Search Results

Panther Stereotactic is intended to support highly advanced precision-targeted radiation planning.

Panther Stereotactic is an optional software module that has been added to the existing Prowess Panther Treatment Planning System to support planning with multiple shots instead of beams/arcs. Each shot is defined as a full or partial arc of one or multiple radiation sources with different collimator sizes depending on the machine configuration depending on the delivery types. Stereotactic forward planning extends Prowess Panther's existing arc definition features to define shot parameters such as location, size and arc angles. Stereotactic inverse planning extends Prowess Panther's existing simulated annealing algorithm to find optimal shot parameters such as location, size and arc angles.

This document is a 510(k) summary for the Panther Stereotactic device by Prowess, Inc. It describes a software module intended to support highly advanced precision-targeted radiation planning.

Based on the provided text, a comprehensive study proving the device meets specific acceptance criteria, with the details requested, is not explicitly detailed. The document focuses on demonstrating substantial equivalence to predicate devices rather than proving performance against specific quantitative acceptance criteria through a dedicated clinical study with detailed metrics.

However, we can infer information about the non-clinical testing and general verification/validation activities that serve to establish the device's safety and effectiveness.

Here’s a breakdown based on the available information, noting where specific details are not provided:

Acceptance Criteria and Device Performance (Inferred from Non-Clinical Testing):

Since specific quantitative acceptance criteria for performance are not explicitly stated in a table format in the provided text, we must infer them based on the description of the verification and validation (V&V) activities. The primary acceptance criterion appears to be functional correctness, safety, and effectiveness equivalent to predicate devices within a radiation planning context.

1. Sample sizes used for the test set and the data provenance:

• Test Set Sample Size: The document mentions "clinical cases" for beta testing and "established test plans" for in-house verification. However, specific numerical sample sizes for the test set (number of cases/patients) are not provided.
• Data Provenance: The beta testing was conducted by "OUR New Medical Technologies Ltd.", which implies it was an external site, likely a clinical environment. No specific country of origin is mentioned for the data, nor is it explicitly stated whether the cases were retrospective or prospective, though "clinical environment" and "clinical cases" suggest they were real-world patient data. In-house testing uses unspecified "test plans."

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

• The document states that "clinical physicists contracted by Prowess" verified the adequacy of risk mitigation methods. For the beta site testing, "OUR New Medical Technologies Ltd." performed the testing, implying that their clinical staff (likely medical physicists, radiation oncologists, or dosimetrists) were involved in generating and evaluating results.
• Specific numbers or qualifications (e.g., years of experience) of these experts are not provided.

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

• The document does not describe any formal adjudication method for establishing ground truth or evaluating test results, such as a consensus process among multiple readers. The emphasis is on testing by the beta site and verification by Prowess's internal teams and contracted physicists.

4. 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. The device is a radiation therapy treatment planning system, not explicitly described as an AI-assisted diagnostic or decision support tool where human reader improvement would be typically measured. The focus is on the software's ability to plan treatment, not on improving human diagnostic accuracy.

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

• The software's core function is planning. The "functional testing" and "verification and validation" would inherently involve evaluating the algorithm's output (e.g., dose calculations, shot parameter optimization) in a "standalone" sense, though it's always within the context of a treatment planning workflow.
• The document states, "The software has been verified and validated based on established testing plans. The functionalities have been tested by in-house test engineers." This suggests standalone performance evaluation of the algorithms.

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

• For a treatment planning system, "ground truth" would primarily relate to the accuracy of dose calculations against established physics models or benchmarks, and the clinical feasibility/quality of the generated treatment plans.
• The ground truth seems to have been established through a combination of:
  • "Predetermined specifications" for functional testing.
  • Comparison to "substantially equivalent performance to the predicate devices."
  • Verification by "clinical physicists contracted by Prowess."
  • Feedback and verification based on "clinical cases" from the beta site, implying a reference to clinical standards of care and expected plan quality.
• No pathology or patient outcomes data were used as ground truth for this clearance.

7. The sample size for the training set:

• The document describes the device as a "software module that has been added to the existing Prowess Panther Treatment Planning System." It refers to extending existing algorithms ("Panther's existing arc definition features" and "existing simulated annealing algorithm").
• There's no mention of a separate "training set" in the context of machine learning, nor any indication that this module is an AI/ML product developed using a training set. The descriptions point to deterministic algorithms for planning.

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

• As the device is described as an extension of existing deterministic algorithms (not an AI/ML model with a 'training set'), this question is not applicable based on the provided information.

Ask a specific question about this device