Search Results

The BeamSite™ System is intended to be used only with photon external beam radiotherapy during treatment to acquire and visualize the shape of the treatment radiation beam relative to surface anatomical landmarks on the patient, anywhere in the body where radiation treatment is indicated. BeamSite is used by radiotherapy professionals in appropriate hospital and freestanding radiation therapy environments.

BeamSite™ is a camera system that enables live visualization of the treatment beam on a patient during radiotherapy. It is an optically based system that is non-patient contacting and produces no radiation. When the treatment beam is on, BeamSite captures images of Cherenkov light emitted from the patient's skin during radiotherapy to provide an optical map of the treatment beam on the patient. When the treatment beam is off, the system provided continuous background images of the treatment area under ambient light illumination. The BeamSite system consists of a camera, a workstation with preinstalled BeamSite software, and a monitor to be used by clinical radiotherapy teams to a) visually observe the patient and the Cherenkov light emitted from irradiated surface anatomy, and b) review the treatment images, if necessary.

The provided text is a 510(k) summary for the BeamSite™ System, V 1.5. This document focuses on demonstrating substantial equivalence to a predicate device due to minor technological changes. It does not present acceptance criteria or detailed study results for device performance in the typical sense of clinical or standalone algorithm performance.

Here's an analysis of the provided text in relation to your request:

Description of Acceptance Criteria and Study to Prove Device Meets Acceptance Criteria

The provided document describes a Special 510(k) submission where the subject device (BeamSite™ System, V 1.5) is compared to a predicate device (BeamSite System, K200940). The primary purpose of this type of submission is to demonstrate that minor changes to a previously cleared device do not raise new questions of safety or effectiveness.

Therefore, the "acceptance criteria" discussed are largely related to maintaining the performance and safety characteristics of the predicate device. The "study" referenced is primarily a set of non-clinical performance tests designed to confirm that the modified device performs comparably to the predicate and meets relevant safety and quality standards, rather than a study to establish novel performance metrics or clinical efficacy.

1. Table of Acceptance Criteria and Reported Device Performance:

Based on the provided text, a table like the one requested, with specific quantitative acceptance criteria and corresponding reported device performance for clinical or diagnostic metrics, cannot be fully constructed. The document focuses on confirming that the changes in the device (specifically the "always on" imaging mode) do not negatively impact its existing, established performance.

Instead, the document details performance testing repeated on the modified device to support substantial equivalence. The implication is that the performance criteria for these tests were either identical to those successfully met by the predicate device or standard regulatory requirements for device safety and functionality.

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

The document lists non-clinical performance test types, such as functional verification, accelerated age testing, electrical safety, EMC, software V&V, and usability testing. These are primarily engineering and regulatory compliance tests, not data-driven clinical studies with "test sets" in the diagnostic performance sense. Therefore, information regarding:

• Sample size for a "test set" (of patient data/images) is not applicable and not provided.
• Data provenance (country of origin, retrospective/prospective) is not applicable and not provided for this type of non-clinical testing.

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

This information is not provided and is generally not required for the type of non-clinical, substantial equivalence testing described in this document. The device is a "visualization tool" to show the beam on the patient; it's not performing diagnostic or analytical measurements that would require expert-established ground truth on image interpretation.

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

This information is not provided and is not applicable given the nature of the non-clinical performance testing described.

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, an MRMC comparative effectiveness study was not done. The BeamSite system is a visualization tool, not an AI-powered diagnostic or decision-support system intended to improve human reader accuracy. The purpose of the submission is to demonstrate substantial equivalence of a modified version of a previously cleared device, not to prove clinical efficacy or reader benefit.
• The document does not mention any AI components in the device.

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

• No, a standalone (algorithm-only) performance study was not done. The device's function is to provide "live visualization" for "radiotherapy professionals" to "visually monitor radiation therapy." It is inherently a human-in-the-loop system. The non-clinical tests described focus on hardware, software, safety, and usability.

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

Given the non-clinical nature of the testing described (functional verification, safety, EMC, V&V, usability), the concept of "ground truth" as it applies to diagnostic or prognostic studies is not directly relevant to the information provided. The "ground truth" for these engineering tests would be established by reference standards, regulatory requirements, and engineering specifications.

8. The sample size for the training set

• Not applicable and not provided. The BeamSite system, as described, does not appear to be an AI/ML device that requires a "training set" of data for algorithm development. Its function is optical imaging of Cherenkov light and patient surface anatomy.

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

• Not applicable and not provided, as there is no mention of a training set or AI/ML algorithm requiring this.

