Search Results

The Panther StereoSeed module is intended to create a plan that is optimized for seed locations and needle directions, allowing needles to be inserted in any angle in order to avoid critical structures.

Panther StereoSeed is an optional software module that has been added to the existing Prowess Panther Brachy system to produce a seed implant plan that is optimized for seed locations and needle directions. The key distinction between Panther StereoSeed and traditional brachytherapy systems is that StereoSeed allows plans to be created such that bones and critical structures can be avoided.

The provided text does not contain detailed acceptance criteria or a study that definitively "proves" the device meets specific performance criteria in a quantitative sense with specific metrics and thresholds. Instead, it describes a substantial equivalence submission to the FDA for the Panther StereoSeed device.

Based on the information provided, here's a breakdown of what can be extracted:

1. Table of Acceptance Criteria and Reported Device Performance:

The document focuses on demonstrating substantial equivalence to predicate devices rather than meeting specific quantitative performance acceptance criteria in the typical "accuracy/sensitivity/specificity" sense. The "acceptance criteria" are broad and relate to safety and effectiveness, as demonstrated by verification and validation testing, and comparison to predicate devices.

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

• Sample Size for Test Set: The document mentions "real patient cases" were used for beta testing at the user site. However, the exact number of cases or the sample size of the test set is not specified.
• Data Provenance: The beta testing was conducted at the Department of Minimal Invasive Cancer Center of Inner Mongolia Cancer Hospital (IMCH) in Hohhot City, China, using "real patient cases." This suggests the data was retrospective (using existing patient data) or, less likely but possible, prospective (patients treated during the beta test), but the document does not explicitly state which. Given "real patient cases" and a beta test, it's more likely retrospective in nature, or a mix, to evaluate the planning system.

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

The document mentions "beta testing at the Department of Minimal Invasive Cancer Center of Inner Magnolia Cancer Hospital (IMCH) in Hohhot City, China using real patient cases." It also states, "Detailed methods of mitigating these potential risks have been identified by the development team, and verified by clinical physicists contracted by Prowess and determined to be adequate."

• The number of experts involved in establishing ground truth for the test set is not specified.
• The qualifications of the experts involved in verifying risks are mentioned as "clinical physicists contracted by Prowess." No specific experience level is given. It is implied that these physicists, or other clinical personnel at IMCH, would be the experts using and evaluating the device and its output in real patient cases, thereby implicitly contributing to the "ground truth" assessment of plan quality and safety, but this is not explicitly detailed as a ground truth establishment process.

4. Adjudication Method for the Test Set:

None is mentioned. The beta testing was conducted to "obtain feedback and to verify the results of in-house testing in a user environment." This suggests an evaluation rather than a formal adjudication process for establishing a definitive ground truth by consensus.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

No. The document describes a substantial equivalence submission, which typically does not involve MRMC comparative effectiveness studies with human readers. The comparison is primarily between the device's features and its predicate devices, validated through technical testing and user-site feedback.

6. If a Standalone (algorithm only without human-in-the-loop performance) Study was done:

Yes, in-house verification and validation (V&V) testing was performed. "Functional testing was conducted both in-house... Verification and validation testing has demonstrated that Panther StereoSeed has met its predetermined specifications, demonstrated substantially equivalent performance to the predicate device, functions as intended, and is safe and effective for its specified use." This implies testing of the algorithm's performance against specifications without direct human intervention as part of the primary performance metric.

7. The Type of Ground Truth Used:

For the in-house V&V, the "ground truth" would be established by the predetermined specifications for the software and potentially synthetic data or established clinical scenarios. For the beta testing with "real patient cases," the "ground truth" would likely be evaluated against clinical judgment and established treatment planning principles by the clinical users at IMCH, but this is not explicitly detailed as a formal "ground truth" labeling process in the document. No mention of pathology or outcomes data as ground truth is made.

8. The Sample Size for the Training Set:

This information is not provided in the document. The Panther StereoSeed is described as an "optional software module" that "produce[s] a seed implant plan that is optimized for seed locations and needle directions." The text implies an optimization algorithm rather than a machine learning model that requires a distinct "training set." Therefore, a traditional "training set sample size" may not be applicable in the sense of supervised learning.

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

This information is not provided. As noted above, the device's description suggests it might not rely on a traditional machine learning "training set" with established ground truth labels, but rather on optimization algorithms built upon predefined rules and clinical principles.

