(65 days)
Pinnacle3 Radiation Therapy Planning System is a software package intended to provide planning support for the treatment of disease processes. Pinnacle3 Radiation Therapy Planning System incorporates a number of fully integrated subsystems, including Pinnacle3 Proton, which supports proton therapy planning. The full Pinnacle Radiation Therapy Planning System software package provides planning support for the treatment of disease processes, utilizing photon, proton, electron and brachytherapy techniques.
Pinnacle3 Radiation Therapy Planning System assists the clinician in formulating a treatment plan that maximizes the dose to the treatment volume while minimizing the dose to the surrounding normal tissues. The system is capable of operating in both the forward planning and inverse planning modes. Plans generated using this system is used in the determination of the course of a patient's radiation treatment. They are to be evaluated, modified and implemented by qualified medical personnel.
Pinnacle3® Radiation Therapy Planning System (hereafter Pinnacle3 RTP) provides radiation treatment planning for the treatment of benign or malignant diseases. When using Pinnacle " RTP, qualified medical personnel may generate, review, verify, approve, print and export the radiation therapy plan prior to patient treatment. Pinnacle RTP can provide plans for various radiation therapy modalities including, utilizing photon, proton, electron and brachytherapy techniques Stereotactic Radiosurgery, and Brachytherapy.
The Proton module builds on the Pinnacle Photon Treatment Planning Solution. A substantial part of the software architecture, display, connectivity and planning tools are transferable or extensible to the Proton Treatment Planning module. Using Pinnacle® RTP as the base-line architecture will address the needs of operating and future treatment centers to seamlessly integrate photon with proton treatment planning.
Pinnacle® RTP is a software package that runs on a Oracle Server and accessed through one or more clients, or an Oracle UNIX workstation and consists of a core software module (Pinnacle') and optional software features (the Proton module requires the Oracle server and cannot be run on a workstation). These optional software features, commonly referred to as "plug-ins", are typically distributed separate from the core software product (separate CD or DVD). The device has network capability to other Pinnacle® RTP workstations, thin client, and to both input and output devices via local area network (LAN) or wide area network (WAN).
Image data is imported from CT, MR, PET, PET-CT and SPECT devices using a DICOM-compliant interface. A qualified medical professional uses the Pinnacle® RTP for functions such as viewing and analyzing the patient's anatomy, and generating a radiation therapy plan.
This 510(k) submission for the Philips Medical Systems (Cleveland), Inc. Pinnacle3 Radiation Therapy Planning System (Pinnacle3 RTP) primarily focuses on demonstrating substantial equivalence to a predicate device, the Computerized Medical Systems, Inc. Xio RTP System - Proton Spot Scanning (K102216), rather than detailing specific acceptance criteria and a study to prove they are met in a quantitative manner. Regulatory submissions for radiation therapy planning systems often rely on verification and validation activities to ensure the software performs as intended and is safe and effective when compared to a legally marketed predicate device.
However, based on the provided text, here's a breakdown of the information requested, with indications where details are not explicitly provided:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly present a table of quantitative acceptance criteria for features like dose calculation accuracy or planning capabilities, nor does it provide specific device performance metrics in a pass/fail format typical of quantitative studies. Instead, it relies on demonstrating similar functionalities and computational approaches to a predicate device.
The "Non-Clinical Tests" section mentions that "Verification tests were written and executed to ensure that the system is working as designed. Pass/fail requirements and results of this testing can be found in the Thunder Core Verification Test Report, which is included in section 16 of this submission. Pinnacle3 RTP successfully passed verification testing." This suggests that internal acceptance criteria and performance thresholds existed and were met, but these specific details are not included in the provided excerpt.
The comparison table (Table 5A) highlights technological characteristics and principles of operation, implying that similarity to the predicate device in these aspects serves as a primary "acceptance criterion" for substantial equivalence.
