Search Results

The Precision™ treatment planning system is indicated for creation and assessment of external photon beam irradiation treatment plans for radiation therapy, stereotactic radiotherapy or stereotactic radiosurgery for lesions, tumors and conditions anywhere in the body when radiation treatment is indicated. A treatment plan provides an estimate of the dose distribution and the parameters utilized by the radiation delivery system. Plans must be reviewed and approved by qualified medical practitioners prior to delivery.

The Precision™ Treatment Planning System is a radiation therapy planning system used for creation and assessment of treatment plans for delivery by radiation therapy, stereotactic radiotherapy or stereotactic radiosurgery treatment systems. It includes the planning system features of both the currently marketed predicate devices: CyberKnife MultiPlan Treatment Planning System (K150873) and the TomoTherapy Planning Station (K121934). Hence, the Precision Treatment Planning System is intended for treatment planning for multiple platforms:

• · Accuray's robotic radiosurgery systems, including but not limited to the CyberKnife® Treatment Delivery System (last cleared K150873).
• · Accuray's ring gantry systems, including but not limited to the Radixact™ Treatment Delivery System which is a next generation TomoTherapy® Treatment System (last cleared K121934).

The provided document is a 510(k) summary for the Accuray Precision™ Treatment Planning System. It describes the device, its intended use, and its substantial equivalence to predicate devices. However, it does not explicitly state acceptance criteria or provide a detailed study report that proves the device meets specific performance criteria through quantitative metrics.

The document focuses on demonstrating substantial equivalence to existing predicate devices (CyberKnife MultiPlan Treatment Planning System (K150873) and TomoTherapy Planning Station (K121934)) rather than presenting a standalone performance study against pre-defined acceptance criteria.

Therefore, many of the requested details such as specific acceptance criteria thresholds, sample sizes for test/training sets, expert qualifications for ground truth, adjudication methods, or MRMC study results are not available in the provided text.

Here's what can be extracted based on the information given, and where information is missing:

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

The document does not provide a table with explicit numerical acceptance criteria. Instead, it states:

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

• Sample Size for Test Set: Not specified.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The document mentions "performance test data" but does not detail its composition.

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)

• Not specified. The document states that "Plans must be reviewed and approved by qualified medical practitioners prior to delivery," implying expert review is part of the clinical workflow, but it doesn't detail their role in establishing ground truth for testing.

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

• 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 MRMC or comparative effectiveness study involving human readers with and without AI assistance is mentioned. The device is a "Treatment Planning System," not an AI-assisted diagnostic tool for human readers. Its primary output is a treatment plan (dose distribution and parameters), not a diagnostic interpretation.

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

• The document implies that the system's performance was evaluated standalone in comparison to the predicate systems, without explicitly calling it an "algorithm only" study. It states, "The performance test data for Precision Treatment Planning System demonstrates that the user will be able to create, save, review and modify treatment plans with the same or higher level of quality as currently produced by each of the individual predicate treatment planning systems." The focus is on the system's ability to generate treatment plans.

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

• Not explicitly stated. Given it's a treatment planning system, the "ground truth" for its performance would likely relate to the accuracy of dose calculations and the ability to generate plans that meet established clinical objectives and physics models, which are typically validated against physical measurements (phantoms) and clinical expert review. The document mentions "review and evaluation against the treatment prescription and established physics models."

8. The sample size for the training set

• The document focuses on the performance of the system as a whole rather than a specific AI component that would require a separate training set. While the system may employ algorithms, the 510(k) summary doesn't detail distinct training sets for machine learning models. Therefore, this information is not provided.

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

• As above, details regarding training sets and their ground truth establishment are not provided in this 510(k) summary.

Ask a specific question about this device

Delivery Analysis is indicated for making:

• Quantitative comparisons of planned and measured MLC fluence sinograms
• Quantitative comparisons of the planned dose distribution to the dose distribution calculated based upon the measured MLC fluence sinogram
• Quantitative comparisons of the delivered detector sinograms from one fraction to another

Delivery Analysis is a software tool that runs on a standalone workstation used to compare radiation therapy pre-treatment and measured in-treatment data with information describing the planned radiation treatment delivery. The pretreatment assessment tools provide a means to confirm whether the multi-leaf collimator (MLC) has performed according to the treatment plan and evaluate any differences in MLC performance that may affect the treatment delivery. The intreatment assessment tools allow comparison of the current radiation treatment fraction as delivered with previous fractions to evaluate the consistency of the treatment delivery with particular sensitivity to variations in patient setup and anatomy.

Delivery Analysis is a computer-based analysis tool for viewing plan and treatment delivery system data, making quantitative comparisons among data sets, trending specific metrics associated with deliveries, and calculating the dose implications for some measured quantities from the treatment delivery system. Delivery Analysis is designed for use with the TomoTherapy Treatment System last cleared under 510(k) number K121934. Delivery Analysis uses the radiation fields that are measured with the TomoTherapy fan-line detector array to provide both theoretical calculations and direct comparisons of raw data on a fraction per fraction basis.

This document (K143269) is a 510(k) summary for a device called "Delivery Analysis" by Accuray Incorporated. It describes the device, its intended use, indications for use, and a comparison to a predicate device. However, it does not provide specific acceptance criteria or an in-depth study detailing quantitative performance metrics as requested.

The document indicates that "Results of verification and validation testing confirm that Delivery Analysis conforms to design specifications and meets the needs of the intended users. No clinical tests were required to establish substantial equivalence. The performance data demonstrate that Delivery Analysis is as safe and effective, and performs as well as the predicate device." This suggests that internal testing was conducted, but the specifics of those tests, including detailed acceptance criteria and reported performance, are not included in this summary.

Therefore, I cannot fulfill your request for a table of acceptance criteria and reported device performance using the provided text.

Based on the provided text, the following information is not available:

• A table of acceptance criteria and the reported device performance
• Sample sizes used for the test set
• Data provenance for the test set
• Number of experts used to establish ground truth for the test set
• Qualifications of those experts
• Adjudication method for the test set
• Whether a multi-reader multi-case (MRMC) comparative effectiveness study was done
• Effect size of human readers improving with AI vs. without AI assistance
• Whether a standalone (algorithm only) performance study was done
• Type of ground truth used (expert consensus, pathology, outcomes data, etc.)
• Sample size for the training set
• How the ground truth for the training set was established

Ask a specific question about this device