(171 days)
radiance is a software system intended for treatment planning and analysis of intraoperative radiation therapy by means of electron beams.
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 radiance shall be clinically qualified radiation therapy staff trained in using the system.
radiance is a treatment planning system, that is, 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 alternative plans to find the best compromise, computing the clinical dose distribution, approving the plan and exporting it.
The provided text describes GMV Aerospace and Defence S.A.'s "radiance" device, a radiation treatment planning software, and its 510(k) premarket notification. The submission focuses on establishing substantial equivalence to a predicate device, RayStation (K100552). However, the document does not contain explicit acceptance criteria or details of a study designed to prove the device meets specific performance criteria.
Instead, the submission relies on demonstrating substantial equivalence to an already cleared device. This means the primary "proof" is the argument that radiance is technologically similar to the predicate and raises no new questions of safety or effectiveness.
Here's an analysis based on the information provided, highlighting what is present and what is absent:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Explicitly Stated) | Reported Device Performance |
|---|---|
| None explicitly stated in the document. | Not applicable, as no explicit criteria are provided. |
| Implicit Acceptance Criteria (from Substantial Equivalence): | |
| Technological Characteristics are essentially the same as predicates. | "The technological characteristics are essentially the same as those of the predicate. All devices produce treatment plans with corresponding dose distributions computed using a three dimensional dosimetry engine. All devices have a function of electronic approval of treatment plans by trained and authorized staff, and export in DICOM format for commencing treatment or archiving." |
| No new types of questions about safety or effectiveness compared to the predicate. | "The submitted devices pose the same types of questions about safety or effectiveness as the existing device." |
| Device functions as a treatment planning system for intraoperative radiation therapy via electron beams, providing treatment unit set-up parameters and dose distribution estimates. | This is the stated "Intended Use" of the radiance device, aligning with its role as a treatment planning system. |
| Dose calculations use a three-dimensional dose engine. | "Dose distributions computed using a three dimensional dose engine." |
| Input is externally acquired patient medical images and user input. | "Externally acquired patient medical images and user input." |
| Output is treatment plans with corresponding dose distributions. | "Treatment plans with corresponding dose distributions." |
| Allows electronic approval of treatment plans by trained and authorized staff. | "Allows electronic approval of treatment plans by trained and authorized staff." |
| Dose calculation algorithms are confirmed for a wide variety of field geometries, treatment units, treatment setups, and patient positions, including different dose grid resolution settings. | This is listed under "Dose calculation algorithm confirmation" for radiance. |
Missing Information: The document does not provide quantitative performance metrics (e.g., accuracy, precision, specific tolerances for dose calculation). This is typical for a 510(k) submission based on substantial equivalence, where detailed performance studies might not be required if the device is demonstrated to be equivalent to an already cleared device.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not mentioned.
- Data Provenance: Not mentioned. The submission focuses on device comparison rather than clinical data.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Experts
- Number of Experts: Not mentioned.
- Qualifications of Experts: Not mentioned.
4. Adjudication Method for the Test Set
- Adjudication Method: Not mentioned.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- MRMC Study Done: No. The document does not describe an MRMC study comparing human readers with and without AI assistance. The radiance device is a treatment planning software, not an AI diagnostic aid that would typically involve human reader performance comparisons in this context.
- Effect Size of Human Readers Improvement with AI vs. without AI Assistance: Not applicable, as no MRMC study was performed or discussed.
6. Standalone (i.e., algorithm only without human-in-the-loop performance) Study
- A formal "standalone" study in the sense of a diagnostic algorithm's performance independent of human interpretation is not described. However, the document does state that the device's "Dose calculation algorithm confirmation" was performed for various parameters. This implies an internal validation of the algorithm's output (dose distributions) against expected values or established benchmarks, but the details of this validation are not provided. The study is largely a comparison of features to a predicate.
7. Type of Ground Truth Used
- Type of Ground Truth: Not explicitly stated. For "Dose calculation algorithm confirmation," it would typically involve comparisons against established physics models, phantom measurements, or existing verified treatment planning systems. The document doesn't specify if clinical outcomes or pathology reports were used to validate the treatment plans produced by radiance.
8. Sample Size for the Training Set
- Sample Size for Training Set: Not applicable. As a treatment planning system based on physics models and algorithms, there isn't a "training set" in the machine learning sense. The device's underlying algorithms are developed based on physical principles, not trained on a dataset.
9. How the Ground Truth for the Training Set Was Established
- How Ground Truth for Training Set was Established: Not applicable, for the reasons stated above. The ground truth for the underlying physics models and algorithms would be established through decades of radiation physics research and experimental validation.
§ 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.