existing, cleared devices.
8. The Sample Size for the Training Set
The document does not mention any training set or machine learning components in the traditional sense that would require a training set. The device is described as performing calculations based on algorithms (e.g., VMC++) and models, not learning from data in the way a modern AI algorithm might. Therefore, a "training set sample size" is not applicable based on the provided information.
9. How the Ground Truth for the Training Set Was Established
Since there is no mention of a training set, the establishment of ground truth for it is not applicable. The algorithms used (like VMC++) are based on physics principles, not learned from labeled data.
§ 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.