Ask a specific question about this device

Panther QIS|R&V is an information management system used to manage medical data and clinical workflow in a hospital or clinic. To support radiation oncology users, it allows the user to:

• . Enter or import, modify, store and archive treatment plans and images from treatment planning systems.
• Import, view, manipulate, enhance, annotate, store, and archive radiological . images.
• Select and provide radiation treatment plans to a radiation treatment delivery . system for patient treatment.
• Store and view treatment records provided by the radiation treatment delivery . system.
• Monitor and track treatment progress. +
• When Panther OIS|R&V is acting as an R&V system, verify the delivery device's . settings against the planned parameters, record the treatment parameters settings and prevent treatment if the parameters are out of tolerance.

Panther OIS|R&V is medical device software which allows the user to deliver radiation treatment on linear accelerator to a patient. The software has been developed to be a record and verify system that also manages oncology medical information in order to simplify the oncologist administrative tasks and to optimize the quality of patient treatment. It is a Windows® based system, which uses a single database that can be accessed by any Panther OIS|R&V client station in the treatment facility. Additionally, Panther OIS|R&V is capable of performing such functions as:

• lmporting treatment plans in DICOM or RTP format -
• Downloading of beams contained in the treatment plans to the linear accelerator ﺖ
• Verifying that the beams from the treatment plan are correctly set up on the linear accelerator
• Recording treatments delivered by the linear accelerator -
• Managing patient schedules ・
• Managing schedules for resources such as treatment machines and personnel "
• Maintaining a central repository of treatment plans and records -
• Documenting, monitoring and updating treatments and treatment plan information -
• Performing administrative tasks such as patient management. -
• Data locking or warning to prevent simultaneous access to patient (Tx) data -
• -Reports of patients and treatment history
• Manual Recording of treatment beams ﺖ
• Late Resumption of incomplete treatments -

The provided text describes the Panther OIS|R&V, a medical device software for radiation therapy record and verify systems. The 510(k) summary (K122616) details how the device meets its acceptance criteria through non-clinical testing.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a specific table of quantitative acceptance criteria with corresponding performance metrics like sensitivity, specificity, accuracy, or AUC for the Panther OIS|R&V device. Instead, it discusses meeting predetermined specifications and pass/fail criteria through verification and validation.

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

• Sample Size: Not explicitly stated as a number of cases or patients. The document mentions "clinical cases" were used by the beta-site for testing.
• Data Provenance: The beta-site testing was conducted at Community Memorial Hospital. This suggests the data is prospective in nature, as it was part of device development and external testing in a clinical setting. The country of origin would be USA, given Community Memorial Hospital is referenced and the submission is to the FDA.

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

• Number of Experts: Not explicitly stated for the beta-site testing itself.
• Qualifications of Experts: The document mentions "clinical physicists contracted by Prowess" were involved in verifying mitigation strategies identified during risk analysis. While not directly stated as establishing ground truth for the test set, this indicates that qualified clinical experts were involved in the overall safety and effectiveness assessment. For the beta-site, it would be implied that hospital staff (oncologists, radiation therapists, physicists) were the "experts" using the system and providing feedback.

4. Adjudication Method for the Test Set

The document does not describe a specific adjudication method (e.g., 2+1, 3+1, none) for the beta-site testing. The nature of testing a Record & Verify (R&V) system is often based on functional validation against expected behavior and safety checks rather than consensus-based ground truth on diagnostic findings.

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 comparative effectiveness study involving human readers and AI assistance is described in this document. The device is not an AI-assisted diagnostic tool but rather an information management and R&V system. The comparison is primarily against existing predicate R&V systems, focusing on functional equivalence and safety, not on improving human reader performance.

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

Yes, the core of the submission (and the "Summary of Non-clinical Tests") indicates that extensive standalone testing (algorithm only) was performed in-house to verify and validate the software according to its protocol and specifications. The "beta-site" testing, while involving human users in a clinical setting, was also focused on validating the system's intended functions and safety in a real-world scenario, essentially testing the "algorithm only" in its operational environment. The system's primary functions (importing plans, downloading beams, verifying settings, recording treatments) are automated or semi-automated functions of the software itself.

