(25 days)
The Eclipse Treatment Planning System (Eclipse TPS) is used to plan radiotherapy treatments with malignant or benign diseases. Eclipse TPS is used to plan external beam irradiation with photon, electron and proton beams, as well as for internal irradiation (brachytherapy) treatments.
The Varian Eclipse™ Treatment Planning System (Eclipse TPS) provides software tools for planning the treatment of malignant or benign diseases with radiation. Eclipse TPS is a computer-based software device used by trained medical professionals to design and simulate radiation therapy treatments. Eclipse TPS consists of different applications, each used for specific purposes at a different phase of treatment planning.
Eclipse TPS is capable of planning treatments for external beam irradiation with photon, electron, and proton beams, as well as for internal irradiation (brachytherapy) treatments.
The provided text describes the 510(k) summary for the Eclipse Treatment Planning System v16.0. It primarily focuses on demonstrating substantial equivalence to a predicate device (Eclipse Treatment Planning System v15.6) through software verification and validation, rather than presenting a performance study with acceptance criteria for a novel AI/ML-driven medical device.
Therefore, many of the requested details such as a table of acceptance criteria, sample sizes for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone AI performance, and training set details are not applicable or not provided in this specific document.
This document outlines a regulatory submission for a software update to an existing medical device, not a new AI-powered diagnostic or treatment planning system that would typically undergo the extensive validation described in your prompt. The "performance data" section primarily refers to software verification and validation testing, not clinical performance or accuracy in a diagnostic or predictive sense.
Here's what can be extracted based on the provided text, and where information is not available:
1. A table of acceptance criteria and the reported device performance
- Not explicitly provided as acceptance criteria for AI model performance. The document states: "Test results demonstrate conformance to applicable requirements and specifications." This implies compliance with software requirements and design specifications, not performance on clinical metrics of accuracy or effectiveness in the way an AI diagnostic tool would be evaluated.
- The "performance data" discussed is related to software verification and validation against requirements, not diagnostic accuracy or clinical impact.
2. Sample sizes used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not applicable/Not provided. The document states: "No animal studies or clinical tests have been included in this pre-market submission." This indicates that the "test set" was for software testing and validation, not for evaluating performance on patient data. Therefore, details like data provenance or retrospective/prospective nature are not relevant to this submission.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not applicable. Since no clinical or patient-data-based studies were performed for performance evaluation in the context of diagnostic accuracy, there was no need for expert-established ground truth on a test set.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable. As no clinical performance study involving human interpretation was conducted to establish ground truth.
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
- No, an MRMC comparative effectiveness study was not done. The submission explicitly states "No animal studies or clinical tests have been included in this pre-market submission."
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not explicitly stated as a separate standalone performance study in the context of an AI algorithm. The device is a "Treatment Planning System" which is a software tool used by trained medical professionals. Its "performance" is evaluated by its conformance to software specifications and safety, not as a standalone AI diagnostic tool.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
- Not applicable for clinical ground truth. The "ground truth" for the software validation would be the functional requirements and design specifications that the software was tested against.
8. The sample size for the training set
- Not applicable. This submission is for a software update to an existing treatment planning system, not for a new AI/ML model that requires a dedicated training set. The changes described are feature introductions and enhancements, not an AI model that learns from large datasets.
9. How the ground truth for the training set was established
- Not applicable. For the same reason as #8.
§ 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.