(135 days)
The TrueBeam and Edge Systems are intended to provide stereotactic radiosurgery and precision radiotherapy for lesions, tumors, and conditions anywhere in the body where radiation therapy is indicated for adults and pediatric patients.
The TrueBeam and Edge Systems may be used in the delivery of radiation for treatment that includes: brain and spine tumors (such as glioma, meningioma, craniopharyngioma, pituitary tumors, spinal cord tumors, hemangioblastoma, orbital tumors, ocular tumors, optic nerve tumors, and skull based tumors), head and neck tumors (such as unknown primary of the head and neck, oral cavity, hypopharynx, larynx, oropharynx, nasopharynx, sinonasal, salivary gland, and thyroid cancer), thoracic tumors (such as lung cancer, esophageal cancer, thymic tumors, and mesothelioma), gynecologic tumors (such as ovarian, cervical, endometrial, vulvar, and vaginal), gastrointestinal tumors (such as gastric, pancreatic, hepatobiliary, colon, rectal, and anal carcinoma), genitourinary tumors (such as prostate, bladder, testicular, and kidney) lymphoid tumors (such as Hodgkin's and non-Hodgkin's lymphoma), skin cancers (such as squamous cell, basal cell, and melanoma), benign diseases (such as schwannoma, arteriovenous malformation, cavernous malformation, trigeminal neuralgia, chordoma, glomus tumors, and hemangiomas), metastasis (including all parts of the body such as brain, bone, liver, lung, kidney, and skin) and pediatric tumors (such as glioma, ependymoma, pituitary tumors, hemangioblastoma, craniopharyngioma, meningioma, metastasis, medulloblastoma, nasopharyngeal tumors, arteriovenous malformation, cavernous malformation and skull base tumors).
The TrueBeamTM Radiotherapy Delivery System is a medical linear accelerator. The system consists of two major components: 1) a photon, electron, and diagnostic kV X-ray radiation beam-producing component that is installed in a radiation-shielded vault in a healthcare facility and 2) a control console using the device software in an area located outside the treatment room.
Here's an analysis of the provided text regarding acceptance criteria and device performance evaluation, formatted to answer your specific questions.
Device: TrueBeam, TrueBeam STx, and Edge Radiotherapy Delivery System
Manufacturer: Varian Medical Systems, Inc.
FDA Submission: K162472
Date: January 19, 2017
It is important to note that the provided document is an FDA 510(k) clearance letter and associated summary, not a detailed study report. As such, it focuses on demonstrating substantial equivalence to a predicate device rather than presenting raw performance data against specific, quantifiable acceptance criteria in the manner one might find in a clinical trial or a more exhaustive performance study. The "performance testing" section primarily describes the types of testing conducted (e.g., hardware/software V&V, biocompatibility, electrical safety, EMC) and confirms that "passing criteria were met." It does not provide numerical performance metrics or specific acceptance thresholds for output parameters like dose accuracy, beam profile, or treatment delivery precision.
Therefore, the following answers are based on the information available in this specific document. Many of your questions, particularly those related to detailed AI/algorithm study design (like MRMC studies, ground truth establishment methods for large datasets, or specific expert qualifications for image-based diagnostics), are not applicable to this type of device (a radiotherapy delivery system) or the nature of this regulatory submission. This document describes a medical linear accelerator, which is a hardware-based radiation delivery system, not an AI/software diagnostic tool.
1. Table of Acceptance Criteria and Reported Device Performance
As this is a 510(k) summary for a radiotherapy delivery system, the "acceptance criteria" are not reported as specific performance metrics (e.g., accuracy, sensitivity, specificity) for a diagnostic algorithm. Instead, the acceptance criteria are implicit in the conformance to established standards, successful completion of verification and validation (V&V) testing, and demonstration of substantial equivalence to a predicate device. The document states that "passing criteria were met" for all tests.