7. The Type of Ground Truth Used

The "ground truth" for verifying this type of software system (an R&V system) would not typically be pathology or outcomes data in the traditional sense, but rather:

• Predetermined Specifications/Expected Behavior: The software's outputs and actions are validated against predefined system requirements, design documents, and expected behavior.
• Functional Accuracy: Verification that the system correctly imports, processes, verifies, and records data according to established radiation therapy protocols and standards. For instance, whether the system accurately verifies that linear accelerator settings match planned parameters.
• Safety Requirements: Validation that the system correctly prevents treatment delivery if parameters are out of tolerance, manages data access securely, and maintains data integrity.
• Comparison to Predicate Devices: Demonstrating that its performance and functionality are equivalent to legally marketed predicate devices.

8. The Sample Size for the Training Set

The document does not provide information about a "training set" in the context of machine learning. The Panther OIS|R&V system, as described, is a record and verify software system, not an AI/ML diagnostic or predictive algorithm that typically requires a large training dataset. Its development would involve traditional software engineering and testing methodologies rather than machine learning training.

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

Since the device is not described as utilizing machine learning or AI that requires a "training set," this question is not applicable based on the provided information. The "ground truth" for its development and testing would be derived from clinical requirements, software specifications, and established radiation oncology best practices, rather than labeled data for algorithm training.

Ask a specific question about this device

The Prowess Panther ProArc module is intended to support radiation treatment planning by creating treatment plans for intensity-modulated arc radiation therapy.

Panther ProArc is an optional software module to the Prowess Panther radiation therapy treatment planning system. It is an extension to the inverse planning, IMRT planning capability provided by Prowess Panther (previously cleared under K032456). Panther ProArc includes tools for visualizing and creating arc therapy plans, defining arc therapy beam properties and constraints, and allowing the user to do export these plans for delivery via DICOM protocol to the linear accelerator for treatment.

The provided text does not contain specific information about acceptance criteria, detailed device performance metrics, or a formal study with statistical data for the Prowess Panther ProArc module. The document is a 510(k) summary for regulatory clearance, primarily focusing on demonstrating substantial equivalence to predicate devices rather than proving specific performance against predefined acceptance criteria.

However, based on the information provided, here's a breakdown of what can be inferred and what is not available:

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

The document does not provide a table of acceptance criteria with corresponding performance metrics. It generally states that the device "met its predetermined specifications" and "demonstrated substantially equivalent performance to the predicate devices, functions as intended, and is safe and effective for its specified use."

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 explicitly stated. The document mentions "real patient cases" were used during beta testing, but the number of cases is not specified.
• Data Provenance: The beta testing was conducted at "Medical College of Wisconsin and Huntsman Cancer Hospital," suggesting data from the USA.
• Retrospective or Prospective: Not explicitly stated. The phrase "using real patient cases" could imply either.

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)

• Number of experts: The "medical physicists at Medical College of Wisconsin and Huntsman Cancer Hospital" were involved in functional testing and beta testing. Additionally, "clinical physicists contracted by Prowess" were involved in verifying risk mitigation. The exact number and their specific roles in establishing ground truth for a test set are not detailed.
• Qualifications of experts: They are referred to as "medical physicists" and "clinical physicists." Specific years of experience or board certifications are not provided.

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

The document does not describe any specific adjudication method for establishing ground truth from multiple experts.

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

A formal MRMC comparative effectiveness study, as typically understood for AI-assisted diagnostic tools, was not conducted or reported. This device is a treatment planning system, not a diagnostic AI. The evaluation focused on substantial equivalence to existing treatment planning systems, not on improving human reader performance.

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

The "verification and validation of the software was performed in-house according to established test plans and protocol," which included "functional testing." This internal testing would represent the standalone performance of the algorithm. Additionally, "beta testing at Medical College of Wisconsin and Huntsman Cancer Institute using real patient cases" also evaluated the software's performance, likely in a user environment.

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

The document implies that the ground truth for evaluating the treatment plans generated by Panther ProArc was established by comparing its output with "predetermined specifications" and by showing "substantially equivalent performance" to predicate devices. This would likely involve:

• Physics-based calculations: Verification of dose distribution, dose-volume histograms (DVH), and other dosimetric parameters against expected values or those generated by the predicate devices.
• Clinical expert review: Medical physicists and clinical physicists would review the generated plans for clinical acceptability and adherence to treatment goals.
• Comparison to predicate devices: The "ground truth" for substantial equivalence was largely defined by the performance of the legally marketed predicate devices (Varian's Eclipse and CMS's Monaco RTP System).

