Search Results

The Clarifi™ Imaging System is indicated for use to determine oxygenation levels in superficial tissues for patients with potential circulatory compromise.

The Clarifi Imaging System is intended for use by healthcare professionals as a non-invasive tissue oxygenation measurement system that reports an approximate value of:

• Oxygen saturation (StO2) ●
• Oxyhemoglobin (HbO2), and .
• Deoxyhemoglobin (HbR) .
  in superficial tissue.

The Clarifi Imaging System is a noninvasive non-contact imaging device used to visualize spatially-resolved functional parameters of biological tissue. The Clarifi Imaging System shares fundamental principles with other oximeters and tissue oxygenation measurement systems. Tissue oximetry exposes tissue to optical radiation of known wavelengths and captures the remitted light or reflectance. The remitted-back scattered light is then used to calculate the tissue constituents. Spectral analysis is used to measure tissue oxygen saturation (StO2), oxyhemoglobin (HbO2), deoxyhemoglobin (HbR), and total hemoglobin (HbT: superficial and subsurface hemoglobin) and determine tissue optical properties (absorption and scattering). The Clarifi Imaging System uses both visible (VIS) and near-infrared (NIR) wavelengths; other systems that also measure oxygenation levels in superficial tissue may use only VIS or NIR wavelengths. The analysis for Clarifi is based on principles of multi-spectral imaging and Spatial Frequency Domain Imaging (SFDI).

The Clarifi system displays two-dimensional color-coded images of tissue oxygenation of the scanned surface and reports hyperspectral tissue oxygenation measurements for selected tissue regions.

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

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly state acceptance criteria in a quantitative table format. Instead, it focuses on demonstrating substantial equivalence to a predicate device (Ox-Imager CS - K153426) based on similar performance and design. The performance data section describes verification testing, which implies internal acceptance limits were met, but these limits are not explicitly listed as "acceptance criteria."

However, we can infer some performance aspects from the "Performance Testing" section:

2. Sample Size for the Test Set and Data Provenance

• Sample Size for Test Set: Not explicitly stated as a number of patients or cases. The performance testing was done on "NIST-traceable Spectralon standards" and "reflectance targets," which suggests a benchtop test rather than a clinical study with patient samples.
• Data Provenance: The testing was conducted as "bench performance data... under design validation 21 CFR 820.30(g)." This indicates internal laboratory testing, not patient data from a specific country or setting.

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

• Number of Experts: Not applicable. The "ground truth" for the bench performance tests was based on "NIST-traceable Spectralon standards" and physical "reflectance targets," which have known properties, not expert interpretation.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. The performance testing was based on direct measurements against established physical standards and device specifications, not on expert adjudication of ambiguous cases.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• MRMC Study Done? No. The submission focuses on demonstrating substantial equivalence through technical and bench performance comparisons to a predicate device, not through a comparative effectiveness study with human readers.

6. Standalone Performance (Algorithm only without human-in-the-loop performance)

• Standalone Performance Done? Yes, effectively. The reported performance data (linearity, precision, stability, image homogeneity, SNR) are measurements of the device's intrinsic capabilities and performance characteristics as a standalone system (Clarifi Imaging System) when compared against physical standards and its predicate device. There is no mention of a "human-in-the-loop" component for these specific validation tests.

7. The Type of Ground Truth Used

• Type of Ground Truth: For the performance tests, the ground truth was based on physical standards (NIST-traceable Spectralon standards) and known properties of reflectance targets.

8. The Sample Size for the Training Set

• Sample Size for Training Set: The document does not describe a "training set" in the context of machine learning or AI models. The Clarifi Imaging System uses "principles of multi-spectral imaging and Spatial Frequency Domain Imaging (SFDI)" and "spectral model-based analysis." This indicates a physics-based model rather than a data-driven machine learning model that would typically require a training set. Therefore, this concept is not applicable as described in the provided text.

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

• How Ground Truth for Training Set Was Established: Not applicable, as there is no mention of a training set for a machine-learning model. The system relies on physical principles and models to determine oxygenation levels.

Ask a specific question about this device

The Ox-Imager CS™ is indicated for use to determine oxygenation levels in superficial tissues for patients with potential circulatory compromise.

The Ox-Imager CSTM is intended for use by healthcare professionals as a noninvasive tissue oxygenation measurement system that maps value of: oxygen saturation, oxy-hemoglobin, and deoxy-hemoglobin into 2D/3D visual presentations. The Ox-Imager™ CS is a non-contact imaging device to visualize spatially-resolved optical and functional parameters of biological tissue. The Ox-Imager CS shares fundamental principles with other oximeters and tissue oxygenation measurement systems. Spectral analysis is used to measure oxygen saturation (StO2), oxyhemoglobin (HbO2), deoxyhemoglobin (HbR) and determine tissue optical properties (absorption and scattering) using specific LED wavelengths and patterns. The Ox-Imager CS uses both visible (VIS) and near infrared (NIR) wavelengths; other systems that also measure oxygenation levels in superficial tissue may use only VIS or NIR wavelengths. Tissue oximetry exposes tissue to optical radiation of known wavelengths and captures the remitted light or reflectance. The remitted back scattered light is then used to calculate the tissue constituents mentioned above based on principles of multispectral imaging and Spatial Frequency Domain Imaging (SFDI).

