(92 days)
Integrity™ is the interface and control software for the Elekta range of medical digital linear accelerators and is intended to assist a licensed practitioner in the delivery of radiation to defined target volumes (e.g. lesions, arterio-venous malformations, malignant and benign tumours), whilst sparing surrounding normal tissue and critical organs from excess radiation. It is intended to be used for single or multiple fractions, delivered as static and/or dynamic beams of radiation, in all areas of the body where such treatment is indicated
This Traditional 510(k) describes enhancements to the integral software performing the graphical interface and machine control functions for the Elekta range of medical digital linear accelerators. Integrity R1.0 employs a new LynxOS operating system that has a proven track record in safety and security to replace RMX. The software introduces Continuously Variable Dose Rate (CVDR), which is an enhancement to standard dose rate for dynamic delivery techniques. This function increases the number of available dose rates which can make treatment delivery more efficient and provide smoother delivery of VMAT prescriptions. The software supports the ability for the MLCi2 leaves to interdigitate, supporting the creation of island fields for X-Ray treatment delivery techniques.
This 510(k) summary (K102200) describes performance for the Elekta Integrity™ R1.0, which is an integrated digital control system and software for Elekta linear accelerators. It is an enhancement to existing software, primarily introducing a new operating system (LynxOS), Continuously Variable Dose Rate (CVDR), and support for MLCi2 leaves to interdigitate.
The document states that "There has been no change made to the underlying technological characteristics of the product from the predicate device." Therefore, the performance acceptance criteria and study details are not presented in the provided document, as a direct comparison and statement of substantial equivalence to the predicate device (Elekta Desktop Pro™ K080585) is the primary method for demonstrating safety and effectiveness.
Because the submission is for an enhancement to control software for a medical linear accelerator and relies on substantial equivalence to a predicate device for safety and effectiveness, the typical types of studies involving patient data, expert readers, and ground truth for disease detection or diagnosis are not applicable in the same way they would be for a diagnostic AI device.
Therefore, the requested information cannot be fully provided based on the given text. However, I can explain why some sections are not applicable to this type of device and what information is provided.
Non-Applicability of Standard AI/Diagnostic Device Study Criteria:
The Elekta Integrity™ R1.0 is a control system software for a medical linear accelerator, not a diagnostic imaging device or an AI algorithm designed to identify or diagnose medical conditions from patient data. Its primary function is to safely and effectively control the delivery of radiation therapy based on a clinician's prescription.
Therefore, many of the typical acceptance criteria and study details requested (e.g., sample sizes for test/training sets, involvement of radiologists, pathology ground truth, MRMC studies) are not relevant to this type of device and would not typically be found in its 510(k) submission. Instead, the focus for such a device is on software validation, safety testing, and demonstrating that the new features do not compromise the safety or effectiveness of the predicate device.
Information Provided in the Document:
-
Table of Acceptance Criteria and Reported Device Performance:
- Not explicitly provided in the format of a table with specific performance metrics (e.g., sensitivity, specificity, accuracy).
- The document implies that the acceptance criterion is "substantial equivalence" to the predicate device, Elekta Desktop Pro™ (K080585), "in safety and effectiveness."
- The reported "performance" is that the "functionality for Integrity™ is equivalent to its predicate device..." and "The fundamental technical characteristics are the same..." This suggests that the device performs its intended control functions as safely and effectively as the predicate.
-
Sample size used for the test set and the data provenance:
- Not applicable/Not provided. This device is control software, not a diagnostic tool evaluated on patient data.
- Testing would involve software validation, functional testing, and potentially clinical use testing (e.g., phantom studies, dose delivery verification) rather than a "test set" of patient data.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not applicable/Not provided. No "ground truth" in the diagnostic sense is established for this device. Ground truth for a linear accelerator control system would involve verifying accurate beam delivery, dose calculations, and machine responses, typically performed by medical physicists and engineers.
-
Adjudication method for the test set:
- Not applicable/Not provided. As there's no diagnostic "test set" requiring expert adjudication.
-
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:
- Not applicable/Not done. This is not an AI-powered diagnostic or interpretive device that assists human readers with case assessment.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not applicable/Not explicitly stated in a way relevant to diagnostic AI. The software "stands alone" in controlling the machine, but it is supervised and programmed by a human practitioner. The validation would focus on the software's ability to execute commands and control the accelerator accurately.
-
The type of ground truth used:
- Implied ground truth related to safety and performance specifications. For control software, ground truth would be defined by engineering specifications, physical laws of radiation, and pre-defined safety limits. Verification would involve testing against these specifications, rather than against pathology or patient outcomes.
-
The sample size for the training set:
- Not applicable/Not provided. This is not a machine learning or AI device that uses a "training set" of data in the typical sense. It is deterministic control software.
-
How the ground truth for the training set was established:
- Not applicable/Not provided.
In summary: The provided document is for a software upgrade to a medical linear accelerator control system. The demonstration of safety and effectiveness relies on "substantial equivalence" to a predicate device, focusing on functional equivalence and the impact of software changes on established performance and safety characteristics, rather than diagnostic performance metrics or studies involving patient data evaluated by human readers and AI.
§ 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.