Search Results

The PercuNav Image Fusion and Interventional Navigation System is a stereotaxic accessory for computed tomography (CT), cone beam CT (CBCT), magnetic resonance (MR), ultrasound (US), and positron emission tomography (PET). CT, Ultrasound, PET, and MR may be fused in various combinations, such as CT with ultrasound, and so on. It may include instrumentation to display the simulated image of a tracked insertion tool such as a biopsy needle or probe on a computer monitor screen that shows images of the target organs and the projected future path of the interventional instrument. The Perculav Interventional Navigation System is intended for treatment planning and to assist guidance for clinical, interventional, or diagnostic procedures in a clinical setting.

The PercuNav Image Fusion and Interventional Navigation System is also intended to supplement live imaging in clinical interventions to determine the proximity of one device relative to another.

The PercuNav Image Fusion and Interventional Navigation System is not intended to be the sole guidance for any procedures that can be guided by the PercuNav Image Fusion and Interventional Navigation System adjunctively include, but are not limited to, the following:

• · Image fusion for diagnostic clinical examinations and procedures
• · Soft tissue biopsies
• · Soft tissue ablation
• Bone ablation
• · Bone biopsies
• · Nerve blocks and pain management
• · Drainage placements

The PercuNav Image Fusion and Interventional Navigation System provides image-guided diagnostic and intervention support that enables fusion of diagnostic images and guidance of tracked instruments to physician-defined targets. The target can be indicated either pre-procedurally or intra-procedurally, either using images or relative to an indicated position on the patient. The system transforms two-dimensional patient images into dynamic representations that can be fused with live ultrasound or other previously acquired images. Those two-dimensional patient images, or scan sets, are derived from Ultrasound, CT, PET, PET/CT, and MRI. The resulting dynamic representation supports diagnostic review and instrument navigation.

The user-assisted Ablation Planning software tool enhancement is to aid the user when placing the ablation tip using a computer algorithm to maximize the spatial overlap between the ablation zone volume and the tumor contour.

The user-assisted Co-Registration software tool is to aid the user in co-registering between two different CT series from the same patient using a computer algorithm to create an image that forms the basis to be applied to the various CT sets for landmark registration.

Here's a breakdown of the acceptance criteria and study information for the Philips PercuNav Image Fusion and Interventional Navigation System, based on the provided FDA 510(k) summary:

This submission focuses on software enhancements: user-assisted Ablation Planning and user-assisted Co-Registration. The core PercuNav system was previously cleared (K201053).

1. Table of acceptance criteria and the reported device performance:

The document states: "For feature testing, all pre-determined acceptance criteria were met. Results of these tests show that the proposed PercuNav Image Fusion and Interventional Navigation System meets its intended use."

Unfortunately, the specific numerical acceptance criteria (e.g., accuracy thresholds, success rates) and the detailed reported device performance metrics are not provided in this 510(k) summary. The document only offers a general statement of compliance. This is common in 510(k) summaries, which aim to provide a high-level overview rather than the detailed test reports themselves.

2. Sample size used for the test set and the data provenance:

• Sample Size for Test Set: Not explicitly stated. The document refers to "non-clinical bench performance testing." This typically involves a set of predefined test cases or datasets, but the number is not specified.
• Data Provenance: The document does not specify the country of origin of the data. It mentions "internal processes" and "non-clinical bench performance testing," suggesting these tests were conducted by Philips. The data would likely be retrospective artificial or representative data used for bench testing, not patient-specific prospective data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Number of Experts: Not explicitly stated. Given the nature of "non-clinical bench performance testing" for software features that provide a "proposed starting point" for user acceptance/manipulation, the ground truth may have been established through a combination of:
  • Pre-defined gold standard data or simulations.
  • Internal expert review by engineers or clinical specialists at Philips during development and testing.
• Qualifications of Experts: Not explicitly stated. However, for medical device software, it's expected that experts involved in ground truth establishment would include those with relevant clinical (e.g., radiologists, interventionalists) or engineering expertise.

4. Adjudication method for the test set:

• Adjudication Method: Not explicitly stated. Given that the software "proposes an option to the user that they then can manipulate or accept," the "adjudication" (or validation process) likely involved demonstrating that the proposed solutions were reasonable and effective starting points, and that users could successfully refine them to reach desired outcomes. This would be part of the "non-clinical bench performance testing."

5. If a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance:

• MRMC Study: No, an MRMC comparative effectiveness study was not explicitly done or required for this 510(k) submission. The document states: "The proposed PercuNav Image Fusion and Interventional Navigation System did not require clinical data for determination of substantial equivalence."
• Effect Size: Therefore, no effect size for human reader improvement with AI assistance vs. without AI assistance is reported. This submission is for enhancements to a system that aids a human user, not a standalone diagnostic AI aiming to replace or significantly augment diagnostic interpretation in a MRMC setting. The enhancements are framed as workflow improvements rather than a direct comparative effectiveness study on diagnostic accuracy.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

• Standalone Performance: While the algorithms themselves (for ablation planning and co-registration) operate in a "standalone" fashion to generate their proposed solutions, the overall system is designed for human-in-the-loop performance. The software "proposes an option to the user that they then can manipulate or accept." Therefore, the "performance" validated was likely the utility and accuracy of these proposed initial solutions as input to a human user's workflow, not as a final, automated decision-maker.

7. The type of ground truth used:

• Type of Ground Truth: The document does not explicitly state the type of ground truth. Given the "non-clinical bench performance testing" for software features that optimize spatial overlap (ablation planning) or co-registration fidelity, the ground truth would likely be pre-defined, gold-standard computational models, synthetic data, or carefully curated clinical image datasets with known geometric relationships and tumor contours. These would be used to evaluate the accuracy of the algorithms' proposed solutions.

8. The sample size for the training set:

• Sample Size for Training Set: Not stated. Training set details are typically not included in 510(k) summaries, especially for software enhancements that might leverage existing or established algorithms rather than entirely new, deep learning models requiring vast training datasets.

9. How the ground truth for the training set was established:

• How Ground Truth for Training Set was Established: Not stated. As the sample size for the training set is not provided, neither is the method for establishing its ground truth.

Ask a specific question about this device