K Number
K071619
Date Cleared
2007-11-09

(149 days)

Product Code
Regulation Number
892.1600
Panel
RA
Reference & Predicate Devices
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The SPY Fluorescent Imaging System is intended to provide fluorescent images for the visual assessment of blood flow in vessels and related tissue perfusion during cardiovascular surgical procedures.

Device Description

The Novadaq® Technologies SPY® Fluorescent Imaging System consists of 2 components:

  • the SP2000 Imaging Device; and
  • the SPY Paq®

The SPY Pag constitutes a 6 procedure kit. Each SPY Pag contains The Sir I aq constitution a o procours ... " procedures ... " leG and diluent to carry out 6 cardiovascular imaging procedures. Novadaq provides the ICG as it is sold by the manufacturer and does not adulterate the integrity of the original packaging or labeling. IC-Green™ (Akorn, Inc.) is packaged in an IC-Green kit that contains 6 x 25 mg vials of ICG along with 6 x 10 ml ampules of Aqueous Solvent.

The SP2000 Imaging Device consists of an imaging head containing a charge coupled device (CCD) camera, a laser light source, motion sensor and distance sensor attached via an articulating arm to a mobile cart. The mobile cart contains a flat panel display, computer, electronics enclosure and printer.

The SPY System provides the surgeon with the capability to view record and replay fluorescent images of blood flow in vessels and bypass grafts of the heart. A laser light source is used to illuminate the area of interest. ICG is injected intravenously through the central venous line, bypass pump, cardioplegia line and coronary graft and while it is passing through the vessels, the absorption of laser light causes excitation of the dye followed by emission of infrared energy. The result is a fluorescent image of blood flow and related tissue perfusion in the vessels. A CCD camera captures the image. These images are used to evaluate the integrity of the coronary vasculature and blood flow in the heart and bypass grafts.

AI/ML Overview

The provided text describes the Novadaq SPY Fluorescent Imaging System (SPY System), model SP2000, and its expanded indications for use. It outlines testing conducted to support the device's safety and effectiveness.

Here’s a breakdown of the information requested, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in the traditional sense of specific, quantifiable metrics that the device must achieve (e.g., sensitivity, specificity, accuracy against a gold standard). Instead, it describes general safety and performance assessments. The reported device performance is qualitative and based on the ability to produce high-quality images and a lack of adverse effects.

Acceptance Criteria Category (Implied)Reported Device Performance
Safety - ElectricalSuccessfully met all requirements per IEC 60601-1 and UL2601-1.
Safety - Electromagnetic CompatibilitySuccessfully met all requirements per IEC 60601-1-2.
Safety - Laser ProductsSuccessfully met requirements per 21 CFR 1040 and ANSI Z136.3, ANSI Z136.1.
Safety - Thermal EffectsNo increase in myocardial tissue temperature (pig studies). Exposure (35 mW/cm²) is far below maximum permissible exposure (327 mW/cm²) by ANSI. Does not cause thermal damage, even after repeated imaging.
Safety - Physiological EffectsNo detrimental effects on heart function, coronary flow, or peripheral pressure (pig studies). No changes in electrocardiograms or arterial pressures during and/or following SPY use.
Safety - Cellular/Organ EffectsNo adverse acute or long-term cellular, renal, or hepatic effects reported in human use (over 4000 CABG procedures). No acute or long-term cellular, renal, or hepatic effects (pig studies).
Effectiveness - Image QualityAble to acquire high-quality images in a simple and reproducible manner (pig studies). Capable of visualizing all coronary beds with high-quality images (pig studies). Able to acquire high-quality images of the entire vascular bed on each area of interest. Produces high-quality and resolution images of the entire vascular bed of the point of interest (human experience).
Effectiveness - Clinical UtilityNon-invasively, quickly, and safely identified 17 conduits requiring revision in 311 patients, visualizing lack of patency clearly (human literature). Capable of imaging through the skin to provide visual assessment of dermal and subdermal blood flow.

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

  • Human Data:
    • Sample Size: Over 4000 CABG procedures (for general market availability and safety data) and 311 patients (for specific outcome data mentioned in peer-reviewed literature for identifying conduits requiring revision).
    • Data Provenance: "Commercially available in the United States of America, Japan, Europe and Canada." This suggests retrospective (post-market surveillance) data collected from various countries.
  • Animal Data:
    • Sample Size: Six pig studies.
    • Data Provenance: Not explicitly stated, but likely conducted in a controlled lab or animal facility. This would be prospective data for the original 510(k).

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

The document does not specify the number of experts or their qualifications for establishing ground truth for the human or animal test sets.

For the human data, the "literature reports" refer to surgeons (implied experts) identifying an issue and performing revisions, suggesting the clinical judgment of the operating surgeon as a form of ground truth for that specific outcome.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method. For the human data, the "literature reports that the SPY System was able to... identify 17 conduits... that required revision," implying that the need for revision was determined by the operating surgeon(s) based on intraoperative findings and the SPY system's input, but no formal adjudication process is detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a MRMC comparative effectiveness study was not explicitly mentioned or described. The document focuses on the standalone performance and safety of the device, and qualitative improvements due to intraoperative visualization. It doesn't report on an effect size of human readers improving with AI vs. without AI assistance, as this is not an AI-assisted device in the sense of predictive or diagnostic algorithms.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

The SPY System is an imaging device meant for human-in-the-loop performance. It provides visual information to the surgeon. Therefore, a purely "standalone" (algorithm-only) performance evaluation, separate from human interpretation, is not applicable or described for this type of device. The system's "performance" is its ability to acquire high-quality images of blood flow for human assessment.

7. The Type of Ground Truth Used

  • Human Data:
    • For safety: Absence of reported adverse acute or long-term cellular, renal, or hepatic effects; absence of reported major complications in over 4000 CABG procedures.
    • For effectiveness: Surgeon judgment/intraoperative findings (the need for graft revision identified by the SPY system and confirmed by the surgeon), and the ability to visualize various vascular beds and perfusion.
  • Animal Data:
    • Direct physiological measurements (e.g., heart function, coronary flow, peripheral pressure, myocardial tissue temperature, electrocardiograms, arterial pressures, cellular, renal, hepatic effects).
    • Visual assessment by researchers/veterinarians of image quality and visualization capabilities.

8. The Sample Size for the Training Set

This report does not mention a training set in the context of an AI/machine learning algorithm. The SPY System is an imaging device, not a diagnostic algorithm that requires a "training set" in the typical sense. Its development would involve engineering and optical design validations, not data-driven model training.

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

As there is no mention of a training set for an AI/machine learning algorithm, this question is not applicable based on the provided text.

§ 892.1600 Angiographic x-ray system.

(a)
Identification. An angiographic x-ray system is a device intended for radiologic visualization of the heart, blood vessels, or lymphatic system during or after injection of a contrast medium. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.