8. The sample size for the training set

This information is not provided. The document does not discuss a "training set" in the context of machine learning, as this is a radiation therapy treatment planning system, implying a more deterministic or rule-based software, rather than a machine learning model that requires explicit training data.

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

Not applicable, as a training set for machine learning is not mentioned. For a treatment planning system, the "knowledge base" would be derived from physics principles, clinical guidelines, and potentially pre-defined planning templates or parameters, rather than a "ground truth" derived from a specific dataset.

Ask a specific question about this device

The intended use of Puma is to allow the radiation therapist to deliver treatment to the patient via linear accelerator (linac). This entails selection of the patient, selection of the day's correct treatment for the patient, set up, and delivery of the treatment fields and recording of the treatment. Puma supports auto-sequencing, a process of automatically downloading a group of fields or segments from the record and verify system to the control of the linear accelerator sequentially, without user intervention. In addition, Puma also supports IMRT (Intensity Modulated Radiation Therapy), a process of shaping, modifying and moving the beam around a target to maximize the dose at the target and minimize the dose to normal structures.

Puma is a medical device, which allows the user to deliver radiation treatment on linear accelerator to a patient. The software has been developed to be a record and verify system that also manages oncology medical information in order to simplify the oncologist administrative tasks and to optimize the quality of patient treatment. It is a Windows® based system, which uses a single database that can be accessed by any Puma client station in the treatment facility. Additionally, Puma is capable of performing such functions as:

• Importing treatment plans in DICOM or RTP format -
• Downloading of beams contained in the treatment plans to the linear accelerator -
• Verifying that the beams from the treatment plan are correctly set up on the linear accelerator -
• Recording treatments delivered by the linear accelerator ・
• Managing patient schedules -
• Managing schedules for resources such as treatment machines and personnel -
• Maintaining a central repository of treatment plans and records -

Here's an analysis of the provided text regarding the acceptance criteria and study for the Prowess Puma device:

The provided text (K100801 for the Puma device) is a 510(k) summary, which focuses on demonstrating substantial equivalence to predicate devices rather than establishing novel safety and effectiveness criteria through extensive clinical trials. As such, the information on specific acceptance criteria and detailed study results, particularly for standalone performance or comparative effectiveness with human readers, is limited.

Here's a breakdown of the requested information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state quantitative acceptance criteria or performance metrics in a table format. Instead, it relies on general statements of meeting specifications and being "as safe and effective" as predicate devices.

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

• Sample Size for Test Set: The document mentions "real patient cases" were used during beta testing at Auburn University, but does not specify the sample size (number of cases or patients) for this test set.
• Data Provenance: The beta testing was conducted at "Auburn University," which is in the USA. The data was from "real patient cases" and was likely retrospective as it refers to "clinical cases" used for testing a developed device.

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

• Number of Experts: The document states "medical physicists/dosimetrists at Auburn University" conducted functional testing and "clinical physicists contracted by Prowess" verified risk mitigation. It does not provide an explicit number of experts.
• Qualifications of Experts: "Medical physicists/dosimetrists" and "clinical physicists" are mentioned. No specific experience levels (e.g., "10 years of experience") are provided.

4. Adjudication Method for the Test Set

The document does not describe an explicit adjudication method (e.g., 2+1, 3+1). The testing involved "medical physicists/dosimetrists" and "clinical physicists" validating the system, implying their professional judgment served as the benchmark, but the process for resolving disagreements is not detailed.

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, an MRMC comparative effectiveness study involving human readers assisting with or without AI was not conducted or described.
• Effect Size: Therefore, no effect size for human reader improvement with AI assistance is reported. The Puma device is a record and verify system, not primarily an AI-driven diagnostic or interpretative tool designed to "assist human readers" in the typical sense of AI-enabled image analysis.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Standalone Performance: The non-clinical tests involved "Verification and validation of the software... Functional testing was conducted both in-house and by medical physicists/dosimetrists." This implies extensive standalone (algorithm only) testing against predetermined specifications. The core function of Puma is as a "record and verify system" that automates certain processes (like auto-sequencing), meaning its performance inherently relies on the algorithm operating correctly without continuous human intervention during those automated steps. The clinical physicist/dosimetrist involvement was to validate these functions.

