Search Results

The Motion Tracking and Compensation Feature is an option within the indications for use of the Radixact Treatment Delivery System. The Radixact Treatment Delivery System is indicated for the delivery of radiation therapy, stereotactic radiotherapy or stereotactic radiosurgery to tumors or other targeted tissues anywhere in the body under the direction of a licensed medical practitioner.

The Motion Tracking and Compensation Feature is designed for use with the predicate Radixact Treatment Delivery System last cleared on K161146. The Motion Tracking and Compensation Feature measures tumor location and motion using images provided by a kV imaging subsystem and predicts tumor location based upon a respiration amplitude measurement device. The Radixact Treatment Delivery System then compensates for tumor motion by making real-time adjustments.

The Radixact Treatment Delivery System is a radiation therapy delivery system that provides Image Guided Radiation Therapy (IGRT) using integral megavoltage CT imaging capabilities and delivers helical (rotational) and fixed-angle (non-rotational) radiation therapy to tumors and other targeted tissues.

The provided text describes a 510(k) premarket notification for a new feature (Motion Tracking and Compensation Feature) for an existing device (Radixact Treatment Delivery System). The core of the submission is to demonstrate substantial equivalence to the predicate device, not necessarily to provide specific performance metrics against pre-defined acceptance criteria in the way one might for a diagnostic AI device.

Therefore, the response below will focus on what is available in the text regarding "acceptance criteria" (more accurately, the claims of substantial equivalence) and the "study" (the verification and validation testing) that supports these claims, rather than a typical AI performance table.

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

For a substantial equivalence submission, the "acceptance criteria" are typically demonstrating that the new device feature does not raise new questions of safety or effectiveness compared to a predicate device, and performs as well as the predicate for its intended use. The table below summarizes the claims of substantial equivalence for various characteristics.

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

The document states: "No animal or clinical tests were required to establish substantial equivalence with the predicate device." This indicates that the evaluations were likely based on bench testing, engineering verification, and validation activities rather than clinical data with patient samples. Therefore, there is no "test set" in the sense of a patient data set for an AI/diagnostic device.

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

Not applicable. As no clinical tests were required, experts to establish ground truth for a test set of patient data were not used. The ground truth for engineering tests would be established by physical measurements and adherence to engineering specifications and recognized consensus standards.

4. Adjudication method for the test set

Not applicable. No clinical test set requiring adjudication was used.

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

Not applicable. This device is a radiation therapy delivery system with a motion tracking and compensation feature, not a diagnostic AI device requiring human reader interpretation, nor an AI-assisted diagnostic tool. No MRMC study was mentioned or performed.

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

While the Motion Tracking and Compensation feature includes algorithms, the performance evaluation described as "verification and validation testing" would pertain to the proper functioning of these algorithms within the integrated system, and their impact on the overall system's ability to deliver radiation accurately despite motion. The submission relies on demonstrating that these new components adhere to established safety standards and maintain the device's original performance specifications, not necessarily on a "standalone" algorithmic performance study in isolation from the machine. The document states that the "Motion Tracking and Compensation Feature measures tumor location and motion... and predicts tumor location... [and] compensates for tumor motion by making real-time adjustments," implying that its performance is inherently tied to the system's function.

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

Given the nature of the device (radiation therapy delivery system) and the type of submission (substantial equivalence with waiver of clinical data), the "ground truth" for the device's performance would be:

• Engineering specifications and design requirements: The device's ability to accurately track and compensate for motion according to predefined engineering tolerances.
• Compliance with recognized consensus standards: The device passed tests against relevant IEC and other standards for radiation therapy equipment and medical electrical equipment (e.g., IEC 60601 series).
• Comparison to predicate device's established performance: The analysis repeatedly states that the new features are "substantially equivalent" and do not introduce new safety or effectiveness concerns compared to the already cleared predicate device.

8. The sample size for the training set

Not applicable. This is not an AI/machine learning model in the sense of needing a separate "training set" of patient data for a diagnostic task. The description of the tracking and compensation algorithms suggests they are deterministic or traditional control algorithms, rather than machine learning models requiring extensive training data.

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

Not applicable, as there is no mention of a training set as would be understood for an AI/ML model for diagnostic purposes.