The provided document is a 510(k) summary for the Ox-Imager CS device, seeking clearance based on substantial equivalence to a predicate device, the Hypermed, Inc. OxyVu-1 System. This type of document typically focuses on demonstrating equivalence rather than establishing new acceptance criteria or providing in-depth performance studies with detailed statistical analysis against pre-defined thresholds.

Therefore, the information available is primarily focused on demonstrating equivalence and device functionality rather than specific acceptance criteria thresholds for a standalone performance study.

Here's an analysis based on the provided text:

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

The document does not explicitly state quantitative acceptance criteria (e.g., specific accuracy thresholds, sensitivity, specificity) for the Ox-Imager CS device's performance. Instead, the performance studies aim to demonstrate substantial equivalence to the predicate device and show that the device measures physiological changes as expected.

The key performance finding is:
"It was demonstrated that the predicate OxyVu-1 and the Ox-Imager CS recover highly correlated values of StO2 during the time course of a vascular occlusion test and that both devices measured a statistically significant decrease in tissue oxygen saturation (StO2) after circulatory compromise."

This implies a qualitative "acceptance criterion" of:

• Highly correlated values of StO2 between the Ox-Imager CS and the predicate OxyVu-1 during a vascular occlusion test.
• Statistically significant decrease in tissue oxygen saturation (StO2) measured by both devices after circulatory compromise.

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: The document does not specify the exact sample size (number of subjects/cases) for any of the clinical, pre-clinical, or benchtop studies. It mentions "a clinical study," "a pre-clinical study in rabbits," and "a blood phantom desaturation study."
• Data Provenance: The document does not specify the country of origin for the data or whether the studies were retrospective or prospective, although clinical and pre-clinical studies are typically prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This section is not applicable in the traditional sense for this device. The "ground truth" for an oximeter is primarily physiological measurements. The studies do not describe a process of expert review or consensus for establishing ground truth, as would be common in image-based diagnostic AI. Instead, the ground truth is established through:

• Physiological changes: Vascular occlusion (inducing circulatory compromise) acts as a physiological "ground truth" stimulus.
• Reference measurements: Co-oximeter values (SaO2/SvO2 from blood draws) and transcutaneous oxygen measurements (tcpO2) serve as reference "ground truth" data points against which the Ox-Imager CS measurements are correlated.
• Expected values: For the blood phantom study, the pO2/StO2 curves were compared to "expected StO2 values."

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

Not applicable. As noted above, the "ground truth" is based on physiological changes and objective reference measurements, not expert review requiring adjudication.

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

No, an MRMC comparative effectiveness study was not done. The Ox-Imager CS is described as a measurement device that provides objective values and images of oxygenation levels, not an AI-assisted diagnostic tool that aids human readers in interpreting images. Therefore, the concept of "human readers improve with AI vs without AI assistance" does not apply to this device's reported evaluation.

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

Yes, the studies evaluate the standalone performance of the Ox-Imager CS device as a measurement tool. For example:

• The comparison between Ox-Imager CS and OxyVu-1 during vascular occlusion.
• The correlation of Ox-Imager CS StO2 with pO2 in blood phantoms.
• The correlation of Ox-Imager CS StO2 with co-oximeter values (SaO2/SvO2) in rabbits.
• The comparison of Ox-Imager CS StO2 with tcpO2 in a clinical study.

These are all assessments of the device's inherent measurement capabilities.

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

The ground truth for evaluating the Ox-Imager CS was based on:

• Physiological manipulation: Inducing a state of circulatory compromise (vascular occlusion) to predictably change tissue oxygenation.
• Reference standards/measurements:
  • The predicate device (Hypermed OxyVu-1) was used for direct comparison of StO2 values.
  • Co-oximeter values (SaO2/SvO2 from blood draws in the rabbit study).
  • Transcutaneous oxygen measurements (tcpO2 in one clinical study).
  • Expected StO2 values derived from pO2 curves for the blood phantom study.

8. The sample size for the training set

The document does not describe a "training set" as would be relevant for a machine learning or AI model. The Ox-Imager CS uses "spectral analysis" and "model-based analysis of light" based on principles of multispectral imaging and Spatial Frequency Domain Imaging (SFDI). These are physics-based models rather than data-driven machine learning models that require a distinct training set. The device's "training" would be more akin to software calibration or model development based on established optical properties and physiological principles, rather than a dataset of labeled clinical images.

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

Not applicable, as there is no mention of a traditional "training set" with ground truth labels in the context of machine learning. The device's underlying models are based on physical and biological principles.

Ask a specific question about this device