Search Results

The LungPoint® ATV Planning and Navigation Software for displaying images of the tracheobronchial tree to aid the physician in guiding endoscopic tools and cathere in the pulmonary tract to a location in the or lung tissue, and to enable marker placement within soft lung tissue. It does not make a diagnosis and is not for pediatric use.

When under fluoroscopy guidance, the software enables users to segment previously acquired 3D CT datasets and register these 3D segmented data sets with live fluoroscopy X-ray images of the same anatomy in order to support cathereldevice navigation. The 3D segmented data set can be displayed with a color map annotation received from an external source.

The LungPoint tools (necdle, balloon dilator, and sheath) are used with a bronchoscope, navigated by the LungPoint Software.

The LungPoint Software is a software device, providing navigation guidance to help the physician plan and proceed to a predefined target site in the bronchial tree and surrounding soft lung tissue by providing a path, which is displayed on a 3D reconstruction of a CT scan. The LungPoint Software provides guidance to targets in the lung preselected by the physician. In doing so, the software provides guidance to lymph nodes or lesions to enable tissue sampling. It can also facilitate the return to the location that had previously been treated for assessment or continued therapy, or to enable marker placement in soft lung tissue.

The software system consists of multiple modules that closely interact with each other to perform the overall product's functions. Each module is designed to perform a specific function such as airway tree segmentation, centerline calculation, etc and relies on outputs of other module(s) to perform its function. All modules share the same data structure defined in the Modules Interface section that is shared as binary and text files.

The software consists of two key programs: Planning and Procedure. The procedure program contains two separate procedural options, depending on the complexity and location of the lesion in the lung: (a) Virtual Bronchoscopic Navigation (VBN) and (b) Navigation with fluoroscopic guidance.

Acceptance Criteria and Performance Study for Broncus Medical LungPoint® ATV Planning and Navigation Software

The provided document describes the Broncus Medical LungPoint® ATV Planning and Navigation Software, which is intended to display images of anatomy to aid physicians in guiding endoscopic tools or catheters through the tracheobronchial tree or lung tissue, and to enable marker placement. The core of the performance evaluation relies on software verification and validation testing, and a preclinical study in canines.

1. Acceptance Criteria and Reported Device Performance

The document states that "All testing results met the pre-determined acceptance criteria that were established in the test protocols." However, the specific quantitative acceptance criteria are not explicitly detailed in the provided text. The overall reported device performance is that it "performs as intended" and "successfully fulfilled the requirements defined in the Software Requirement Specifications (SRS)," with "no new questions of safety or effectiveness identified."

2. Sample Size for the Test Set and Data Provenance

• Sample Size: The test set for the preclinical study involved "healthy canines." The specific number of canines is not provided.
• Data Provenance: The study was "preclinical" and involved "healthy canines," indicating it was a prospective experimental study in an animal model, not human data.

3. Number of Experts and Qualifications for Ground Truth

• The document does not specify the number of experts used to establish ground truth for the tests.
• It also does not detail the qualifications of any such experts if they were involved in ground truth establishment. The study in canines implies targets were "implanted," which would likely have a clear, objective ground truth definition.

4. Adjudication Method for the Test Set

• The document does not mention any adjudication method (e.g., 2+1, 3+1) for the test set.

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

• A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted, or at least not reported in this summary. The study was a preclinical evaluation of the device's performance in navigating to implanted targets in canines, not a comparison of human reader performance with and without AI assistance.

6. Standalone Performance Study

• A standalone performance study of the algorithm (without human-in-the-loop performance) appears to have been the primary focus of the testing. The "software verification and validation testing" evaluates the LungPoint ATV Software's ability to segment, calculate centerlines, and guide navigation. The preclinical study in canines assessed the software's ability to "met its intended use for navigating and accessing target sites," implying the software's direct performance in guiding the procedure.

7. Type of Ground Truth Used

• For the preclinical study, the ground truth was based on the ability to access "implanted targets" in soft lung tissue. This suggests a known, objective physical ground truth established through the implantation process, rather than expert consensus, pathology, or outcomes data. For software verification and validation, the ground truth would be defined by the "Software Requirement Specifications (SRS)."

8. Sample Size for the Training Set

• The document does not provide any details regarding the sample size used for the training set.

9. How Ground Truth for the Training Set Was Established

• The document does not provide any information on how ground truth was established for the training set. Given that this is a 510(k) summary for a navigation software, detailed information on training data and methods is often less extensively documented compared to submissions for diagnostic AI devices where training data quality is paramount for classification performance.

Ask a specific question about this device

The LungPoint Tools are endoscopic tools intended to be used with LungPoint Software guided bronchoscopes. The LungPoint Sheath is intended to be used as a working channel through which endoscopic tools may be introduced to targeted tissue. The LungPoint Dilation Balloon is intended to dilate tissue of the bronchial tree and may be inserted through the LungPoint Sheath or directly through the working channel of the bronchoscope. Not for pediatric use.

The LungPoint Tools are endoscopic tools used during bronchoscopy procedures. The LungPoint Sheath is designed to be used with a bronchoscope to provide a working channel through which endoscopic tools, such as needles, dilation balloons, or other endoscopic devices may be introduced to the targeted lung tissue within the respiratory organs. The LungPoint Dilation Balloon is used to dilate tissue of the bronchial tree and may be inserted through the sheath or directly through the working channel of the bronchoscope. The bronchoscope is advanced to a predefined target following guidance of the LungPoint Software (previously cleared under 510(k) #K 12051 to guide endoscopic tools or catheters in the lungs or to enable marker placement in soft lung tissue).

The materials used in the LungPoint Tools are commonly used medical grade materials and include platinum iridium markers.

This document describes the validation of the LungPoint™ Tools (LungPoint Sheath and LungPoint Dilation Balloon). It's important to note that this is a 510(k) summary for a medical device (tools), not an AI/ML device, so many of the requested fields related to AI/ML device validation (e.g., effect size with AI assistance, training set details) are not applicable (N/A). The summary focuses on demonstrating substantial equivalence to predicate devices through physical and functional performance testing.

Acceptance Criteria and Device Performance

The acceptance criteria for the LungPoint Tools were based on meeting pre-determined specifications for functional and performance tests. The specific numerical acceptance criteria are not detailed in the provided text but are stated to have been met.

Study Details

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

   • Test set sample size: Not explicitly stated in terms of number of devices tested, but the performance data refers to a series of physical and functional tests performed on the devices themselves.
   • Data provenance: The tests were conducted internally by the manufacturer (Broncus Medical, Inc.) to verify the design and safety of the devices. The context suggests these were laboratory-based engineering and performance tests relevant to the physical characteristics and function of the tools.

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

   • N/A. This device is a physical medical tool, and its "ground truth" is established by its physical specifications and functional performance under laboratory conditions, not by expert interpretation of data or images. Performance was verified against pre-determined engineering and safety specifications.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • N/A. Adjudication methods are typically relevant for interpretive tasks involving human experts, which is not the case for this type of device performance testing.

4. 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:

   • N/A. This is not an AI/ML device.

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

   • N/A. This is not an AI/ML device.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The "ground truth" for these physical tools is their engineering specifications, material properties, and functional performance benchmarks as established during the design and manufacturing process. The goal was to demonstrate that the devices met these pre-determined acceptance criteria and performed comparably to predicate devices.

7. The sample size for the training set:

   • N/A. This is not an AI/ML device.

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

   • N/A. This is not an AI/ML device.

Ask a specific question about this device