Search Results
Found 1 results
510(k) Data Aggregation
(316 days)
Static Vessel Analyzer (SVA) with VesselMap2 is intended to capture, display, store, and manipulate images of the eye, especially the retina area, as well as surrounding areas, to aid in diagnosing or monitoring diseases of the eye that may be observed and photographed. Specifically, the VesselMap2 software is intended to be used for semiautomated measurement and calculation of the retinal artery/vein diameter ratio.
The IMEDOS SVA unit is designed as a complete Fundus Imaging system or the software can be sold separately as a standalone product. The SVA software consist of two components - VisualIS, an imaging software for capture, display, storage and manipulation of images of the eye and VesselMap2, an add-on for enhanced analysis of retina images. VisualIS captures the images which are provided by the fundus camera and the connected digital image sensor. Together with an image set the data of the patient are recorded and stored. The complete examination can be stored and opened for follow-up examination purposes. The add-on VesselMap2 offers a semi-automated measurement for Arterial -- Venous Ratio of retinal vessels. The software allows the user to select veins and arteries. Vessel diameters are estimated by the software and the ratio of the analyzed arteries to veins is calculated. The image is not altered in any way during this calculation.
The provided text describes the IMEDOS GmbH's Static Vessel Analyzer (SVA) and its VesselMap2 software. The information focuses on a method comparison study between the semi-automated VesselMap2 software and a manual method for determining arterial-venous ratios.
Here's a breakdown of the requested information based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative "acceptance criteria" with specific thresholds (e.g., "accuracy > 90%"). Instead, it describes performance in terms of agreement, repeatability, and reproducibility, and the absence of certain biases. The reported device performance is presented as conclusions from the study.
| Acceptance Criteria (Implied) | Reported Device Performance (VesselMap2) |
|---|---|
| Agreement with manual method | "Agreement between manual and semi-automatic (VesselMap2) retinal vessel analysis, without any indication of statistically significant differences between methods." |
| Repeatability (Intragrader) | "Smaller intragrader variability for the semi-automatic method (VesselMap2) than for the manual method." |
| Reproducibility (Intergrader) | "Smaller [...] intergrader variability (reproducibility) for the semi-automatic method (VesselMap2) than for the manual method." |
| Absence of reader-to-reader bias | "In the manual method, a systematic bias between the two graders exists, which is not the case in the semi-automatic method. Thus, the comparison study demonstrated that the VesselMap software does not introduce reader-to-reader bias." |
| Intravisit Reproducibility | "Appropriate intravisit [...] reproducibility for the semi-automatic method." |
| Intervisit Reproducibility | "Appropriate [...] intervisit reproducibility for the semi-automatic method." |
| Low device-associated variability | "The visit-to-visit variability (whether for manual or semi-automated analysis) was shown to be much higher than the variability in results associated with the device." |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: The document does not specify the exact number of retinal images or patients used in the method comparison study. It only mentions "representative retina images."
- Data Provenance: Not explicitly stated (e.g., country of origin, retrospective or prospective).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
The document mentions "two graders" in the context of comparing manual methods and intergrader variability. It does not provide their specific qualifications (e.g., "radiologist with 10 years of experience"). It's implied these graders performed the manual measurements against which the semi-automatic method was compared.
4. Adjudication Method for the Test Set
The document does not describe an explicit adjudication method (like 2+1 or 3+1) for establishing ground truth. Instead, it describes a comparison between manual measurements performed by graders and the semi-automatic software.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Its Effect Size
A formal MRMC comparative effectiveness study, comparing human readers with AI assistance versus without AI assistance, is not explicitly described. The study compared a semi-automatic method (VesselMap2) to a purely manual method, highlighting the improved repeatability and reproducibility of the semi-automatic method and the absence of reader-to-reader bias. It does not quantify an "effect size of how much human readers improve with AI vs. without AI assistance" in terms of observer performance but rather demonstrates the device's inherent performance characteristics.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
The VesselMap2 is described as a "semi-automated measurement" tool where "the software allows the user to select veins and arteries." This indicates human-in-the-loop involvement, so a purely standalone (algorithm-only) performance evaluation is not detailed for the final output (arterial-venous ratio). The comparison performed was between this semi-automated approach and a manual approach.
7. The Type of Ground Truth Used
The "ground truth" for the test set was effectively the manual method of determining arterial-venous ratios performed by human graders, against which the "semi-automated calculation" of the VesselMap2 software was compared. The study aimed to show agreement with this established manual method and improvements in consistency.
8. The Sample Size for the Training Set
The document does not provide any information about a dedicated training set or its sample size. The focus is on the performance of the software in a comparison study.
9. How the Ground Truth for the Training Set Was Established
Since no training set is mentioned, there is no information on how its ground truth would have been established.
Ask a specific question about this device
Page 1 of 1