Search Results

The purpose of Panther Treatment Planning System is to provide a complete program for radiation therapy treatment planning. This includes computation, display, evaluation, and output documentation of radiation dose estimations to be submitted for independent clinical review and judgment prior to use. The device provides data in the form of display, hardcopy prints and/or plots to guide a physician in selecting the optimum patient treatment plan. Prowess products are radiotherapy treatment planning programs that allow radiation physicists, and dosimetrists to optimize the delivery of radiation in treating cancer and related diseases.

The radiation therapy treatment planning system provides two-dimensional and three-dimensional planning software for external (photon and electron) treatments using linear accelerators and cobalt-60 beams. The software includes several optional modules which are licensed to users.

IMRT – the IMRT module provides treatment planning for intensity-modulated radiation therapy (IMRT) using external photon beams.

RealART – the RealART module is intended to provide online correction of the position and shape of the beam portals based on the images acquired on the treatment day when the patient is in the treatment position.

ProArc – the ProArc module is intended to support treatment planning by creating treatment plans for intensity-modulated arc radiation therapy.

Stereotactic – the Stereotactic module is intended to support highly advanced precision-targeted radiation planning.

Panther TPS is a three-dimensional treatment planning system for external beam radiation. The software is intended to assist in the relative positioning of radiation therapy treatment devices by predicting the three-dimensional isodose distributions that would be delivered for a particular device setting. It includes computation, display, evaluation and output documentation of radiation dose estimates to be submitted for independent clinical review and judgment prior to use.

Panther TPS is a Microsoft Windows based treatment planning system that includes several modules, each of which has a specific function or series of functions.

This significant change associated with the release of this version is a platform change, adding support for Windows Server.

The provided document, a 510(k) summary for the "Panther TPS" device, does not contain specific acceptance criteria or an explicit "study" proving the device meets performance criteria in the typical sense of a clinical or comparative study. Instead, it relies on demonstrating substantial equivalence to a predicate device (Panther Stereotactic, K193459) through non-clinical testing, hazard analysis, and adherence to quality standards.

The key information regarding performance assessment is detailed in sections 8 and 9 of the 510(k) summary: "Summary of Non-clinical Tests" and "Performance Testing." These sections focus on verification and validation of the software and comparison to the predicate device using identical test cases.

Therefore, many of the requested items (sample size, expert qualifications, adjudication methods, MRMC studies, effect sizes, specific ground truth types) are not applicable or not explicitly detailed in the provided K231825 document, as it focuses on software validation and substantial equivalence rather than a clinical performance study.

Here's a breakdown of the information that is available or can be inferred, and where the document lacks the requested detail:

Acceptance Criteria and Device Performance (Based on available information):

Detailed Breakdown of Study Information:

1. A table of acceptance criteria and the reported device performance: See table above. The acceptance criteria are largely inferred from the general requirements for substantial equivalence and software validation.

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

   • Sample Size: Not specified in terms of number of patient cases or specific test data sets. The document states "established test plans and protocol" and "identical validation test cases." This implies a set of predetermined test cases, but the quantity is not provided.
   • Data Provenance: Not explicitly stated. Given it's a software validation for a treatment planning system, the "data" would likely be simulated patient data, phantoms, or anonymized clinical data used for testing dose calculations and other functions. No country of origin is mentioned. The testing described is "in-house." The nature is implicitly retrospective as it involves testing a developed software against pre-defined scenarios and a predicate.

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

   • Number of Experts: Not specified.
   • Qualifications: "clinical physicists contracted by Prowess." No further detail regarding years of experience or board certification is provided. Their role was in "verif[ying]" the adequacy of methods for mitigating potential risks.

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

   • Adjudication Method: Not applicable or not specified. This type of adjudication is typically for subjective assessments in clinical studies (e.g., image interpretation by multiple readers). The testing described here is primarily a technical verification and validation of software functionality and dose calculation accuracy against established norms or the predicate.

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:

   • MRMC Study: No. The Panther TPS is a treatment planning system, not an AI-assisted diagnostic device where human reader improvement would be measured via MRMC. The study described is a non-clinical software validation demonstrating substantial equivalence.
   • Effect Size: Not applicable.

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

   • Standalone Performance: Yes, in essence. The "Performance Testing" refers to the software's inherent ability to perform calculations and generate plans. 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 is a confirmation of the algorithm's performance independent of a human operator's influence on the algorithm's internal execution (though human users input data and make judgments based on the output).

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

   • Type of Ground Truth: For a radiation therapy treatment planning system, the "ground truth" would generally involve:
     • Physical Phantoms/Measurements: Comparing calculated dose distributions to actual measurements in phantoms.
     • Analytical/Theoretical Calculations: Comparing software calculations to established physics principles or gold-standard analytical solutions.
     • Predicate Device Output: Demonstrating that the new device produces results identical to a legally marketed predicate device for the same inputs (as stated: "Identical validation test cases were performed on both the device and the predicate").
     • Clinical Physicist Review: "verified by clinical physicists" implies expert review of the outputs and methods.
       The document emphasizes the "identical validation test cases" proving substantial equivalence to the predicate, implying the predicate's performance serves as a key reference for correctness.

8. The sample size for the training set:

   • Training Set Sample Size: Not applicable. The Panther TPS is not described as an AI/ML device that requires a training set in the conventional sense (e.g., for pattern recognition or image segmentation models). It's a deterministic software for dose calculation and treatment planning. The "training" in this context would be related to algorithm development and parameterization, not machine learning model training with data.

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

   • Training Set Ground Truth: Not applicable, as it's not an AI/ML device with a training set.

Ask a specific question about this device