Search Results

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

The SPY System consists of two components: the SP2001 Imaging Device and the SPY Pag. The SPY System utilizes the fluorescent imaging agent ICG. The SP2001 Imaging Device consists of an imaging head containing a camera, a laser light source, and a distance sensor attached to a mobile cart via an articulating arm. The mobile cart contains a flat panel monitor, a computer with keyboard and mouse, an electronics enclosure, and a printer. While ICG distributes through the vessels or tissues, absorption of laser light at 808 nm causes excitation of the ICG followed by emission of infrared energy at a wavelength of 830 nm. This results in a fluorescent image of the blood vessels and related tissue perfusion. A CCD camera with an 830 nm optical band-pass filter captures the images, Image sequences. up to 60 seconds in duration, are displayed on the monitor and recorded on the computer hard drive. The image sequences can be exported to a CD, DVD, memory stick or lpod. The camera head can be moved in the in horizontal plane during image sequence acquisition. Once the image is captured, the laser automatically shuts off.

Here's a breakdown of the acceptance criteria and the study information based on the provided 510(k) summary:

Acceptance Criteria and Device Performance Table:

It's important to note that this 510(k) summary does not explicitly state specific pass/fail acceptance criteria with numerical targets for the device's performance related to the proposed expanded indication (GI surgical procedures). Instead, it relies on demonstrating comparable performance to previously cleared indications and safety profiles. The performance reported is qualitative based on clinical utility and image quality.

Study Details:

1. Sample Size used for the test set and data provenance:

   • Test Set Sample Size: Not explicitly stated as a numerical sample size for the current 510(k) submission's GI surgical procedures. The text refers to "All cases were conducted under the attending surgeons' medical judgment as part of the reconstructive clearance for the device. The examples are not meant to be all encompassing... but illustrate the safety and effectiveness of SPY imaging in this system throughout the GI tract from the esophagus to the anus." This suggests a collection of cases, but no specific number is provided.
   • Data Provenance: The studies were conducted on humans in various countries where the SPY System is commercially available (United States of America, Japan, Europe, Canada, Israel, and Russia). It's a combination of prospective and retrospective human experience since it refers to "over 10,000 surgical procedures in humans" and "This current 510(k) submission contains clinical performance data that support the use of the SPY System during GI surgical procedures. All cases were conducted under the attending surgeons' medical judgment as part of the reconstructive clearance for the device." This implies clinical use data rather than a dedicated, controlled prospective study for this specific indication expansion.

2. Number of experts used to establish the ground truth for the test set and their qualifications:

   • This information is not provided in the summary. The qualitative assessment of "utility," "safety," and "high quality images" appears to be based on the general judgment of "attending surgeons" and the reported experience in clinical use, rather than a formal ground truth established by a panel of independent experts for a specific test set.

3. Adjudication method for the test set:

   • This information is not provided. Given the nature of the data ("clinical utility" and "attending surgeons' medical judgment"), a formal adjudication method (like 2+1 or 3+1 consensus) for a specific test set does not appear to have been performed or described for this submission.

4. 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:

   • No, an MRMC comparative effectiveness study was not done. The SPY System is described as an intra-operative imaging system that provides images for visual assessment by surgeons, not an AI-assisted diagnostic tool that interprets images or improves human reader performance in a quantifiable MRMC study setup.

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

   • No, a standalone algorithm-only performance study was not done. The device's utility is explicitly stated as providing "fluorescence images for the visual assessment of blood flow," implying human interpretation is integral, not merely a supplemental step to an automated algorithm. The system is a medical device for imaging, not an AI diagnostic algorithm in isolation.

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

   • For the current GI indication, the "ground truth" is largely observational clinical utility and safety data from real-world surgical procedures, assessed by the attending surgeons, and general lack of adverse events. It is not framed as a formal ground truth established against a gold standard like pathology or long-term outcomes data in the context of a controlled study. For the original 510(k) (K042961), pig studies were used to demonstrate image quality, lack of thermal/physiological effects, but not explicitly linked to a "ground truth" in the diagnostic sense.

7. The sample size for the training set:

   • This information is not applicable/not provided in the context of this 510(k) summary. The SPY System is an imaging device, not a machine learning model that requires a "training set" in the traditional AI sense. Its underlying technology is optical fluorescence imaging. Previous clearances and extensive clinical use (over 10,000 procedures) serve as a broad "experience base" rather than a dedicated training set for an algorithm.

8. How the ground truth for the training set was established:

   • This information is not applicable for the same reasons as #7. There is no training set for a machine learning algorithm described in this submission.