Ask a specific question about this device

ExacTrac Vero is intended to be used in conjunction with the MHI-TM2000 radiation therapy linear accelerator system manufactured by Mitsubishi Heavy Industries, Ltd.

ExacTrac Vero uses the images received from the MHI-TM2000 linear accelerator for analyzing the current patient position and calculating - when applicable - a necessary correction shift. The correction shift is then exported to the MHI-TM2000 linear accelerator.

ExacTrac Vero uses stereoscopic x-ray or cone beam CT registration and optical tracking of infrared reflective markers in order to localize and correct the patient position before and during treatment.

Optionally ExacTrac Vero provides position data for the pan/tilt motion of the TM2000 gantry head to the MHI-TM2000 controller for continuous alignment of the beam orientation with a moving target. The position data is based on target detection via X-ray imaging and IR tracking of external surrogate markers.

ExacTrac Vero is a patient positioning and monitoring system for the MHI-TM2000 Linear Accelerator System by Mitsubishi Heavy Industries Ltd. providing the following main features:

• Patient positioning based on comparison between X-ray images and . CT data provided by a treatment planning system.
• . Patient positioning based on comparison between Cone Beam CT data and CT data provided by a treatment planning system.
• Optionally providing position data for the pan/tilt motion of the MHI-. TM2000 gantry head controller for continuous alignment of the beam orientation with a moving target. The position data is based on infrared tracking of external surrogate markers and the calculated correlation between those external markers and implanted marker positions as detected in X-ray images.
• Monitoring of the patient position during treatment. .

The following main functionalities were already available for the predicate device ExacTrac 3td Party (K072046) and have been found to be substantially equivalent:

• Patient positioning based on comparison between X-ray images, provided by an Imaging Device of the MHI-TM2000 Linear Accelerator System, and CT data provided by a treatment planning system.
• . Patient positioning based on comparison between Cone Beam CT data, provided by an Imaging Device of the MHI-TM2000 Linear Accelerator System, and CT data provided by a treatment planning system.
• Both modalities can be based on anatomical landmarks or implanted . markers.
• . Monitoring of the patient position during treatment.

The new functionality for treatment of moving targets was found to be substantially equivalent with the predicate device Synchrony® Respiratory Tracking System (K120233) by Accuray Inc.

This new feature provides position data for the pan/tilt motion of the MHI-TM2000 gantry head controller for continuous alignment of the beam orientation with a moving target. The position data are based on infrared tracking of external surrogate markers and the calculated correlation between those external markers and implanted marker positions as detected in X-ray images.

Changes to Predicate Device ExacTrac 3"d Party (K072046):

ExacTrac Vero introduces a new functionality that provides in combination with the MHI-TM2000 linear accelerator the option of aligning the treatment beam with moving targets. This new function provides position data for the pan/tilt motion of the MHI-TM2000 gantry head controller for continuous alignment of the beam orientation with the breathing induced movement of the target.

The provided K122451 submission for ExacTrac Vero does not contain a detailed study report with specific acceptance criteria, reported performance, or sample sizes for clinical validation in the format requested. The document outlines general verification and validation methods and concludes that the system is safe and effective based on these procedures, but it does not provide quantitative results against predefined acceptance criteria.

The submission primarily focuses on establishing substantial equivalence to predicate devices (ExacTrac 3rd Party and Synchrony® Respiratory Tracking System) for its functionalities, including patient positioning and monitoring, and a new feature for continuous alignment with moving targets.

However, based on the type of information typically expected for such submissions and what is generally associated with "acceptance criteria" and "device performance" in general medical device development, and what can be inferred from the text, here's an attempt to structure the answer, acknowledging the limitations of the provided document.

1. Acceptance Criteria and Reported Device Performance

The provided document does not explicitly list quantitative acceptance criteria or detailed reported device performance metrics in a tabular format. The submission states that "The verification and validation proves the safety and effectiveness of the system," implying that the device met its internal design and performance specifications, which would include accuracy and precision.

