(57 days)
Indicated for displaying images of the tracheobronchial tree to aid the physician in guiding endoscopic tools or catheters in the pulmonary tract and to enable marker placement within soft lung tissue. It does not make a diagnosis and is not an endoscopic tool. Not for pediatric use.
This premarket notification covers Broncus' LungPoint VBN System. The VBN System is a software only device, providing a navigation system to help the bronchoscopist plan and proceed to a predefined target site in the tracheobronchial tree. Specifically, the VBN system provides global quidance to targets preselected by the bronchoscopist in peripheral airways. In doing so, the VBN can provide local guidance to lymph nodes to enable tissue sampling. It can also facilitate the return to an exact location in the lungs that had previously been treated for assessment of or continued therapy. The VBN software is installed on an off-the-shelf PC computer system, and is intended to be used with commercially-available flexible bronchoscopes with HRCT scans that are saved in DICOM format.
Here's a breakdown of the acceptance criteria and study information for the LungPoint™ Virtual Bronchoscopic Navigation (VBN) System, based on the provided 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Accuracy: Distance error between virtual targets and actual targets in real bronchoscope video. | 2.17 +/- 0.84 mm (from animal study) |
| Accuracy: Mean and standard deviation of distance error (phantom study). | 2.2 +/- 2.3 mm (from phantom study) |
Note: The 510(k) summary does not explicitly state "acceptance criteria" but rather presents performance data from studies. The interpretation is that the demonstrated accuracy values were deemed acceptable by the FDA for clearance.
2. Sample Size Used for the Test Set and Data Provenance
- Animal Study: The document mentions "an animal study" in a "canine model" but does not specify the exact number of animals or trials conducted.
- Phantom Study: The document refers to "an earlier phantom study performed by Merritt et al" but does not specify the sample size (number of phantom cases/measurements).
- Data Provenance:
- Animal Study: Canine model (prospective, as it was conducted to evaluate the system).
- Phantom Study: Not explicitly stated, but phantom studies are typically controlled and designed prospectively.
3. Number of Experts Used to Establish Ground Truth and Qualifications
The provided 510(k) summary does not include information on the number or qualifications of experts used to establish ground truth for either the animal or phantom studies. The ground truth for accuracy was likely established through direct measurement of physical distances, rather than expert consensus on subjective interpretations.
4. Adjudication Method for the Test Set
The document does not describe any adjudication method for the test set. Given the nature of measuring distance error in physical or virtual environments, it's unlikely that adjudications by multiple readers were required in the same way they would be for subjective image interpretations.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done or reported in this 510(k) summary. The studies focused on the standalone accuracy of the navigation system rather than its impact on human reader performance.
6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance
Yes, the reported studies primarily assess the standalone performance of the LungPoint VBN system. The accuracy measurements (distance error) evaluate the system's ability to precisely align virtual targets with actual targets, which is an intrinsic performance characteristic of the algorithm/system rather than its direct impact on a human user's diagnostic ability.
7. Type of Ground Truth Used
- Animal Study: The ground truth was based on the "actual target in the real bronchoscope video" which implies physical, measurable locations marked or identified in a live setting, against which the virtual targets were compared. This would be a form of direct measurement/physical truth.
- Phantom Study: Similarly, the ground truth for the phantom study would have been based on physical precision measurements within the phantom model.
8. Sample Size for the Training Set
The 510(k) summary does not mention or specify a sample size for the training set for the VBN software. As a navigation system, its core function is to process existing HRCT scans (DICOM format) to create virtual pathways. While software development involves testing and calibration, the summary does not detail a separate "training set" in the context of machine learning model development. This submission precedes the widespread emphasis on AI/ML training data reporting in regulatory submissions.
9. How the Ground Truth for the Training Set Was Established
Since no training set is mentioned in the provided document, there is no information on how its ground truth was established. For a navigation system of this type, the "training" (if applicable in a more traditional software sense) would likely involve adherence to anatomical models and engineering specifications for calculating virtual paths and registering images.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).