(64 days)
The CyberKnife and CyberKnife VSI Systems are intended to provide treatment planning and image-quided stereotactic radiosurgery and precision radiotherapy for tumors, lesions and conditions anywhere in the body when radiation treatment is indicated. The CyberKnife Systems may be used to treat astrocytoma, glioma, skull base tumors, metastases (brain and bony), nasopharyngeal carcinoma, meningioma, acoustic neuroma, schwannoma, pituitary adenoma, hemangioblastoma, craniopharngioma, arteriovenous malformation, cavernous malformation, trigeminal neuralgia, and tumors of the neck, spine, pancreas, liver, lungs, ovary, prostate, and bladder. Patients should be examined by a team of physicians to determine if they are candidates for CyberKnife treatment.
The CyberKnife Robotic Radiosurgery System and CyberKnife VSI Robotic Radiosurgery System are computer controlled medical systems for planning and performing minimally invasive stereotactic radiosurgery and precision radiotherapy using a treatment radiation generator, linear accelerator, manipulator (robot), and a target locating subsystem to accurately deliver radiation to the treatment target. The target locating system provides X-rays of the treatment area taken by a diagnostic X-ray system that lets the user know the position of the target. The CyberKnife and CyberKnife VSI Systems use skull tracking, fiducial tracking, Xsight® Spine Tracking, Xsight® Lung Tracking, and Synchrony® Respiratory Tracking for dynamic positioning and pointing of the linear accelerator. The system uses a 6 MV linear accelerator to provide a dose rate up to 1000 MU/minute.
The provided 510(k) summary for the CyberKnife VSI™ Robotic Radiosurgery System primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed de novo clinical study with specific acceptance criteria and detailed performance metrics.
Therefore, the requested information, particularly regarding specific numerical acceptance criteria, detailed device performance for those criteria, sample sizes for test sets, expert-established ground truth, adjudication methods, MRMC studies, standalone performance, and training set details, is largely not present in this document.
However, I can extract the available relevant information and highlight what is missing based on your request.
Acceptance Criteria and Study for CyberKnife VSI™ Robotic Radiosurgery System
This device did not present a standalone study with explicit acceptance criteria and corresponding performance metrics in a table format in this 510(k) summary. Instead, it focused on demonstrating substantial equivalence to an existing predicate device (the CyberKnife System). The main acceptance criterion appears to be that the new tracking software performs equivalently to the predicate device's tracking systems.
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| New tracking software performs as designed. | Demonstrated to perform as designed. |
| Tracking performance is equivalent to predicate CyberKnife tracking systems. | Proved to be equivalent to the predicate CyberKnife tracking systems. |
| Integrity of existing features is maintained after updates. | Regression testing verified integrity of existing features. |
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size: Not explicitly stated as a number. The document mentions "Archived images from CyberKnife patient lung treatments." This implies a set of patient data, but the quantity is not specified.
- Data Provenance: Retrospective, as it involved "Archived images from CyberKnife patient lung treatments." The country of origin is not specified, but given the applicant's address in Sunnyvale, California, USA, and FDA submission, it's likely US-based data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications:
- Not specified. The document does not describe a process for establishing ground truth via expert consensus for this specific equivalence testing. The "ground truth" for tracking performance would likely be derived from the inherent physical accuracy of the existing CyberKnife system's tracking mechanisms, which the new software was compared against.
4. Adjudication Method for the Test Set:
- Not specified. This detail is not relevant given the nature of the equivalence testing described.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:
- No, an MRMC study was not described. The submission focuses on the performance of the device's tracking software, not human reader performance with or without AI assistance.
6. If a Standalone (algorithm only without human-in-the-loop performance) was done:
- Yes, in spirit. The testing described involves "tracking software" performance and "regression testing to verify integrity of existing features." This typically refers to the algorithm's direct performance based on inputs (archived images) without active human interpretation as part of the core evaluation. The system itself is "computer controlled."
7. The Type of Ground Truth Used:
- Not explicitly defined in terms of expert consensus, pathology, or outcomes data for this specific testing. Given that it was "tracking performance" compared to a predicate, the ground truth would likely be established by the known, validated performance characteristics of the predicate CyberKnife system's tracking, which the new software aimed to match. This would involve internal validation metrics of positioning accuracy and dynamic targeting.
8. The Sample Size for the Training Set:
- Not specified. The document does not mention details about a training set for the tracking software. It's possible the software relies on established algorithms or models that were trained elsewhere, or that the "new" software is an update or refinement rather than a completely new AI model requiring a distinct training phase.
9. How the Ground Truth for the Training Set was Established:
- Not applicable / Not specified. As no training set details were provided, the method for establishing its ground truth is also not elaborated upon.
Summary of Missing Information:
The 510(k) summary focuses on demonstrating substantial equivalence, which often means showing that the device performs "as well as" or "equivalently to" an existing device, rather than providing absolute performance metrics against predefined acceptance criteria for a novel functionality. Consequently, much of the detailed study design information requested (e.g., number of experts, specific sample sizes for test/training sets, detailed ground truth establishment for novel algorithms) is not present in this type of submission when the primary claim is equivalence via regression testing and performance matching a predicate.
§ 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.