Given the nature of the device (a patient positioning and monitoring system for radiation therapy), typical acceptance criteria would relate to:

• Localization Accuracy: The precision with which the system can determine the position of the target (e.g., tumor, anatomical landmark, implanted marker).
• Correction Shift Accuracy: The accuracy of the calculated correction shift to be applied to the linear accelerator.
• Tracking Accuracy (for moving targets): For the new functionality, the accuracy of continuously tracking a moving target and aligning the beam.
• Latency: The time delay between detecting a position and providing a correction.
• Reliability/Reproducibility: Consistency of measurements.

Without explicit numbers, we can only infer that the device met internal thresholds for these types of performance metrics that are typically aligned with clinical requirements for precision radiation therapy.

2. Sample Size Used for the Test Set and Data Provenance

The document states that the clinical evaluation used:

• "Simulated treatment of anthropomorphic human-bone phantoms within a simulated clinical environment."
• "Retrospective analysis of correlation between breathing and tumor motion."
• "Analysis of existing x-ray image sets acquired during routine clinical use of predicate devices."

Sample Size:

• Phantoms: The number of phantoms used is not specified.
• Retrospective Analysis: The size of the dataset used for retrospective analysis of breathing and tumor motion, and the number of existing X-ray image sets from predicate devices, are not specified.

Data Provenance:

• Phantoms: Simulated clinical environment (location not specified, likely internal to Brainlab AG or a collaborator).
• Retrospective Analysis: Originated from "routine clinical use of predicate devices." The country of origin is not specified, but given Brainlab AG is based in Germany, it's possible this includes European data.
• Prospective/Retrospective: The analysis of phantom data would be considered a form of prospective testing in a simulated environment. The analysis of "existing x-ray image sets acquired during routine clinical use of predicate devices" and "retrospective analysis of correlation between breathing and tumor motion" are explicitly retrospective.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

The document does not specify the number of experts used to establish ground truth or their qualifications for any of the clinical evaluation methods (phantoms, retrospective analysis, or X-ray image sets).

In phantom studies, the "ground truth" is typically established by the known physical properties and precise placement of structures within the phantom, measured independently. For retrospective image analysis, ground truth would typically be established by expert review (e.g., radiation oncologists, radiologists, medical physicists), but this is not detailed.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method (e.g., 2+1, 3+1, none) for the test set or any part of the clinical evaluation. The evaluations appear to be conducted via technical analyses and simulations rather than multi-reader clinical interpretation scenarios.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

The document does not mention or describe a Multi-Reader Multi-Case (MRMC) comparative effectiveness study. There is no information regarding a study comparing human readers with and without AI assistance, or any effect size related to AI improvement. The device itself is a positioning and monitoring system, not primarily an AI-assisted diagnostic or interpretation tool for human readers in the traditional sense of an MRMC study.

6. Standalone (Algorithm Only) Performance Study

The studies described ("Simulated treatment of anthropomorphic human-bone phantoms," "Retrospective analysis of correlation between breathing and tumor motion," "Analysis of existing x-ray image sets acquired during routine clinical use of predicate devices") appear to evaluate the standalone performance of the ExacTrac Vero system. These evaluations focus on the system's ability to accurately perform its functions (patient positioning, correction calculation, and tracking) in a simulated and retrospective context, independent of human interaction during the measurement process, before the human operator would decide to apply a correction.

7. Type of Ground Truth Used

The ground truth for the clinical evaluation was established using:

• Physical Phantom Data: For the "simulated treatment of anthropomorphic human-bone phantoms," the ground truth would be based on the known, precise physical locations of structures and markers within the phantoms.
• Retrospective Clinical Data: For the "retrospective analysis of correlation between breathing and tumor motion" and "analysis of existing x-ray image sets," the ground truth would likely refer to the clinically established information about patient/tumor motion from the original clinical trials or routine use where these images were acquired. This could implicitly involve expert consensus or established treatment plans, but the document does not elaborate.

8. Sample Size for the Training Set

The document does not specify any sample size for a training set. The descriptions of the verification and validation methods focus on testing the developed system, rather than describing the development and training of machine learning models with explicit training datasets. If the system uses machine learning components, the training data is not detailed in this submission.

9. How the Ground Truth for the Training Set Was Established

Since no training set is described or mentioned, the method for establishing ground truth for a training set is not provided.

Ask a specific question about this device