(83 days)
XPlan-1 is a stereotactic LINAC-based radiation treatment planning system. XPlan-1 localizes lesions to be treated using CT scans, MR scans and digitized angiographic film. XPlan-1 provides a stereotactic planning system, for treatment of tumors
The XPlan-1 system has the same intended use and similar technological characteristics as the commercially available XKnife-3 Stereotactic Radiation Treatment Planning System. Like XKnife-3, the XPlan-1 system includes the same image acquisition, localizing, contouring and beam planning techniques. In addition, XPlan-1 and XKnife-3 both contain methods of QA verification for targeting setup and delivery. XPlan-1 includes modifications of the XKnife-3 system, such as the ability to use conformal collimation devices and a modification to the dose algorithm to account for the use of conformal collimation devices. XPlan-1 also supports the use of the Laser Angio Target Localizer (LATL) as an additional QA check to verify the orientation and position of the LINAC jaws and gantry, the collimator and couch rotation. Like the XKnife-3 use of the Rectilinear Phantom Pointer (RLPP) and Laser Target Localizer Frame (LTLF), XPlan-1 supports the use of the LATL to confirm system alignment at isocenter and to position the patient at isocenter.
XPlan-1 is also substantially equivalent to the commercially available Conformal Radiation Treatment Planning System, FOCUS. Like FOCUS, XPlan-1 supports the use of LINAC jaws, MLCs and wedges to modify the shape and attenuation of the beam. Both XPlan-1 and FOCUS also have the ability to model the total on the target volume and surrounding tissue via a 3D Beam's Eye View and 2D beam visualization. Both systems, also addition to the dose-volume histogram.
The provided document is a 510(k) premarket notification for the XPlan-1 Stereotactic Radiation Treatment Planning System. It primarily focuses on demonstrating substantial equivalence to predicate devices (RSA XKnife-3 System and CMS Focus System), rather than detailing specific acceptance criteria and the results of a primary study.
Therefore, many of the requested details about acceptance criteria, study design, sample sizes, expert involvement, and ground truth establishment are not explicitly present in the provided text. The document refers to "testing" that verifies functionalities, but does not provide the specifics of these tests as a formal study with statistical outcomes.
Here's an attempt to extract the available information and highlight what is missing based on your request:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Inferred from "Safety Summary") | Reported Device Performance (Inferred from "Safety Summary") |
|---|---|
| Correct aperture generation by beam shaping function | XPlan-1 system testing verifies that the beam shaping function generated the correct aperture. |
| Correct dose displays in Geometry Viewer and Dose Summary | [XPlan-1 system testing verifies] that the dose displays in the Geometry Viewer and Dose Summary are correct. |
| Accuracy of PTV generation | [XPlan-1 system testing verifies] that the PTV generation... [is] accurate. |
| Accuracy of Block and MLC generation | [XPlan-1 system testing verifies] that the... Block and MLC generation... [is] accurate. |
| Accuracy of DRR display | [XPlan-1 system testing verifies] that the DRR display... [is] accurate. |
| Accuracy of other new features | [XPlan-1 system testing verifies] that... other new features are accurate. |
| Functionality of QA verification for targeting setup and delivery | XPlan-1 and XKnife-3 both contain methods of QA verification for targeting setup and delivery. |
| Support for conformal collimation devices | XPlan-1 includes modifications of the XKnife-3 system, such as the ability to use conformal collimation devices. |
| Modification to dose algorithm for conformal collimation | XPlan-1 includes a modification to the dose algorithm to account for the use of conformal collimation devices. |
| Support for Laser Angio Target Localizer (LATL) as QA | XPlan-1 also supports the use of the Laser Angio Target Localizer (LATL) as an additional QA check to verify the orientation and position of the LINAC jaws and gantry, the collimator and couch rotation. |
| System alignment and patient positioning confirmation (via LATL) | Like the XKnife-3 use of the Rectilinear Phantom Pointer (RLPP) and Laser Target Localizer Frame (LTLF), XPlan-1 supports the use of the LATL to confirm system alignment at isocenter and to position the patient at isocenter. |
| Support for LINAC jaws, MLCs, and wedges to modify beam | Like FOCUS, XPlan-1 supports the use of LINAC jaws, MLCs and wedges to modify the shape and attenuation of the beam. |
| Ability to model total volume and surrounding tissue via 3D Beam's Eye View and 2D beam visualization | Both XPlan-1 and FOCUS also have the ability to model the total volume and surrounding tissue via a 3D Beam's Eye View and 2D beam visualization. |
| Inclusion of dose-volume histogram | Both systems, also addition to the dose-volume histogram. |
Note: The document uses phrases like "verifies that..." and "are accurate" to describe performance, without providing quantitative metrics or specific pass/fail criteria for what constitutes "correct" or "accurate" in a statistical sense.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: Not specified. The document states "XPlan-1 system testing verifies," but does not provide details on the number of cases, patients, or data points used during this testing.
- Data Provenance: Not specified. It's unclear if the data used for testing was retrospective or prospective, or its country of origin.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Not specified.
- Qualifications: Not specified.
4. Adjudication Method for the Test Set
- Adjudication Method: Not specified. There is no mention of expert review, consensus methods (e.g., 2+1, 3+1), or any other adjudication process.
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. This document describes a radiation treatment planning system, not an AI-assisted diagnostic or interpretation tool for human readers. Therefore, an MRMC study comparing human reader performance with and without AI assistance is not applicable to the outlined purpose of this device.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Standalone Performance Study: The document refers to "XPlan-1 system testing" to verify various functions like beam shaping, dose display, and PTV/MLC generation. This implies a form of standalone testing of the algorithm's outputs. However, specific performance metrics (e.g., accuracy percentages, error margins) from such a standalone study are not provided. The "Safety Summary" paragraph could be interpreted as a High-Level summary of a standalone performance evaluation, but lacks the granular detail of a formal study report.
7. The Type of Ground Truth Used
- Type of Ground Truth: Not explicitly stated. For a treatment planning system, ground truth would typically involve comparisons against established physics models, phantom measurements, or expert-defined optimal plans. The document broadly mentions "accuracy" and "correctness," which suggests a comparison to some reference, but the nature of that reference (e.g., a gold standard derived from established physics, or expert consensus on ideal plan parameters for specific cases) is not detailed.
8. The Sample Size for the Training Set
- Sample Size for Training Set: Not applicable/Not specified. This device is described as a "Stereotactic Radiation Treatment Planning System" which uses algorithms to calculate and plan, rather than an AI/Machine Learning system that typically requires a distinct "training set." The system likely relies on physics-based models and established dosimetry principles, not data-driven learning from a training set in the modern sense.
9. How the Ground Truth for the Training Set was Established
- Ground Truth for Training Set: Not applicable/Not specified, for the same reasons as #8. If the system incorporates any machine learning, this information is not provided. Given the 1997 date of the document, it's highly unlikely that "training set" as understood in current AI contexts applies here.
§ 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.