(54 days)
The Innova systems are indicated for use in generating fluoroscopic images of human anatomy for vascular angiography, diagnostic and interventional procedures, and optionally, rotational imaging procedures. They are also indicated for generating fluoroscopic images of human anatomy for cardiology, diagnostic, and interventional procedures. They are intended to replace fluoroscopic images obtained through image intensifier technology. These devices are not intended for mammography applications.
The Innova 4100 IQ, 3100 IQ, 2100 IQ Systems are modified with an optional software feature called StentViz. The StentViz feature enhances the visibility of stents in the x-ray images produced by the Innova systems. Specifically, StentViz provides an enhanced static image of the stent that is derived from the video image sequence as recorded during fluoroscopic guidance. It does not provide real-time guidance.
The information provided focuses on demonstrating substantial equivalence to predicate devices rather than establishing specific acceptance criteria and detailed performance studies for the StentViz feature itself. Therefore, many of the requested details about acceptance criteria, sample sizes, expert involvement, and ground truth establishment are not explicitly stated in the provided text.
Here's a breakdown of the available information:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not explicitly present a table of acceptance criteria with numerical targets. Instead, it relies on a qualitative comparison to predicate devices and general statements about image enhancement.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Enhanced visibility of stents (compared to Innova without StentViz) | Bench tests were performed "to assess the enhancement of stent visibility." The text states, "When StentViz is used, the image quality and visibility of the stent is improved." |
| Comparable image quality/stent enhancement to predicate devices (StentOp and StentBoost) | Bench tests were performed "to compare the performance of the Innova with StentViz to... the performance of the similar feature contained in the predicate device StentOp." The document concludes, "The image quality of the stent is enhanced in a comparable way with StentViz than with StentOp and StentBoost." Its performance is "substantially equivalent to the predicate devices." |
| No adverse impact on safety or effectiveness | The improvement "does not adversely impact safety or effectiveness." |
| Compliance with voluntary standards | The Innova systems with StentViz comply with voluntary standards as detailed in Sections 9 and 17 of the premarket submission (details not provided in the extract). |
2. Sample size used for the test set and the data provenance:
- Sample Size: "Bench tests were performed based on a library of clinical images." The exact number of images in this "library" is not specified.
- Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. It only mentions "clinical images."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This information is not provided in the document. The evaluation of "enhancement of stent visibility" appears to have been part of bench testing, but who performed these assessments and their qualifications are not mentioned.
4. Adjudication method for the test set:
- This information is not provided.
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 MRMC comparative effectiveness study is not explicitly mentioned. The evaluation described is "bench tests" to assess enhancement and perform comparisons. The document does not discuss human reader performance or improvement with AI assistance (StentViz).
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The evaluation was a "bench test" comparing the StentViz feature to the Innova without StentViz and to a predicate device's feature (StentOp). While human eyes would ultimately interpret the enhanced images, the description of "bench tests... to assess the enhancement of stent visibility" and compare performance suggests an evaluation of the algorithm's output (the enhanced image) itself, making it akin to a standalone performance assessment of the image enhancement capability. However, it's not explicitly stated as "algorithm only without human-in-the-loop performance" in the strict sense of a diagnostic task.
7. The type of ground truth used:
- The document mentions "a library of clinical images" being used for bench tests to assess "enhancement of stent visibility." The "ground truth" for assessing this enhancement is not explicitly defined. It likely relied on a subjective or objective assessment of image clarity and stent outline on the enhanced images compared to unenhanced images or images from predicate devices. There is no mention of pathology, or outcomes data being used as ground truth for this enhancement feature.
8. The sample size for the training set:
- The document does not provide information about a specific training set. The StentViz is described as an "optional software feature" that "enhances the visibility of stents." The development process mentioned includes "Risk Analysis, Requirements Reviews, Design Reviews, Testing on unit level (Module verification), Integration testing (System verification), Final acceptance testing (Validation), Performance testing (Verification), Safety testing (Verification)." This suggests a standard software development and testing cycle rather than a machine learning model that would typically have a distinct "training set."
9. How the ground truth for the training set was established:
- As no specific training set for a machine learning model is mentioned, this information is not applicable/provided. The feature development would have followed established engineering principles for image processing, not a typical machine learning training paradigm with a labeled ground truth dataset.
§ 892.1650 Image-intensified fluoroscopic x-ray system.
(a)
Identification. An image-intensified fluoroscopic x-ray system is a device intended to visualize anatomical structures by converting a pattern of x-radiation into a visible image through electronic amplification. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). An anthrogram tray or radiology dental tray intended for use with an image-intensified fluoroscopic x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9. In addition, when intended as an accessory to the device described in paragraph (a) of this section, the fluoroscopic compression device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.