(111 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 4.0.2 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 images obtained from a CT scanner, defining regions of interest either manually or semi-automatically, deciding on a treatment 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.
The provided text is a 510(k) Summary for RayStation 4.0.2, a radiation treatment planning system. However, it does not contain specific acceptance criteria or a detailed study description with performance metrics, sample sizes, ground truth establishment, or expert qualifications necessary to fully answer your request.
The document primarily focuses on demonstrating substantial equivalence to predicate devices (RayStation 3.5 and XiO RTP System) through a general description of functionalities, technological characteristics, and a summary of non-clinical performance data.
Here's a breakdown of what can be extracted and what information is missing based only on the provided text:
1. A table of acceptance criteria and the reported device performance
- Missing Information: The document does not explicitly state quantitative "acceptance criteria" or provide "reported device performance" metrics in the way you've requested (e.g., sensitivity, specificity, accuracy, dice scores, etc.).
- What is reported: The document states that "The summary of the performed non-clinical tests shows that RayStation 4.0.2 is as safe and effective, and performs as well as the predicate devices." This is a qualitative statement of equivalence rather than a quantitative performance metric against specific criteria.
2. Sample size used for the test set and the data provenance
- Missing Information: The document does not specify any sample sizes for test sets (e.g., number of patient cases, images).
- Data Provenance: Not mentioned (e.g., country of origin, retrospective or prospective).
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Missing Information: This information is not provided. The document refers to "verification and validation" and "test results" but does not describe the methodology of establishing ground truth or the involvement of experts in this process for a test set.
4. Adjudication method for the test set
- Missing Information: No adjudication method (e.g., 2+1, 3+1, none) is mentioned.
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
- Missing Information: The document makes no mention of an MRMC study or any AI components, nor does it discuss human reader improvement with or without assistance. The device described is a treatment planning system, not an AI-assisted diagnostic tool in the sense implied by this question.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Missing Information: No information is provided about standalone performance studies for an "algorithm only" where the context suggests AI. The device is a "treatment planning system," implying human interaction is integral.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Missing Information: The document does not specify the type of ground truth used for any testing. It mentions "verification performed for proton planning verifies the functionality for - Proton planning treatment plan calculation, - Proton energy range estimation, - Proton dose calculation, - Pencil Beam Scanning (PBS)." This suggests a ground truth related to physical accuracy of calculations, but how this ground truth was established (e.g., comparison to gold standard physics measurements, theoretical models) is not detailed.
8. The sample size for the training set
- Missing Information: As the document describes a traditional software system rather than a machine learning/AI model, the concept of a "training set" in the context of deep learning is not applicable here, and therefore, no sample size for training is provided.
9. How the ground truth for the training set was established
- Missing Information: Not applicable as per point 8.
Summary of Study Information Provided:
The document describes a non-clinical performance data assessment to support substantial equivalence. The "study" appears to be a verification and validation (V&V) process against internal requirements and the functionalities of predicate devices.
- "General Technology" V&V: The test specification for RayStation 4.0.2 is a "further developed version of the test specification of RayStation 3.5," supported by similar requirements specifications. The "successful verification and validation" of 4.0.2 supports its substantial equivalence to previous RayStation versions.
- "Proton Planning" V&V: Verification was performed for specific proton planning functionalities: treatment plan calculation, energy range estimation, dose calculation, and Pencil Beam Scanning (PBS). These are stated to be the "same functionality as included in the predicate device XiO RTP System."
Conclusion based on provided text:
The 510(k) submission for RayStation 4.0.2 relies on demonstrating substantial equivalence to its predicate devices through internal verification and validation of its expanded functionalities (especially PBS for proton planning). It asserts that the tests performed show the device is "as safe and effective, and performs as well as the predicate devices." However, it does not provide the detailed study characteristics, quantitative acceptance criteria, or performance metrics typically associated with studies for AI/ML-based medical devices. The information supplied is typical for a traditional software update where V&V against existing requirements and functionalities is the primary means of demonstrating safety and effectiveness.
§ 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.