K Number
K091934
Date Cleared
2009-12-02

(155 days)

Product Code
Regulation Number
892.1750
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The ig4™ Image Guided System is a stereotactic accessory for Computed Tomography (CT) and endoscopic bronchoscope systems. The ig4 System is indicated for displaying:

  • . An interventional instrument such as a biopsy needle, an aspiration needle, or ablation needle on a computer monitor that also displays a CT-based model of the target organ(s).
  • . Images of the tracheobronchial tree to aid a physician in guiding endoscopic tools, catheters or guidewires, in the pulmonary tract.
    The ig4™ System compensates for the patient's respiratory phases.
    The ig4™ System is intended for use in clinical interventions and for anatomical structures where computed tomography and/or endoscopic bronchoscopy are currently used for visualizing such procedures.
Device Description

The ig4™ EndoBronchial is an accessory for a CT System that utilizes electromagnetic tracking technology to locate and navigate endoscopic tools, catheters and guidewires relative to a CTbased model of the tracheobronchial tree. Due to system use to locate structures in soft tissue, the system incorporates a method of gating the location information on soft tissue to the patient's respiration. The ig4™ System consists of an EM tracking accessory, a patient referencing system, an EM field generator and tracking system, software, a computer system, and a pulmonary planning workstation. The EM tracking accessory consists of a navigation guidewire and may include additional navigated endoscopic tools.

AI/ML Overview

The provided text describes the Veran Medical Technologies ig4™ EndoBronchial device, an accessory for CT and endoscopic bronchoscope systems. It focuses on demonstrating substantial equivalence to predicate devices rather than presenting a detailed study proving the device meets specific acceptance criteria in terms of reported device performance metrics.

Therefore, many of the requested details about acceptance criteria, specific performance metrics, sample sizes for test/training sets, expert qualifications, and ground truth establishment are not explicitly provided in the document.

Here's an attempt to answer the questions based on the available information:

1. A table of acceptance criteria and the reported device performance

The document does not explicitly state quantitative acceptance criteria or specific reported device performance metrics (e.g., accuracy, sensitivity, specificity, etc.) for the ig4™ EndoBronchial in a clinical or benchmarked sense.

Instead, the performance evaluation is described qualitatively as:

  • "Bench testing on a static phantom and animal testing were completed to demonstrate navigation accuracy."
  • "Additionally, biological testing was completed on the EM navigation accessory to demonstrate that there are no biocompatibility issues."
  • "As required by Veran Medical Technologies design control processes and risk analysis, all verification and validation activities have been completed by designated individuals and have demonstrated the safety and effectiveness of the device."

The focus of the 510(k) submission is on demonstrating "safety and effectiveness" through substantial equivalence to predicate devices rather than meeting predefined quantitative performance targets.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document mentions "bench testing on a static phantom and animal testing," but it does not specify the sample sizes for these tests. It also does not provide information on the country of origin of the data or whether it was retrospective or prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not provided in the document. The tests performed ("bench testing" and "animal testing") would not typically involve human experts establishing ground truth in the way described for diagnostics devices. For navigation accuracy, ground truth is usually established through precise measurement systems.

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

This information is not provided. Given the nature of the bench and animal tests, an adjudication method for a test set as typically understood for diagnostic imaging or AI performance is not applicable.

5. 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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not mentioned or performed. The device is an "image-guided system" and "stereotactic accessory," implying a tool for assisting procedures, not an AI diagnostic system directly improving human reader performance.

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

The device is an "image-guided system" and "stereotactic accessory" for "guiding endoscopic tools, catheters or guidewires." This implies it's fundamentally designed for human-in-the-loop use. Therefore, a standalone performance evaluation in the context of an AI algorithm is not applicable and was not performed, nor would it be relevant for this type of device.

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

For "navigation accuracy" in "bench testing on a static phantom and animal testing," the ground truth would likely be established through physical measurements against known spatial coordinates or anatomical landmarks. Expert consensus, pathology, or outcomes data would not be the primary ground truth for demonstrating navigation accuracy.

8. The sample size for the training set

The document does not mention a training set for an AI/machine learning model. The ig4™ EndoBronchial is described as utilizing "electromagnetic tracking technology" and software for navigation, not as a device employing machine learning that would require a distinct training set.

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

Since a training set for an AI model is not mentioned or implied, this question is not applicable.

§ 892.1750 Computed tomography x-ray system.

(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.