(259 days)
The Radixact Treatment Delivery System is indicated for the delivery of radiation therapy stereotactic body radiotherapy (SBRT), or stereotactic radiosurgery (SRS) to tumors or other targeted tissues anywhere in the body under the direction of a licensed medical practitioner. The megavoltage x-ray radiation is delivered using rotational, intensitymodulated (IMRT), or non-modulated (non-INRT/three-dimensional conformal) treatment techniques and using imageguided (IGRT) or non-image-guided workflows in accordance with the physician-approved plan. The Radixact Treatment Delivery System integrates Surface Guided Radiation Therapy (SGRT) for patient position and motion monitoring, and breath-hold gating.
The predicate and modified Radixact Treatment Delivery Systems are radiation therapy delivery systems, that provide megavoltage CT imaging capabilities coupled with x-ray radiation delivery. The system achieves delivery using rotational, intensity modulated (IMRT), or non-modulated (non-IMRT/three-dimensional conformal) radiation therapy treatment techniques utilizing image-guided (IGRT) or non-image-guided workflows, to tumors or other targeted tissues anywhere in the body, in accordance with the physician-approved plan.
The additional feature update: VitalHold incorporates an external optical monitoring system (EMS), which is integrated with the Radixact system to enable Surface Guided Radiotherapy (SGRT) for patient setup, patient position and motion monitoring, and breath-hold gating.
Neither the predicate Radixact Treatment Delivery System nor the modified Radixact Treatment Delivery System diagnose disease or quantify treatment effectiveness. Accordingly, they are not intended for diagnostic use.
The provided text describes a 510(k) premarket notification for the Radixact Treatment Delivery System, which is a medical device for radiation therapy. The submission focuses on the substantial equivalence of the modified device to a legally marketed predicate device.
It's crucial to understand that this document does not describe a study involving AI-driven diagnostic or treatment planning software that requires complex acceptance criteria based on human expert review, high-volume datasets, or MRMC studies. Instead, it describes a hardware and software update to an existing radiation therapy delivery system, primarily the integration of a Surface Guided Radiotherapy (SGRT) system for patient positioning and motion monitoring, and breath-hold gating.
Therefore, many of the requested elements regarding acceptance criteria for AI performance (like sensitivity, specificity, MRMC studies, large training/test sets for AI, expert readers for ground truth, and adjudication methods) are not applicable to this type of device submission as described in the provided text.
The "Performance Data" section primarily addresses engineering verification and validation, compliance with electrical safety and EMC standards, and risk management. The "Non-Clinical Data" section focuses on testing the functionality of the SGRT integration with the core Radixact system, not AI performance. It states "No animal or clinical tests are being submitted to establish substantial equivalence with the predicate device."
Here's a breakdown of the requested information based on the provided text, indicating where information is present and where it is not applicable or not detailed for this type of device:
Acceptance Criteria and Study for Radixact Treatment Delivery System (K223159)
This submission is for a modification to an existing radiation therapy delivery system, primarily focusing on the integration of a Surface Guided Radiotherapy (SGRT) system for patient positioning and motion monitoring, and breath-hold gating. The "study" described is primarily engineering verification and validation testing to demonstrate the device's functionality, safety, and effectiveness, not a clinical trial or an AI performance study as typically understood for diagnostic support systems.
1. A table of acceptance criteria and the reported device performance
The document lists "Key system performance attributes" related to the SGRT integration and states that "The Verification results show that the design goals and objectives had been met." However, it does not provide a quantitative table of specific acceptance criteria values and reported performance values beyond stating that the tests demonstrated conformity to design specifications and met user needs. The performance attributes mentioned are functional:
| Acceptance Criteria (Functional) | Reported Device Performance (as stated) |
|---|---|
| 1. Track a moving surrogate | "Verification results show that the design goals and objectives had been met." "Data within this submission... include data, discussion, and results." (Implying successful tracking) |
| 2. Deliver treatment beam to the surrogate | "Verification results show that the design goals and objectives had been met." (Implying successful beam delivery in relation to the surrogate) |
| 3. Pause the treatment beam when the surrogate has moved out of a defined threshold, i.e., gating window | "Verification results show that the design goals and objectives had been met." (Implying successful pausing when out of threshold) |
| 4. Inform the user to resume the treatment beam when the surrogate moves within the defined threshold | "Verification results show that the design goals and objectives had been met." (Implying successful user notification for resumption) |
| Overall Safety and Effectiveness | "The modified Radixact Treatment Delivery System meets the safety and performance criteria and is substantially equivalent with reference to safety and effectiveness to the predicate Radixact Treatment Delivery System." "The enhanced ability to turn the MV beam on in under one second." |
| Compliance with Standards | Conforms to listed electrical safety, EMC, radiation protection, and usability standards (e.g., ANSI AAMI ES60601-1, IEC 60601-1-2 Ed 4.1, IEC 60601-2-1 Ed 3.1) and regulatory references (21 CFR §820, ISO 13485, ISO 14971). |
2. Sample size used for the test set and the data provenance
- Test Set Sample Size: Not specified in terms of patient cases or images for performance testing. The "Non-Clinical Data" section refers to "testing outlined above" (functional tests with a "moving surrogate"), which are likely engineering tests rather than patient studies.
- Data Provenance: Not applicable in the context of patient data for a test set. The validation is primarily technical/engineering.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not Applicable. This submission does not involve AI-driven diagnosis or analysis requiring expert interpretation of medical images to establish ground truth for a test set. The "ground truth" for the functional tests would be the controlled movement of the surrogate and the expected system response, not expert consensus on clinical data.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
- Not Applicable. There are no medical image interpretations requiring adjudication for this device's submission as described.
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
- No Multi-Reader Multi-Case (MRMC) study was done. The document explicitly states: "No animal or clinical tests are being submitted to establish substantial equivalence with the predicate device." This device is a treatment delivery system, not a diagnostic AI system intended to assist human readers in interpretation.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
- The performance evaluation focused on the integrated system's functional capabilities (tracking, beam delivery, pausing, informing user). While the SGRT system itself performs some automated actions (e.g., gating the beam), the evaluation is of its function within the treatment delivery workflow, not as a standalone AI algorithm producing outputs for human review. The document does not describe "algorithm only" performance as a separate study element in the context of an AI-driven system.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Type of Ground Truth: For the "Key system performance attributes" related to the SGRT, the ground truth would be the controlled and known physical parameters of the moving surrogate (e.g., its position, movement beyond/within thresholds) and the expected system response according to design specifications. This is typical for engineering verification and validation of a mechanical/software system, not clinical ground truth from patient data like pathology or expert consensus.
8. The sample size for the training set
- Not Applicable. This document does not describe the development of a machine learning (AI) model with a "training set" in the context of diagnostic or predictive AI. The submission is for a hardware and software update to a radiation therapy delivery system.
9. How the ground truth for the training set was established
- Not Applicable. As there is no described training set for an AI model, this question is not relevant to the provided text.
§ 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.