(85 days)
PerFRACTION is intended to allow for the detection of errors that can occur in the delivery of a patient's radiation therapy treatment.
PerFRACTION allows for the comparison of the cumulative exit image(s) for one treatment fraction to the cumulative exit image(s) for another treatment fraction, thus providing a consistency check on the delivery of the treatment fraction.
PerFRACTION™ is a device that includes software installed on standard, modern computing hardware (provided with the software) that allows clinicians to perform quality assurance for each fraction of a radiotherapy treatment plan. PerFRACTION compares the beam-exit measurement data from a treatment fraction to data from a prior baseline fraction. This comparison allows for the detection of errors that may occur with the delivery system such as the multi-leaf collimator, accelerator, and collimating jaws.
The FDA 510(k) summary for the PerFRACTION (Model 1215) device provides limited information regarding specific acceptance criteria and detailed study designs. However, based on the provided text, here's what can be extracted and inferred:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state a table of acceptance criteria with numerical targets. Instead, it broadly states: "PerFRACTION™ has been tested in non-clinical and clinical settings, and it has been shown that this device performs within its design specifications."
It further elaborates on the types of errors the device was tested to detect:
- Errors in the collimation jaws
- Errors in multileaf collimator leaves
- Errors in accelerator output
- Errors in gantry rotation of the treatment delivery device
The performance claim is: "Based on the results of this performance testing when evaluated against published data for the predicate, Model 1215 PerFRACTION is as safe, as effective, and performs as well or better than the predicate device."
Inferred Acceptance Criteria (based on the description):
The device is expected to reliably detect errors in the delivery of radiation therapy treatment, specifically those related to collimation jaws, MLCs, accelerator output, and gantry rotation, to a degree comparable to or better than the predicate device.
Reported Device Performance:
The device "performs within its design specifications" and is "as safe, as effective, and performs as well or better than the predicate device" in detecting the specified errors.
2. Sample size used for the test set and the data provenance
The document does not specify the sample size for the test set or the data provenance (e.g., country of origin, retrospective or prospective). It simply states that the device was "tested in non-clinical and clinical settings."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not provided in the document.
4. Adjudication method for the test set
This information is not provided in the document.
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
The document does not mention an MRMC study or any assessment of human reader improvement with or without AI assistance. The device is described as software that performs a consistency check, implying a standalone analysis rather than an assistive tool for human interpretation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, based on the description, a standalone performance assessment was done. The device "compares the beam-exit measurement data from a treatment fraction to data from a prior baseline fraction," and this comparison "allows for the detection of errors." This implies the algorithm (PerFRACTION) performs the detection independently.
7. The type of ground truth used
The document does not explicitly state the type of ground truth used. However, given that the device detects "errors that can occur in the delivery of a patient's radiation therapy treatment" and was tested when "exposed to errors," it strongly suggests that the ground truth was based on known, induced errors or simulated errors in a controlled environment, likely confirmed by physical measurements or pre-defined error scenarios. It could also potentially involve comparison against highly precise reference measurements or other established QA methods.
8. The sample size for the training set
The document does not mention a "training set" or its sample size. This suggests that the device might not be based on a machine learning model that requires explicit training data in the typical sense. It seems to be a rule-based or algorithmic comparison system.
9. How the ground truth for the training set was established
As no training set is explicitly mentioned, this information is not provided.
§ 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.