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Hardware & Software V&V | "Passing criteria were met, device conformance to applicable requirements specifications and assured hazard safeguards functioned properly." |
| Biocompatibility | "Conducted in accordance with the FDA Blue Book Memorandum #G95-1... and International Standard ISO 10993-1... as recognized by FDA." (Implicitly, the device material biocompatibility met acceptance for patient contact.) |
| Electrical Safety | "The system complies with the IEC 60601-1 standards for safety." (Implicitly, safety requirements were met.) |
| Electromagnetic Compatibility (EMC) | "The system complies with the IEC 60601-1-2 standard for EMC." (Implicitly, EMC requirements were met.) |
| Quality Systems | "Conducted according to the FDA Quality System Regulation (21 CFR §820), ISO 13485 Quality Management System standard, ISO 14971 Risk Management Standard and the other FDA recognized consensus standards." (Implicitly, the development and manufacturing processes met regulatory standards.) |
| Software Level of Concern | Designated as "major" level of concern. Software V&V results "showed passing criteria were met and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.'" (Implicitly, software rigor matched risk level.) |
| Substantial Equivalence | "The results of verification, validation and safety standards bench testing demonstrate that the Varian Medical Systems TrueBeam™, TrueBeam STx™ and Edge™ medical linear accelerators are substantially equivalent to their predicate device." (This is the ultimate regulatory acceptance criterion for a 510(k).) |
2. Sample Sizes Used for the Test Set and Data Provenance
This document does not describe a "test set" in the context of a dataset for an AI algorithm evaluation (e.g., images for classification). The testing described is primarily bench testing and verification and validation (V&V) of system functions. Therefore, there is no information on:
- The sample size of a specific test set (e.g., patient data).
- Data provenance (country of origin, retrospective/prospective) for a clinical dataset. The V&V testing typically involves engineering tests, phantom measurements, and software functionality checks, not necessarily a large patient cohort study for performance validation.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Those Experts
This information is not applicable to this type of device and submission. The ground truth for a radiotherapy delivery system's performance is typically established through:
- Physical measurements (e.g., dosimeters, ionization chambers) against known physical principles and standards.
- Engineering specifications and design documents.
- Mathematical models of radiation physics.
- Software testing against expected outputs.
- Comparison to existing, validated devices.
Clinical experts (like radiologists) are involved in defining the clinical indications for the device's use, but not in establishing "ground truth" for the device's technical performance in the way they would for an image-based diagnostic AI.
4. Adjudication Method for the Test Set
This information is not applicable. Adjudication methods like "2+1" or "3+1" are typically used in studies involving human interpretation of medical images or clinical outcomes, where there can be inter-reader variability. The testing described for this device is physical and software-based V&V, not human-reader performance.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, an MRMC comparative effectiveness study was not done or reported in this document. MRMC studies are specific to evaluating how AI assistance affects human reader performance with medical images. This device is a radiotherapy delivery system, not an imaging or diagnostic AI tool that assists human readers.
6. If a Standalone (i.e., Algorithm Only Without Human-in-the-Loop Performance) Was Done
While the device contains significant software components, the "standalone" performance concept (algorithm-only performance) as typically discussed for AI diagnostics is not applicable in the same way. The software controls the hardware to deliver radiation. The performance is assessed based on the accuracy and precision of the system's (hardware + software) delivered radiation, not an independent diagnostic output. The document states that "Software verification and validation bench testing were conducted. Results showed passing criteria were met..." This confirms the algorithm's functionality within the system.
7. The Type of Ground Truth Used
For a radiotherapy delivery system, the "ground truth" for performance evaluation is typically established through:
- Physics principles: Expected dose distribution, beam energy, and geometric accuracy based on fundamental physics.
- Reference standards: Calibrated measurement devices (e.g., electrometers, phantom materials).
- Predicate device comparison: Performance is compared to an existing, legally marketed device to demonstrate substantial equivalence.
It would not be expert consensus, pathology, or outcomes data in the context of device performance testing, though these are crucial for defining the clinical utility and safety in the broader context of radiation therapy.
8. The Sample Size for the Training Set
This information is not applicable. This is not an AI/machine learning device that relies on a "training set" of data in the common sense (e.g., labeled images for deep learning). The software within a linear accelerator is typically developed through traditional software engineering paradigms rather than data-driven machine learning models requiring large training datasets for feature extraction and model building.
9. How the Ground Truth for the Training Set Was Established
As there is no "training set" in the context of machine learning, this question is not applicable.
§ 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.