K Number
K181676
Date Cleared
2018-08-15

(51 days)

Product Code
Regulation Number
892.5050
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The PROBEAT-V is a medical device designed to produce and deliver a proton beam for the treatment of patients with localized tumors and other conditions susceptible to treatment by radiation.

Device Description

The PROBEAT-V is a proton beam irradiation system, which provides a therapeutic proton beam for clinical treatment. It is designed to deliver a proton beam with the prescribed dose, dose distribution and directed to the prescribed patient site. The equipment to perform the above work is composed of two main components: (1) a beam delivery system properly delivered and (2) equipment necessary to generate the proton beam and direct it to the beam delivery system for patient treatment.

The beam delivery system is composed of the following components

  • Gantry Room o
  • . Rotating Gantry
  • Scanning Nozzle .
  • . Patient Positioning System
  • Cone Beam CT / X-ray Imaging System .
  • Fixed Beam Room o
  • . Scanning Nozzle
  • Patient Positioning System 트
  • . Cone Beam CT / X-ray Imaging System

The beam production system is composed of the following components

  • Accelerator system (LINAC, Synchrotron) o
  • O Beam transport system (Low/High Energy Beam Transport systems)

The system incorporates several optional features and accessories, namely:

  • The Mini Ridge Filter ("mRF") is an optional accessory to modify the beam of the o PROBEAT-V system. The mRF is installed manually and may be used in conjunction with the range shifters inside the nozzle or extended range shifter. The mRF can be added to the cleared PROBEAT-V nozzle to spread out the Bragg peak along the axis of the beam in order to reduce the amount of beam energy in the delivery of proton radiation to defined target volumes.
  • Beam gating function allowing for interface with cleared external gating systems to o control the beam delivery for treatment such as to synchronize irradiation with respiration. Although the overall treatment time tends to be longer than the treatment time without gating, the extension of the treatment time will not affect irradiation performance to the target treatment site. Instead, the gating functionality may limit radiation exposure to regions outside of the target treatment volume.
  • Allows for use of fluoroscopy during proton irradiation at the physician's discretion. o Fluoroscopy may be used for observation of treatment site during treatment, which could be used for interruption of the treatment or analysis for treatment planning.
AI/ML Overview

The provided text describes a 510(k) premarket notification for a medical device called PROBEAT-V, a proton beam therapy system. It outlines additional optional features and the performance data for these features.

However, the document does not contain the following information typically found in a comprehensive acceptance criteria and study report:

  • A table of acceptance criteria and reported device performance: While it states "All tests were successful and confirmed the performance of these additional optional features," it does not specify quantitative acceptance criteria or the numerical performance metrics.
  • Sample size used for the test set and data provenance.
  • Number of experts used to establish the ground truth for the test set and their qualifications.
  • Adjudication method for the test set.
  • If a multi-reader multi-case (MRMC) comparative effectiveness study was done, or the effect size of human readers improve with AI vs without AI assistance. (This is not an AI device, so an MRMC study related to AI assistance would not be applicable here).
  • If a standalone performance study (algorithm only without human-in-the-loop performance) was done. (Again, not an AI device).
  • The type of ground truth used.
  • The sample size for the training set. (Not an AI/machine learning device that typically requires a training set in that context).
  • How the ground truth for the training set was established. (Not an AI/machine learning device).

Summary of available information regarding acceptance criteria and study:

The device's additional optional features are the Mini Ridge Filter (mRF), an external beam gating function, and the ability to use fluoroscopy during proton irradiation.

1. Acceptance Criteria and Reported Device Performance:

FeatureAcceptance Criteria (Implied)Reported Device Performance
Mini Ridge Filter (mRF)To evaluate range loss, distal dose falloff, and beam spot size."All tests were successful and confirmed the performance of these additional optional features."
External Beam GatingTo ensure appropriate signal reception and adequate gating function."All tests were successful and confirmed the performance of these additional optional features."
Fluoroscopy functionTo ensure fluoroscopy can be enabled/disabled without compromising proton dose monitoring."All tests were successful and confirmed the performance of these additional optional features."

2. Sample size used for the test set and the data provenance:

  • Not specified. The document mentions "testing" but does not detail the number of tests performed or the data used.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

  • Not applicable / not specified. For a physical device like a proton therapy system, "ground truth" relates to physical measurements and engineering specifications, not expert interpretation of outputs in the same way it would for diagnostic imaging devices.

4. Adjudication method for the test set:

  • Not applicable / not specified.

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. This is not an AI-assisted device, so an MRMC study for AI assistance is not relevant.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

  • Yes (for the device's functions). The "Performance Data" section describes testing conducted on the device's features (mRF, gating, fluoroscopy) to confirm their intended function. This is a standalone performance evaluation of the device itself rather than an AI algorithm.

7. The type of ground truth used:

  • Physical measurements and engineering specifications. For a proton therapy system, "ground truth" would be established through calibrated instruments measuring beam properties (range, dose falloff, spot size) and system responses to ensure they meet pre-defined engineering tolerances and physical laws.

8. The sample size for the training set:

  • Not applicable. This device is not an AI/machine learning system that requires a "training set" in the conventional sense. Its functionality is based on established physics and engineering.

9. How the ground truth for the training set was established:

  • Not applicable. As above, no training set in the context of machine learning.

§ 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.