Ask a specific question about this device

For use in intraoperative visual assessment of the coronary vasculature and bypass grafts during coronary artery bypass (CABG) surgery.

The SPY Imaging System: SP2000 is currently cleared for intraoperative visual assessment of the coronary vasculature and grafts during coronary artery bypass graft (CABG) surgery. The Novadaq Technologies SPY Intra-operative Imaging System consists of 2 components: the SPY Imaging Device; and the SPY Paq®

This 510(k) pertains to a medical imaging system rather than an AI/ML device. Therefore, the typical acceptance criteria and study designs for AI/ML devices involving performance metrics like sensitivity, specificity, AUC, and multi-reader studies are not applicable in this context.

The document describes the SPY® Intra-operative Imaging System (Model SP2000), which is a fluorescent angiographic system used for intraoperative visual assessment of coronary vasculature and grafts during coronary artery bypass graft (CABG) surgery.

The FDA's decision is based on a determination of substantial equivalence to legally marketed predicate devices, not on specific performance acceptance criteria as would be typical for an AI/ML diagnostic or prognostic device.

Here's an analysis of what can be extracted from the provided text, recognizing the limitations due to the nature of the device (imaging system, not AI/ML):

1. Table of Acceptance Criteria and Reported Device Performance:

• Acceptance Criteria: Not explicitly stated as quantifiable performance metrics (e.g., sensitivity, specificity thresholds) in this 510(k) summary. The primary "acceptance criterion" for clearance in this context is demonstrating substantial equivalence to a predicate device.
• Reported Device Performance: The document does not contain specific quantifiable performance results (e.g., accuracy rates, image quality scores, comparison against a gold standard in a statistical sense). Instead, it describes:
  • Intended Use: "For use in intraoperative visual assessment of the coronary vasculature and bypass grafts during coronary artery bypass (CABG) surgery."
  • Functional Description: "The SPY Imaging System: SP2000 is currently cleared for intraoperative visual assessment of the coronary vasculature and grafts during coronary artery bypass graft (CABG) surgery." This indicates its functional capability rather than statistical performance.
  • Substantial Equivalence: The FDA determined the device is "substantially equivalent" to legally marketed predicate devices (K042961, K060867). This is the core "performance" assessment for this type of device submission.

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

• Not applicable / Not provided: The document does not describe a "test set" in the context of an AI/ML algorithm's evaluation with specific patient data. The substantial equivalence determination likely relied on technical specifications, design comparisons, and potentially non-clinical testing (e.g., bench testing, animal studies, or limited human clinical data typical for device safety and efficacy demonstration for systems of this type) that are not detailed here. Data provenance (country of origin, retrospective/prospective) is therefore not mentioned.

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

• Not applicable / Not provided: Since there's no defined "test set" for performance evaluation in the AI/ML sense, expert-established ground truth information is not present. The assessment relates to the system's ability to produce images suitable for a human clinician's visual assessment, rather than an AI's interpretation.

4. Adjudication Method for the Test Set:

• Not applicable / Not provided: No test set or corresponding adjudication method is described.

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

• No: This type of study is typically conducted for AI/ML diagnostic devices to assess how AI assistance impacts human reader performance. This device is an imaging system, not an AI diagnostic tool, so an MRMC study is not relevant here.

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

• No: This concept is not applicable as the SPY system itself is an imaging tool designed for human interpretation, not an automated algorithm for standalone diagnosis.

7. The Type of Ground Truth Used:

• Not applicable / Not provided: For a medical device like an imaging system, the "ground truth" often relates to its ability to accurately visualize anatomical structures or physiological processes as confirmed by established clinical methods, but the 510(k) summary does not detail the specific studies or ground truth methodologies. The assessment focuses on the system's ability to aid a clinician in "visual assessment."

8. The Sample Size for the Training Set:

• Not applicable / Not provided: There is no "training set" in the context of AI/ML algorithm development for this device.

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

• Not applicable / Not provided: As above, no training set or associated ground truth establishment is relevant to this device submission.

In summary: The provided document is a 510(k) summary for an imaging system, not an AI/ML device. Therefore, the requested information points related to AI/ML device evaluation (like test/training sets, ground truth, expert adjudication, MRMC studies, standalone performance, and quantified acceptance criteria) are not present or applicable. The FDA clearance is based on the device's substantial equivalence to previously cleared predicate devices for its intended use as an intraoperative imaging tool.

Ask a specific question about this device

For use in intra-operative visual assessment of the coronary vasculature and bypass grafts during coronary artery bypass (CABG) surgery.

