K Number
K050372
Date Cleared
2005-03-25

(39 days)

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

This product is to be used by radiation therapy oncologist or staff under their direction to locate the position relative to the patient of the isocenter of a treatment beam on a gantry mounted radiation therapy treatment machine. Some internal marker must be visible on both a radiograph of the patient taken at the time of treatment and the images used for the treatment plan in order to use this software to align the marker image on the radiograph with the plan to find the proper patient support system coordinates. Only a translation along the couch lateral, longitudinal, and height directions are considered and solved for. Possible rotations or repositioning of the patient are not considered.

Device Description

VisiTrak is a radiation therapy localization software system that assist in aiming the radiation beam. This software uses functions from System 2100, a Radiological Image Display System, 510(k) K993530, and Dosimetry Check, a treatment plan delivery testing system, 510(k) K010225.

The following functions are included in VisiTrak:

  • (1) Means to download a treatment plan from a treatment planning system, to include a stackable image set (such as the CT scans used to generate the plan), beam geometry, and optional regions of interest outlines. [This function from Dosimetry Checkl
  • (2) Means to define and trace a marker that is visible in the stackable image set. [This function from System 2100]
  • (3) Means to draw the markers on two dimensional plane images and three dimensional perspective room views.
  • (4) Means to read in radiographic images made of the patient in the treatment position on the gantry mounted treatment machine.
  • (5) Means to define the geometry for each radiographic image, i.e., in the treatment machine coordinates.
  • (6) Means to project the defined markers onto the radiographic images.
  • (7) Means to manually select couch coordinates to match up the images of the markers on the radiographs with the projected marker images.
  • (8) Means to trace the images of the markers on the radiographs.
  • (9) Means to solve for the best estimate of the couch coordinates that will align the projected and traced marker images.
  • Means to display the couch coordinates for each treatment beam using the (10) couch position found in (7) or (9) above.
AI/ML Overview

The provided text is a 510(k) summary for VisiTrak, a radiation therapy localization software system. While it describes the device's functions and intended use, it does not contain information about specific acceptance criteria, a study proving performance against those criteria, or the detailed methodological information requested.

Therefore, many of the requested points cannot be answered from the provided document.

Here's a breakdown of what can and cannot be extracted:

1. A table of acceptance criteria and the reported device performance

  • Cannot be answered from the text. The document does not define specific acceptance criteria (e.g., accuracy thresholds, precision measurements) or present a table of results from a performance study.

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

  • Cannot be answered from the text. The document mentions the device "mathematically solves for the x, y,z coordinates" and projects markers, but it does not describe any specific testing or validation study with a test set.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

  • Cannot be answered from the text. There is no mention of a test set, ground truth establishment, or experts involved in such a process.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

  • Cannot be answered from the text. No adjudication method is described as no test set or expert review process is detailed.

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

  • Cannot be answered from the text. The document describes a software system that assists in aiming radiation beams, performing calculations and projections. It does not mention any MRMC comparative effectiveness study, nor does it quantify human reader improvement with or without AI assistance. The device's function is more about precision and alignment calculation than interpretive human assistance.

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

  • Cannot be answered from the text. The document describes the software's functionality, which includes both automated projection/solving and manual selection/tracing by users ("Means to manually select couch coordinates," "Means to trace the images of the markers"). It doesn't explicitly state whether a standalone algorithm-only performance test was conducted. The nature of the device suggests it's an human-in-the-loop tool.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

  • Cannot be answered from the text. No ground truth type is specified, as no performance study or test set is described.

8. The sample size for the training set

  • Cannot be answered from the text. The document does not describe any machine learning or AI models that would require a training set, nor does it mention a training set size. The device is described as mathematically solving coordinates and projecting images based on geometric definitions.

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

  • Cannot be answered from the text. Since no training set or machine learning components are mentioned, the establishment of ground truth for a training set is not discussed.

§ 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.