Search Results

The XiO RTP System is used to create treatment plans for any cancer patient for whom external beam radiation therapy or brachytherapy has been prescribed. The system will calculate and display, both on-screen and in hard-copy, either two- or three-dimensional radiation dose distributions within a patient for a given treatment plan set-up.

Optionally, the user may elect to generate plans using Dynamic Conformal Arc Therapy capability. Dynamic Conformal Arc Therapy is a treatment modality in which the gantry rotates in an arc (or multiple arcs) over user-specified angles while the leaves of a multileaf collimator (MLC) continually reshape the beam to conform to the targer.

The XiO Radiation Treatment Planning system accepts a) patient diagnostic imaging data from CT and MR scans, or from films, and b) "source" dosimetry data, typically from a linear accelerator. The system then permits the user to display and define (contour) a) the target volume to be treated and b) critical structures which must not receive above a certain level of radiation, on these diagnostic images.

Based on the prescribed dose, the user, typically a Dosimetrist or Medical Physicist can then create multiple treatment scenarios involving the type, number, position(s) and energy of radiation beams and the use of treatment aids between the source of radiation and the patient (wedges, blocks, ports, etc.). The XiO system then produces a display of radiation dose distribution within the patient, indicating not only doses to the target volume but to surrounding tissue and structures. The "best" plan satisfying the prescription is then selected, one that maximizes dose to the target volume while minimizing dose to surrounding healthy volume. The parameters of the plan are output in hard-copy format for later reference and for placement in the patient file.

This Premarket Notification addresses the addition of support for Dynamic Conformal Therapy. Dynamic Conformal is a treatment modality in which radiation beams are continuously shaped to conform to a target while the gantry rotates and the beam is on. In XiO, the user chooses the target, defines structures to avoid, optional margin(s), and treatment angles. XiO then plans a treatment over a specified arc and with specified beam increments, with the leaves of the multi-leaf collimator (MLC) continually reshaping the beam to conform to the target. The target receives a homogenous dose while the structures designated as "avoidance structures" are avoided absolutely.

Dose calculation is performed using existing, validated algorithms within XiO. Determination of dose at the specified angles is calculated in the same way as conventional and asymmetric arc beams; the calculated dynamic beam dose distribution is determined as the sum of multiple fixed beam dose distributions across the specified arc.

This submission describes the XiO Radiation Treatment Planning System with the added functionality of Dynamic Conformal Therapy. The information provided heavily emphasizes the regulatory process and comparisons to predicate devices rather than detailed performance studies with acceptance criteria.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state specific acceptance criteria in terms of numerical thresholds for dose calculation accuracy or clinical outcomes. Instead, it focuses on the device's ability to calculate dose and conform to targets.

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

• Test Set Sample Size: Not explicitly stated. The document mentions "Algorithm test cases were written and executed." The number of these test cases is not specified.
• Data Provenance: The testing was "executed in-house by CMS customer support personnel." This suggests simulated or internally generated data rather than real patient data. The country of origin is implicitly the US, where Computerized Medical Systems, Inc. is located. It was a retrospective evaluation against defined test cases.

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

• Number of Experts: Not specified. The "Algorithm test cases were written and executed" and "Clinically oriented validation test cases were written and executed" by "CMS customer support personnel." It's unclear if these personnel are qualified medical experts (e.g., medical physicists, dosimetrists) or if external experts were involved in establishing the ground truth for these test cases.
• Qualifications of Experts: Not explicitly stated. While the system's users are described as "typically a Dosimetrist or Medical Physicist," it doesn't confirm if these roles or similarly qualified individuals generated the test cases or the ground truth for them.

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified. Since the testing involved "algorithm test cases" and "clinically oriented validation test cases," it's likely a comparison against predetermined correct outputs for those cases rather than an adjudication process involving multiple human observers reviewing complex real-world interpretations.

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

• No, an MRMC comparative effectiveness study was not done. The text explicitly states: "Actual testing in a clinic was not performed as part of the development of this feature." It also adds that such testing "is not required to demonstrate substantial equivalence or safety and effectiveness of the device." Therefore, there is no effect size reported for human readers improving with AI vs. without AI assistance.

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

• Yes, a standalone study was done, as far as the algorithm's performance is concerned. The text highlights "Algorithm test cases were written and executed to ensure that the system is calculating dose correctly for Dynamic Conformal beams." This "algorithm test" would represent a standalone evaluation of the core calculation engine's accuracy against predefined inputs and expected outputs, without direct human intervention in each calculation step.

7. The Type of Ground Truth Used

• Type of Ground Truth: The ground truth for the "Algorithm test cases" would likely be pre-calculated, theoretical, or established results from known physics principles or established algorithms for radiation dose calculation under specific, controlled parameters. For "Clinically oriented validation test cases," the ground truth would similarly be pre-defined correct treatment plans or dose distributions established by medical physicists/dosimetrists for those specific clinical scenarios. It is not pathology, expert consensus on patient images, or outcomes data.

8. The Sample Size for the Training Set

• Training Set Sample Size: Not applicable/Not provided. Radiation Treatment Planning (RTP) systems like XiO, particularly from this era (2003), typically rely on deterministic physical algorithms for dose calculation rather than machine learning models that require training data sets in the conventional sense. The "algorithms" mentioned are likely physics-based models rather than AI models.

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

• Ground Truth for Training Set: Not applicable. As mentioned above, this system likely operates on deterministic algorithms rather than machine learning, so there isn't a "training set" or corresponding ground truth in the AI context. The algorithms themselves would have been developed and validated against established physics principles and possibly empirical measurements (though those details are not in this summary).

Ask a specific question about this device