| Characteristic / "Acceptance Criterion" | Reported Device Performance (Pinnacle3 RTP) |
|---|---|
| Intended Use | Software package intended to provide planning support for the treatment of disease processes, utilizing photon, proton, electron, and brachytherapy techniques. Assists clinicians in formulating treatment plans to maximize dose to treatment volume and minimize dose to normal tissues. |
| Dose Engine: passive double scattering | Pencil beam algorithm based on published work by L. Hong et al. (1996). |
| Dose Engine: uniform scanning | Pencil beam algorithm based on published work by L. Hong et al. (1996). |
| Dose model parameter values and related functions | Measured data is imported and fitted to models based on published works by A. Somov et al. (poster), H. Szymanowski et al. (2001), T. Bortfeld (1997), and Schaffner, B. (2008) for input into the dose engine. |
| Vendor Independent Beam modifier | Yes, uses standard ray tracing and projection techniques. Materials, limitations of size and thickness, physical milling techniques and limitations are all modeled. |
| Export plan parameters required by DICOM-RT Ion standard | Yes |
| DICOM RT-Dose import and export | Yes |
| Mixed Modality Planning | Yes. Dose is combined by summing up dose values from each modality in units of Co-60 equivalent Radiobiological Effective dose. |
| Quality Assurance | Yes. Plan and physics reports, compensator and aperture printing, dose calculations in QA phantom, etc., are supported. |
| Beam Weight Optimization of Proton Beams | Simple point based method. No full 3D dose optimization performed - Monitor Units of pre-calculated, static beams adjusted only to meet point dose criteria. |
| Compensator Modification (Manual and Automatic) | Compensator thickness values are calculated from ray tracing techniques by determining the difference in Water Equivalent Distance for each ray that intersects the target for irradiation. Physical milling techniques are incorporated. User has manual and automated tools, with automated tools based on published work by M. Urie et al. (1983). |
| Verification Testing (General Functionality & Design Specifications) | Successfully passed verification testing as documented in the internal "Thunder Core Verification Test Report" (not provided in this excerpt). Hazard analysis completed and mitigated. Verification and Validation test plans followed Philips procedures. |
| Dose Calculation Accuracy | Algorithm testing was performed in a QA "Phantom" to compare calculated against measured doses. (No specific numerical acceptance criteria or performance results are provided in this excerpt). |
| Clinical Validation (User Experience/Workflow) | Clinical-oriented validation test cases were written and executed by PMS customers at External evaluation sites with oversight by PMS customer support personnel. (No specific acceptance criteria or quantitative results provided in this excerpt). |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: Not explicitly stated. The document mentions "algorithm testing was performed in a QA 'Phantom'" and "clinical orientated validation test cases were written and executed by PMS customers at External evaluation sites." However, the number of phantom configurations, patient cases (if simulated), or specific test sets used in these validations is not provided.
- Data Provenance:
- Phantom Data: For "Algorithm testing... in a QA 'Phantom'", the data is synthetically generated or acquired in a controlled lab environment. This is typically internal, not from a specific country of origin in the clinical sense.
- Clinical-Oriented Validation: For "clinical orientated validation test cases... executed by PMS customers at External evaluation sites," the data would likely be based on simulated or mock patient cases, or potentially anonymized clinical data provided by these "PMS customers." The countries of origin for these "External evaluation sites" are not specified, nor is whether the data was retrospective or prospective. It is implied to be retrospective or simulated to prevent patient exposure to risk.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Not explicitly stated.
- Qualifications of Experts: For the "clinical orientated validation test cases," it mentions "oversight by PMS customer support personnel." It also states that treatment plans "are to be evaluated, modified, and implemented by qualified medical personnel." While this implies that qualified personnel are involved in the validation, their specific roles (e.g., medical physicists, radiation oncologists, dosimetrists) and years of experience are not detailed as "experts establishing ground truth." For the QA phantom testing, the "ground truth" (measured doses) would be established by the physical measurements themselves, typically verified by medical physicists via dosimetry.
4. Adjudication Method for the Test Set
Not explicitly stated. The document refers to "oversight by PMS customer support personnel" for clinical validation, but it doesn't describe any formal adjudication process for disagreements or discrepancies. For phantom testing, the "ground truth" is measured data, and the comparison is usually direct.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No. The document explicitly states: "Clinical trials were not performed as part of the development of this product." Therefore, a multi-reader multi-case (MRMC) comparative effectiveness study focusing on human readers' improvement with AI vs. without AI assistance was not conducted or reported. The device is a planning system, not an AI-assisted diagnostic or interpretation tool in the typical sense of MRMC studies.
6. Standalone (Algorithm Only) Performance Study
Yes, in part. "Algorithm testing was performed in a QA 'Phantom' to compare calculated against measured doses to ensure dose calculation accuracy." This constitutes a standalone performance evaluation of the dose calculation algorithm.
7. Type of Ground Truth Used
- Algorithm Testing: "Measured doses" in a QA "Phantom." This refers to physical measurements in a controlled environment as the ground truth.
- Clinical-Oriented Validation: This implicitly relies on the consensus of "qualified medical personnel" and "PMS customer support personnel" validating that the plans generated by the system are clinically appropriate and meet intended goals. However, a formal "ground truth" establishment process for these cases is not described beyond this general validation.
8. Sample Size for the Training Set
Not applicable. This device is a radiation therapy planning system that uses established physics models and algorithms (e.g., pencil beam algorithm, dose model parameter fitting to published works and measured data) rather than a machine learning model that requires a distinct "training set" in the context of deep learning or AI. The algorithms are based on fundamental physics principles and validated against measured data and published literature.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as there isn't a "training set" in the machine learning sense. The models used (e.g., pencil beam algorithm) are derived from fundamental physics and validated against "measured data... fitted to models based on published works." This fitting process uses measured physical data (e.g., Bragg Peak, Spread Out Bragg Peak, Effective SAD, Virtual SAD, Effective Source Size, CT-Number to Stopping Power Tables) as its "ground truth" for parameter derivation.
§ 892.5050 Medical charged-particle radiation therapy system.
(a)
Identification. A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.(b)
Classification. Class II. When intended for use as a quality control system, the film dosimetry system (film scanning system) included as an accessory to the device described in paragraph (a) of this section, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.