Search Results

The LAP LUNA 3D system is used to support reproducible patient positioning and monitor patient surface motion during radiotherapy and radiosurgery treatments and during CT simulation for radiation therapy planning. LAP LUNA 3D may also be used to guide patients through breath-holds. The LAP LUNA 3D system can be used for all patients, undergoing radiotherapy and radiosurgery treatments and radiosurgery treatments and CT simulation for radiation therapy planning.

The LUNA 3D optical camera system captures the current 3D patient skin surface with one or multiple camera pods. The software calculates the spacial deviations between the captured live surface and a reference surface within a selected region of interest using a registration algorithm. Reference surfaces may be generated with the optical camera system or may be imported using data received from Treatment Planning Systems (TPS). Based on the registration results the user can adjust the patient position for reproducible patient positioning relative to the treatment isocenter. During the imaging (simulation) and treatment delivery process, the system continuously calculates the deviations between live- and reference surface for patient motion monitoring to ensure that the patient position remains within pre-defined tolerances.

Here's an analysis of the acceptance criteria and study information for the LUNA 3D device based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA 510(k) summary provides limited detailed acceptance criteria and mostly focuses on comparison to a predicate device. The performance claims primarily relate to accuracy.

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

The provided summary does not specify a sample size for any clinical test set or the data provenance (e.g., country of origin, retrospective/prospective). The performance testing described is "non-clinical performance testing" which typically refers to bench testing rather than studies involving human subjects or clinical data.

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

The provided summary does not mention any test set requiring expert ground truth or the involvement of experts for this purpose. The performance testing relies on a "calibration phantom."

4. Adjudication Method for the Test Set

As no expert-derived ground truth or clinical test set is described, no adjudication method is mentioned or applicable in the provided document.

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

A MRMC comparative effectiveness study was not performed or described in the provided summary. The summary focuses on the device's standalone performance and comparison of technical characteristics to a predicate device, not on human reader improvement with or without AI assistance.

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

Yes, a standalone performance assessment was conducted. The "non-clinical performance testing in terms of warm-up drift, latency, and multi-camera accuracies of the camera pods" and the reported "positioning accuracy" and "respiratory tracking" metrics (using a calibration phantom) reflect the algorithm's performance without direct human interaction during the measurement process. The device's function is to provide information for humans to use, but the core measurements are automated.

7. Type of Ground Truth Used

The ground truth for the non-clinical performance testing was established using a calibration phantom. This is a physical object with known dimensions and properties used to assess the accuracy of the imaging system.

8. Sample Size for the Training Set

The provided summary does not specify a sample size for any training set. Given that this is a 510(k) for a medical charged-particle radiation therapy system accessory and not a purely AI/ML enabled diagnostic device, details on training data are often less emphasized in the summary unless substantial AI model development is a primary feature. The LUNA 3D is described as an "optical camera system" with "software calculates the spacial deviations... using a registration algorithm," which implies algorithms but not necessarily deep learning that would require a large training set in the typical sense.

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

As no training set is described, no information on how its ground truth was established is provided.

Ask a specific question about this device