Search Results

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. In addition, the Eclipse Proton Eye algorithm is specifically indicated for planning proton treatment of neoplasms of the eye.

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 is capable of planning treatments for external beam irradiation with photon, electron, and proton beams, as well as for internal irradiation (brachytherapy) treatments.

This document is a 510(k) summary for the Eclipse Treatment Planning System (Eclipse TPS), specifically version 15.5, from Varian Medical Systems. It describes changes from a previous version (v15.1.1, K170969) and argues for substantial equivalence.

Here's an analysis of the provided information concerning acceptance criteria and supporting studies, particularly regarding the newly included "Smart Segmentation Knowledge Based Contouring (SS KBC)" module, which appears to be the most relevant AI/software feature:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a formal table of explicit acceptance criteria with quantitative performance metrics for the entire Eclipse Treatment Planning System, nor for the specific new features. Instead, it states a general conclusion from non-clinical testing:

• Acceptance Criteria/Goal (Inferred): The product conforms to defined user needs and intended uses, and there are no discrepancy reports (DRs) remaining with a priority of Safety Intolerable or Customer Intolerable. The device is considered safe and performs at least as well as the predicate device.
• Reported Device Performance: "The outcome was that the product conformed to the defined user needs and intended uses and that there were no DRs (discrepancy reports) remaining which had a priority of Safety Intolerable or Customer Intolerable."

For the Smart Segmentation Knowledge Based Contouring (SS KBC) module, the document notes that it was previously cleared under K141248 (v2.2). This implies that the specific performance metrics and acceptance criteria for this module would have been detailed in that earlier submission. In this current submission (K172163), the SS KBC module is being integrated into the broader Eclipse TPS, and the claim is that its previously established safety and effectiveness hold.

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

The document provides very limited detail on specific test sets for the current submission (K172163). It broadly refers to "Verification and Validation" being performed for all new features and "regression testing" for existing features.

• Sample Size: Not explicitly stated for the overall V&V or for specific features.
• Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). The document refers to "test outcomes" but doesn't specify data sources.

For the Smart Segmentation Knowledge Based Contouring (SS KBC) module, since it was previously cleared under K141248, the relevant test set details would be found in that earlier submission. This document only states that the feature "is included as a part of Eclipse Treatment Planning System (v15.5)" and references its prior clearance.

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

This information is not provided in the current document. The document primarily focuses on software engineering V&V processes (tracing requirements to test outcomes, DRs). For the SS KBC module, this information would have been part of the K141248 submission where its performance as a standalone tool was assessed and ground truth established. Given it's a "Knowledge Based Contouring" system, human expert input for ground truth would be expected.

4. Adjudication Method for the Test Set

This information is not provided in the current document.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No MRMC study is mentioned in this 510(k) summary. The summary focuses on comparing technical features with a predicate device and confirming software functionality, not on human-in-the-loop performance improvement with AI assistance.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• The document implies that standalone performance testing was done as part of the overall "Verification and Validation" process for the software features, as it addresses "product conformance to the defined user needs and intended uses." However, specific details or quantitative results of such standalone performance are not provided in this summary directly.
• For the Smart Segmentation Knowledge Based Contouring (SS KBC) module, as it was previously cleared under K141248, it is highly probable that its standalone algorithmic performance (e.g., accuracy of auto-segmentation compared to ground truth) was evaluated in that prior submission. This document lists it as a feature of the Eclipse TPS v15.5, meaning its existing, cleared functionality is being integrated.

7. Type of Ground Truth Used

• This information is not explicitly stated for the general V&V.
• For the Smart Segmentation Knowledge Based Contouring (SS KBC) module, given its function ("Knowledge Based Contouring"), the ground truth for its original clearance (K141248) would typically involve expert delineation consensus (e.g., radiation oncologists, radiologists) as the gold standard for anatomical structures.

8. Sample Size for the Training Set

• This information is not provided in the current document. Training set details would be most relevant for the knowledge-based/AI component (SS KBC).

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

• This information is not provided in the current document. For the SS KBC module, again, this would have been part of the K141248 submission. Typically, for knowledge-based contouring systems, ground truth for training data involves expert delineation and potentially review processes.

Summary of AI-Specific Information from the Provided Document:

The most AI-related component mentioned is the "Smart Segmentation Knowledge Based Contouring (SS KBC) as an Eclipse module." Crucially, the document states: "Smart Segmentation - Knowledge Based Contouring (SS KBC) v2.2 was cleared under K141248. The corresponding features above were cleared previously as a part of that submission."

This means that the current submission (K172163) does NOT provide the detailed acceptance criteria or study results for the SS KBC module itself. Instead, it incorporates a previously cleared module and relies on its prior clearance for safety and effectiveness. To find the specific details regarding the SS KBC's performance, a review of the K141248 submission would be necessary. This current document validates that the integration of this module into Eclipse TPS v15.5 maintains its intended functionality and does not introduce new safety or effectiveness concerns.

Ask a specific question about this device