7. The Type of Ground Truth Used

The ground truth for the testing appears to be based on:

• Predetermined Specifications: The software "has met its predetermined specifications."
• Expert Consensus/Clinical Judgment: Functional testing by "medical physicists/dosimetrists" and verification by "clinical physicists" against "real patient cases" implies that the correct operation and output were judged against established clinical practice and expert knowledge in radiation therapy planning and delivery.
• Comparison to Predicate Devices: The overall goal was to demonstrate substantial equivalence, meaning the device's performance aligned with that of legally marketed, safe, and effective predicate devices.

8. The Sample Size for the Training Set

The document does not specify any sample size for a training set. As a record and verify system, especially one cleared in 2010, it's highly unlikely that it relied on machine learning models requiring large "training sets" in the modern AI sense. Its development would have followed traditional software engineering and validation processes against designed specifications.

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

As no training set is described (due to the nature of the device and the development era), the method for establishing its ground truth is not applicable/not provided.

Ask a specific question about this device

Panther™ RealART is used to correct geometric mismatches between radiation beams and the treatment target under on-line image-guidance. The optional software module is part of the family of treatment planning products under the trade name Panther™.

PANTHER™ RealART is an optional software module to the Prowess radiation therapy planning software for supporting online image-guided radiation therapy. The Panther™ RealART on-line plan adaptation system is composed of a workstation with two Intel Quad-Core Xeon processors (or later versions) running Windows XP operation system (or later versions) and proprietary software that allows the trained users to adjust radiation therapy treatment plans based on the images acquired on the day of treatment with the patient at the treatment position.

The provided text describes the Panther™ RealART device and its 510(k) submission but does not include a detailed table of acceptance criteria or specific reported device performance metrics against such criteria. The study described is primarily a non-clinical verification and validation study, supplemented by a limited "clinical testing" activity.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding device performance metrics. Instead, it broadly states that the device "met its specifications" and "demonstrated substantially equivalent performance to the predicate device, and is safe and effective for its intended use."

The closest statements to performance criteria are:

• "results in equivalent or better quality of treatment plans as compared with the use of predicate device as demonstrated in our field tests."
• "the use of Panther™ RealART will improve the accuracy of IMRT treatment delivery."

Without specific numerical targets for "quality of treatment plans" or "accuracy of IMRT treatment delivery," a precise table cannot be constructed.

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

• Sample Size for "Clinical Tests": Four CT datasets, acquired from a total of four fractions from two prostate and one pancreas cases.
• Data Provenance: The "clinical testing" was conducted at the Medical College of Wisconsin using "real patient cases." This indicates prospective data collection for the purpose of testing the device, though the term "clinical testing" in this context refers to a limited field test rather than a full-scale clinical trial.

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 or their qualifications involved in establishing ground truth for the test set. It mentions "medical physicists/dosimetrists at the Medical College of Wisconsin" conducted functional testing and "clinical physicists contracted by Prowess" verified risk mitigation methods. However, it doesn't state if these individuals established the specific ground truth for the "clinical tests" cases, nor does it detail their qualifications (e.g., years of experience).

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for establishing ground truth or assessing the device's performance on the test set.

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

No multi-reader multi-case (MRMC) comparative effectiveness study is mentioned. The "clinical testing" involved a very small sample of cases and did not appear to focus on comparing human reader performance with and without AI assistance.

6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop Performance)

The primary testing described is focused on the software's functionality and its ability to assist trained users in adjusting treatment plans.
The device's description highlights its components ("Rapid delineation of targets and organs at risk (OAR)," "Segment aperture morphing," "Segment weight optimization"). These are algorithms, and their performance was likely evaluated in a standalone manner during the "Verification and validation of the software... in house according to the Verification and Validation (V&V) Protocol" and functional testing. However, no specific standalone performance metrics (e.g., sensitivity, specificity for contour delineation, or accuracy of segment morphing) are reported in this summary. The "clinical tests" serve to "verify the dose coverage of the target and the correctness of the on-line correction" (which is an output of the algorithm with user input).

7. Type of Ground Truth Used

The type of ground truth used for the "clinical tests" is not explicitly defined, but it can be inferred that it involves expert assessment of the correctness of the on-line correction and dose coverage based on actual patient CT images and treatment plans. It is likely a form of expert consensus or expert-defined optimal plan rather than pathology or long-term outcomes data, given the context of radiation therapy planning.

8. Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set of the Panther™ RealART algorithms.

9. How Ground Truth for the Training Set Was Established

The document does not provide any information on how the ground truth for the training set was established, as it does not discuss the training phase of the algorithm.

Ask a specific question about this device

Prowess 3D™ Radiation Therapy Treatment Planning System, including the IMRT option Panther™, is used to plan photon and electron radiation therapy treatments using linear accelerators and Cobalt-60 beams. The optional software module with the trade name Pather™ provides treatment planning for intensity-modulated radiation therapy (IMRT) treatments using external photon beams.

PROWESS PANTHER is an inverse planning option to the Prowess radiation therapy planning software for supporting intensity-modulated radiation therapy (IMRT) (K980379). The Prowess 3D system is composed of a Workstation with an Intel Pentium* processors (or later versions) running Windows 2000 operation system (or later versions) and proprietary software that allows the trained users to generate radiation therapy treatment plans.

The Prowess IMRT software contains 3 components:

• 1. Objective and constraint specification --- The first step of the inverse planning process is to allow the user to specify the treatment objectives, which include the dose and dose uniformity to the target or targets, the dose and volume limits to different critical organs, and the relative importance of achieving these objectives.
• 2. Optimization --- This is a process by which the system iteratively adjust the deliverable parameters including the field shapes and their weights to derive a treatment plan that best achieves the treatment objectives. A proven and most widely used optimization algorithm, simulated annealing, was used. As with P3IMRT™ system by ADAC (K002237), IMRT uses the convolution superposition algorithm as the final dose calculation engine.
• 3. DICOM Transfer --- This involves transfer the plan parameters via DICOM-RT to a delivery control system (a Record and Verify system or the linear accelerator controller itself) for delivery.

The Prowess Panther device is a software module for radiation therapy treatment planning. The study described in the document evaluates its performance for Intensity-Modulated Radiation Therapy (IMRT).

Here's the breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not explicitly stated as a number of cases, but referred to as "real patient cases" and "all the cases tested."
• Data Provenance: Prospective (clinical testing using real patient cases) at the University of Maryland Medical System in the USA.

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

• Number of Experts: Functional testing was conducted by "medical physicists/dosimetrists" at the University of Maryland, School of Medicine. The exact number of individuals is not specified.
• Qualifications of Experts: Medical physicists/dosimetrists. No specific years of experience are mentioned, but their professional titles suggest expertise in radiation therapy planning and dosimetry.

4. Adjudication Method for the Test Set

• Adjudication Method: Not explicitly described. The evaluation involved comparing "measured point doses" with "calculated values" and dose distributions captured by films. This suggests a direct comparison method rather than an expert consensus/adjudication process for establishing ground truth from multiple expert interpretations.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• MRMC Study: No, an MRMC comparative effectiveness study was not done. The study focused on the performance of the device itself against established physical measurement and calculation benchmarks, and comparison to predicate devices, not on how human readers' performance changes with or without AI assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Standalone Performance: Yes, the described "clinical testing" and dose calculation comparisons represent a standalone evaluation of the algorithm's output. While human users (medical physicists/dosimetrists) were involved in setting up the plans and measurements, the core evaluation was on the accuracy of the device's calculations and planned dose delivery against physical measurements (phantom) and established guidelines, which is a form of standalone performance assessment for a treatment planning system.

7. The Type of Ground Truth Used

• Type of Ground Truth: The ground truth was established through physical measurements against a phantom ("delivering the plan to a phantom. The measured point doses showed agreement with calculated values... The dose distributions captured by films showed..."). This is a highly objective measurement-based ground truth, often considered the gold standard for dose delivery verification in radiation therapy.

8. The Sample Size for the Training Set

• Sample Size: Not specified. The document states that the Prowess Panther uses a "proven and most widely used optimization algorithm, simulated annealing" and the "convolution superposition algorithm as the final dose calculation engine." These are established algorithms and the document does not mention custom training data for these specific components. Any "training" would likely refer to the development and validation of these underlying algorithms, which are not detailed in the context of this specific 510(k) submission.

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

• Ground Truth for Training Set: Not applicable in the context of this submission. As noted above, the core algorithms are established. If any internal validation or parameter tuning was done, the ground truth for that would typically involve simulation data or clinical data with known dose distributions, but this level of detail is not provided or required for this type of device submission.

Ask a specific question about this device