In summary: The provided FDA 510(k) summary is for a Special 510(k) submission, which focuses on demonstrating that a modified device is substantially equivalent to a predicate device and that the changes do not raise new safety or effectiveness concerns. The "performance testing" described comprises standard engineering and regulatory compliance tests (e.g., electrical safety, EMC, software validation) to confirm the continued safety and functional performance of the device after minor modifications, primarily the addition of an "always on" imaging mode. It does not contain information related to diagnostic performance, clinical efficacy studies, or AI/ML algorithm performance metrics that would involve patient data, expert ground truth, or MRMC studies.

Ask a specific question about this device

The BeamSite™ System is intended to be used only with photon external beam radiotherapy during treatment to acquire and visualize the shape of the treatment radiation beam relative to surface anatomical landmarks on the patient, anywhere in the body where radiation treatment is indicated. BeamSite is used by radiotherapy professionals in appropriate hospital and freestanding radiation therapy environments.

BeamSite™ is a system that enables real-time visualization of the treatment beam on a patient during radiotherapy. It is an optically based system that is non-patient contacting and produces no radiation. BeamSite captures images of Cherenkov light emitted from the patient's skin during radiotherapy to provide an optical map of the beam on the patient. The BeamSite system consists of a camera, workstation with pre-installed BeamSite software and a monitor to be used by clinical radiotherapy teams to visually observe the treatment, as it happens, and review after the treatment, if necessary.

The BeamSite system is designed to be used as a fixed mounted camera having a field of view of the treatment area, to routinely image patient treatments with minimal impact to the clinical workflow. The video images produced are intended to provide additional information about the treatment for the clinical team by displaying the beam size and shape on the patient during treatment. The images produced will provide real-time, direct visual indication that the beam is on, that it is impacting the patient at the intended treatment surface, provides visual feedback regarding the patient's movement relative to the beam, and that surfaces of the body not intended for treatment remain outside the beam path. BeamSite is to be used as a visualization tool. Therapeutic decisions should not be made solely based on the images acquired from this device. However, the images will provide a simple and intuitive means to visually monitor radiation therapy on a routine basis.

The provided text is a 510(k) summary for the DoseOptics BeamSite™ System. This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving the device meets specific performance acceptance criteria for a new clinical claim or an AI algorithm's diagnostic performance. Therefore, many of the requested details regarding acceptance criteria, ground truth, expert adjudication, and MRMC studies, which are typical for AI/ML-based diagnostic devices, are not explicitly present in this document.

The BeamSite™ System is described as an optical visualization tool for radiotherapy, showing the beam shape relative to surface anatomical landmarks. It is not an AI/ML diagnostic or assistive device in the sense that it provides a specific diagnosis, classification, or modifies treatment decisions based on an AI's output. Its primary function is to provide visual feedback to human operators.

Here's an attempt to answer the questions based only on the provided text, highlighting what is present and what is missing:

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

The document does not present a table of specific performance acceptance criteria for the visualization capabilities of the BeamSite System, nor does it quantify its diagnostic performance. The performance testing summarized primarily relates to functional verification, safety (electrical, EMC), software V&V, and usability, which are general engineering and regulatory compliance tests rather than benchmarks for clinical performance metrics (e.g., sensitivity, specificity, accuracy for a diagnostic task).

The "Performance Testing Summary (Non-Clinical)" section lists the types of tests conducted:

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

This information is not provided in the document. The performance testing described is "non-clinical," implying it was not a patient-based clinical trial. If any data was used for functional verification or usability testing, the sample size and provenance are not specified. Given the device's function as a real-time visualization tool and its substantial equivalence argument, a large test set of patient images with verified ground truth (as would be needed for an AI diagnostic device) is not described here.

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)

This information is not provided. As "ground truth" for diagnostic performance is not within the scope of this non-clinical testing summary, no experts are mentioned for this purpose.

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

This information is not provided and is not applicable given the nature of the tests described.

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 MRMC study was conducted or reported. This device is not an AI-assistive diagnostic tool that would typically undergo such a study. It provides raw visual information, and its purpose is not to improve human reader performance on a diagnostic task, but rather to give immediate feedback on beam delivery.

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

This is not explicitly stated or implied. The device is a "system consisting of a camera, workstation with pre-installed BeamSite software and a monitor to be used by clinical radiotherapy teams to visually observe the treatment." It is inherently a human-in-the-loop device, and standalone algorithm performance, separate from human interpretation, is not a relevant measure for its function.

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

As no clinical performance claims (e.g., diagnostic accuracy) are being made based on this device's output, the concept of "ground truth" for clinical images (like expert consensus or pathology) is not applicable or mentioned in this summary. The device visualizes Cherenkov light, which itself is a direct physical phenomenon related to the beam.

8. The sample size for the training set

This information is not provided. The document does not describe the use of machine learning or deep learning that would typically involve a "training set."

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

This information is not provided and is not applicable, as there is no mention of a training set or machine learning.

Ask a specific question about this device