The SPYTM Intra-operative Imaging System: SP2000 is indicated for use for intraoperative visual assessment of the coronary vasculature and grafts during CABG surgery.

The SPYTM system provides the surgeon with the capability to view, record and replay fluorescent images of blood vessels and bypass grafts of the heart. A laser light source is used to illuminate the heart surface. Indocyanine Green (ICG) is injected intravenously through the central venous line, bypass pump or cardioplegia line and, while coursing through the coronary arteries and grafts, the absorption of laser light causes excitation of the dye followed by emission of infrared energy. The result is a fluorescent image of the coronary vasculature. A CCD camera captures the image. These images are used to evaluate the integrity of the coronary vasculature and bypass grafts.

The provided text describes the SPY™ Intra-operative Imaging System: SP2000, its intended use, and the testing performed to demonstrate its safety and effectiveness. However, it does not specify discrete acceptance criteria in a quantitative format (e.g., minimum sensitivity or specificity targets) with corresponding reported device performance metrics in a table. It instead outlines the types of testing and general conclusions on safety and effectiveness, and equivalence to predicate devices, without detailed performance data against specific, quantifiable criteria.

Therefore, many of the requested details about acceptance criteria, specific performance metrics, sample sizes for test sets, expert involvement, and ground truth establishment cannot be fully extracted from the provided document. The document focuses more on regulatory compliance, safety, and equivalence rather than a detailed performance study with explicit acceptance criteria.

Below is an attempt to address the prompts based on the available information:

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

The document does not explicitly define quantitative acceptance criteria for device performance (e.g., specific sensitivity, specificity, accuracy thresholds). Instead, the "Testing" section outlines general requirements and conclusions from in vitro and in vivo studies. The performance is primarily reported as meeting safety standards and achieving image quality equivalent to radiographic angiography.

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

• Sample Size for Test Set: The document states "human experience in 950 CABG procedures were completed to demonstrate safety and effectiveness." This indicates a substantial sample size from clinical use.
• Data Provenance: The document does not specify the country of origin of the data. It also does not explicitly state whether the human experience was collected retrospectively or prospectively, but "human experience" in conjunction with demonstrating safety and effectiveness could encompass a variety of observational or trial-like data collection methods. Given the context of a 510(k) summary, it's likely a combination of clinical observations and possibly some form of prospective data collection, but this is not explicitly stated.

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 text refers to "human experience" and the "image quality... was equivalent to radiographic angiography," implying expert assessment of images. However, it does not detail how many experts were involved, their qualifications, or their role in establishing ground truth for the 950 CABG procedures.

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

This information is not provided in the document.

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

• MRMC Study: An MRMC comparative effectiveness study is not mentioned. The document describes "intra-operative visual assessment" and "image quality... was equivalent to radiographic angiography," but it does not detail any study designed to compare human reader performance with and without the device, or against an AI, as the device itself is an imaging system, not an AI-assisted diagnostic tool.
• Effect Size of AI assistance: Not applicable as the device is an imaging system and not designed with AI assistance, nor is an AI component mentioned.

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

The device is an imaging system (hardware and associated software for image acquisition and display), not an algorithm for standalone diagnosis. Therefore, a "standalone algorithm only" performance study is not applicable in this context. The SPY™ system is designed for "intra-operative visual assessment," implying human-in-the-loop use.

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

The document primarily relies on the following for demonstrating effectiveness:

• Equivalence to Radiographic Angiography: This suggests a comparison against an established imaging modality, likely interpreted by experts.
• Clinical Observation/Experience: "Human experience in 950 CABG procedures" implies direct clinical observation and assessment by surgeons regarding the system's ability to visualize vasculature and grafts.
• Absence of Adverse Events/Safety Measures: Lack of thermal damage, ECG/pressure changes, or cellular/organ effects were key safety "ground truths."

While expert assessment is strongly implied for "image quality" and "visual assessment," explicit details on how ground truth for vessel patency or graft integrity was formally established (e.g., through a gold standard like pathology or long-term clinical outcomes) are not detailed. It appears to be based on the established clinical utility and visual confirmation during procedures.

8. The sample size for the training set

This information is not provided. The SPY™ system is an imaging device, not an AI model that typically has a distinct training set. The "human experience" of 950 CABG procedures served as part of the validation/testing to demonstrate safety and effectiveness.

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

Not applicable, as the device is not an AI model trained on a dataset with established ground truth in the conventional sense. The "training" for such a system would involve engineering and physical testing, not data labeling for an algorithm.

Ask a specific question about this device