(105 days)
RayStation is a software system designed for treatment planning and analysis of radiation therapy. The treatment plans 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 4.5 is a radiation therapy treatment planning system, i.e. a software program for planning and analysis of radiation therapy treatment plans. Functionality includes fusion capabilities (CT, PET and MRI), contouring, collapsed cone convolution dose computation and 4D data compatibility, as well as unique features such as multi-criteria optimization, dose tracking, treatment adaptation and deformable registration, all available on one platform.
This is a premarket notification for RayStation 4.5, a radiation therapy treatment planning system. The document states that successful verification and validation of RayStation 4.5 support its substantial equivalence to the predicate device, RayStation 4.0.2. However, it does not explicitly define acceptance criteria or detail a specific study with performance metrics for RayStation 4.5. Instead, it refers to the predicate device and the continuation of testing specifications.
Therefore, many of the requested details about acceptance criteria, specific study results, sample sizes, expert qualifications, and ground truth establishment are not present in the provided text.
Based on the available information:
1. A table of acceptance criteria and the reported device performance:
The document does not explicitly state acceptance criteria or provide a table of reported device performance metrics in numerical terms. It broadly states that "The successful verification and validation of RayStation 4.5 therefore support the substantial equivalence of the above RayStation versions." This implies that the device met internal verification and validation requirements, which would include performance benchmarks, but these are not disclosed.
2. Sample size used for the test set and the data provenance:
Not specified in the provided text.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
Not specified in the provided text.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
Not specified in the provided text.
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:
Not applicable. The RayStation is a treatment planning system, not a diagnostic AI device requiring human reader improvement comparison.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
The device is a "software system designed for treatment planning and analysis of radiation therapy." Its performance is inherently "standalone" in generating plans and dose estimates, but these plans are "used to administer treatments after review and approval by the intended user," indicating a human-in-the-loop for clinical application. The document describes a workflow where the user launches RayStation, imports data, creates ROIs, sets up a plan, optimizes it, reviews it, evaluates it, and approves/exports it. This confirms a human-in-the-loop process for clinical use, not a purely standalone AI interpretation.
7. The type of ground truth used:
Not explicitly stated. For a radiation therapy treatment planning system, ground truth would typically revolve around the accuracy of dose calculations, adherence to prescribed dose targets, and safety parameters. This would involve comparisons against established physics models, phantom measurements, and potentially retrospective patient data.
8. The sample size for the training set:
Not applicable. This document describes a software update (RayStation 4.5) to an existing product (RayStation 4.0.2). It is not a de novo AI device that would typically have a distinct "training set" in the machine learning sense. The development likely involved traditional software engineering, verification, and validation processes.
9. How the ground truth for the training set was established:
Not applicable for the reasons mentioned above. Development of this type of software would rely on established physics principles, clinical guidelines, and previous version's validated performance rather than a specific "training set ground truth."
§ 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.