Search Results

EmboGuide is a post processing software medical device intended to assist physicians in performing embolization of hypervascular tumors in the liver using interventional X-ray. It provides tools to help the user with the analysis of 3D rotational angiography images. Its output is intended as an adjunct means to help with the planning and guidance of the embolization procedure. It provides real time overlay of 3D rotational angiography images of the same anatomy to support device/catheter guidance.

EmboGuide is a post processing software medical device intended to assist physicians in performing embolization of hypervascular tumors in the liver using interventional X-ray. EmboGuide is an extension of XperCT and intended to be used in combination with an Allura interventional X-ray system. Like the primary predicate device 3D Roadmap, EmboGuide adds specific functionality to the Allura system but does not change the overall intended use of the Allura system or the overall risk profile.

EmboGuide uses a 3D volume reconstructed from 3D rotational angiography images acquired on the Allura X-ray system and the segmentation of lesions on previously acquired CT, MR or XperCT datasets as input data for the planning of the embolization. The physician can use this input data to analyze the vasculature of lesions, and to identify and annotate the blood vessels that shall be embolized (feeding vessels). The real-time overlay and registration of the 3D volume on live 2D X-ray images from the Allura X-ray system of the same anatomy can be used as additional 3D image guidance to support the navigation of the device/catheter. Planning data, like the earlier annotated feeding vessels and/or 3D landmarks can be displayed on 2D-3D fused images as supporting information.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document explicitly states acceptance criteria for the "overall agreement among readers for identification of feeding vessels" and reports sensitivity for EmboGuide. It also implicitly compares EmboGuide's performance to CBCT.

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

• Sample Size: The clinical validation study was based on a retrospective image collection of 63 patients. Within this, 44 subjects were included in the study, and 19 were excluded. This means the test set comprised data from 44 subjects.
• Data Provenance: The data was collected retrospectively. The patients were located outside the United States.

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

• Number of Experts: Two experienced interventional radiologists established the ground truth.
• Qualifications: They were described as "experienced interventional radiologists" who also performed the procedures. Specific years of experience are not mentioned.

4. Adjudication Method for the Test Set:

• The ground truth was established by consensus of two experienced interventional radiologists. This implies a form of consensus adjudication (e.g., 2/2 agreement, or discussion until agreement is reached).

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, what was the effect size of how much human readers improve with AI vs without AI assistance:

• Yes, a multi-reader study was performed. It involved three independent interventional radiologists determining feeding vessels.
• The study compared EmboGuide AFD alone, EmboGuide used in normal clinical practice (human-in-the-loop, adding/deleting vessels), and CBCT (without EmboGuide assistance).
• The effect size of human readers improving with AI assistance (EmboGuide AFD and EmboGuide in clinical practice) vs. without AI assistance (CBCT alone) is indicated by:
  • Higher sensitivity: EmboGuide (AFD alone and clinical practice) provided higher sensitivity for identifying feeding vessels compared to CBCT. Specific numerical effect size for this improvement is not given, only the qualitative statement "higher sensitivity."
  • Higher Inter-Reader Agreement:
    • EmboGuide AFD alone showed exceptionally high agreement (0.99).
    • EmboGuide in clinical practice showed agreement greater than 0.7.
    • CBCT alone showed lower agreement (0.69), which was below the acceptance criterion.
  • This implies that EmboGuide significantly improves consistency among readers.

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

• Yes, the performance of "EmboGuide AFD alone" was evaluated. This represents the algorithm's standalone performance in identifying feeding vessels.

7. The Type of Ground Truth Used:

• The ground truth was established by expert consensus (two experienced interventional radiologists) based on "all available information (2D angiography, MR and /or CT, Cone Beam CT (CBCT) and EmboGuide)". This is a form of clinical expert opinion/reference standard.

8. The Sample Size for the Training Set:

• The document does not provide information regarding the sample size for the training set. The clinical validation study is described as based on a "retrospective image collection," and the focus is on testing the performance, not on training data.

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

• As the document does not provide information about the training set, it also does not describe how the ground truth for any training set was established.

Ask a specific question about this device