(679 days)
UltraSightHD™ with ImageSense™ is a digital colposcope designed to image the cervix and lower genital tract under illumination and magnification. Colposcopy is indicated for women with an abnormal Pap smear in order to affirm normality or detect abnormal appearances consistent with neoplasia, often with directed biopsy.
OpacityViewer™ is an ImageSense™ digital filter for displaying areas of acetowhitening. It is a tool that should NOT be used as a substitute for a thorough colposcopic evaluation.
The UltraSight HD™ Digital Colposcopy System with ImageSense™ Technology is a digital colposcope designed to image the cervix and lower genital tract under illumination and magnification.
ImageSense™ is an image processing suite available for the UltraSightHD™ digital colposcope. The ImageSense™ suite consists of two different modules: UltraGreen™ filter and Acetownite OpacityViewer™.
The UltraGreen™ filter provides the user with greater contrast than an unprocessed image. UltraGreen™ is displayed as a reqular full color image, and is available to be used on any stillframe image displayed in the Review Hi-Res Imagery, View ImageSense Results, and Annotate lmage modes.
The Acetowhite OpacityViewer™ compares two images, one taken prior to the application of Acetic Acid and an additional image taken 60 seconds after the application of Acetic Acid, otherwise known as the pre- and post- Acetic Acid images. The Acetowhite OpacityViewer™ then generates a difference map that shows the extent of white difference between the two images, which is indicated by a gradient color scale ranging from blue (no measurable difference between the images), through white (some difference) and vellow (moderate difference), to red (large difference). Red, on the difference map, indicates only the greatest color difference between the images.
The illumination and optical design of the device allow the user to capture high resolution digital images. The optical subsystem is augmented by integrated image quality assessment algorithms. ensuring that focused and balanced-contrast images are acquired. Two liquid crystal displays (LCDs) provide video display and user interface information. The software includes functionality for annotating, filtering and storing the images on external PACS servers via the DICOM protocol.
The provided text describes the UltraSightHD™ Digital Colposcopy System with ImageSense™ Technology. However, it does not include specific acceptance criteria with numerical targets or detailed results of a study designed to prove the device meets such criteria.
The document states: "Test results indicate that the device meets the performance specifications." and "Appropriate risk analysis-driven product testing was conducted to evaluate conformance to product specification and substantial equivalence to the predicate device." However, the specific performance specifications and the quantitative results proving conformance are not detailed within the provided text.
Here's an analysis based on the information that is available, and what is explicitly stated as not performed:
1. A table of acceptance criteria and the reported device performance
No explicit table of acceptance criteria with numerical targets is provided in the document. The document lists areas of testing but does not offer specific criteria or quantitative results against them.
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Not Explicitly Stated (e.g., x% resolution, y distortion) | "Test results indicate that the device meets the performance specifications." (General statement, no specific data provided) |
| Electrical Safety | Conformed |
| Electromagnetic Compatibility | Conformed |
| Optical Radiation | Conformed |
| Resolution | Conformed (Specifications not detailed) |
| Distortion | Conformed (Specifications not detailed) |
| Illumination Variance | Conformed (Specifications not detailed) |
| Image Registration | Validated by clinical studies |
| Color Difference Map Range | Conformed (Specifications not detailed) |
| Mechanical Subsystem (Ease of movement, Orientation motion, Settling time, Affect of internal vibration, Height adjustment) | Conformed |
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
- Clinical Studies: The document explicitly states: "The only clinical studies conducted were run to validate image registration."
- Sample Size for Image Registration Validation: The sample size for this validation is not specified in the provided text.
- Data Provenance: The provenance of data for the image registration validation is not specified.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable, as no detailed clinical study is described where experts established ground truth for a test set to evaluate the ImageSense™ features (e.g., OpacityViewer™). The clinical studies were limited to "image registration," and details are missing.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
Not applicable, as no detailed clinical study is described that involved multiple readers or adjudication for establishing ground truth for the test set.
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, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The document explicitly states: "No clinical studies were conducted to demonstrate improved clinical performance using the new OpacityViewer digital filter."
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This is difficult to ascertain directly from the provided text for the ImageSense™ features. The "ImageSense™ Technology" (UltraGreen™ filter and Acetowhite OpacityViewer™) are described as image processing tools available to the user, suggesting they are meant to be used with a human in the loop. The document states "OpacityViewer™ is a tool that should NOT be used as a substitute for a thorough colposcopic evaluation," further emphasizing the human's role.
The clinical studies were only to validate "image registration," which is a technical aspect of the device's image processing rather than a standalone clinical performance study of the ImageSense™ diagnostic features.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- For the image registration validation, the type of ground truth is not specified.
- For the ImageSense™ features (UltraGreen™ and OpacityViewer™), no clinical studies were performed to establish ground truth for their "improved clinical performance." The OpacityViewer creates a "difference map that shows the extent of white difference between the two images," which is an algorithmic output, not a ground truth derived from expert consensus, pathology, or outcomes data in the context of clinical effectiveness.
8. The sample size for the training set
Not applicable. The document describes a medical device with image processing features, not a machine learning model that would require a distinct "training set" in the conventional sense for a clinical algorithm.
9. How the ground truth for the training set was established
Not applicable, as there is no mention of a training set for a machine learning model in the context of the ImageSense™ features.
§ 884.1630 Colposcope.
(a)
Identification. A colposcope is a device designed to permit direct viewing of the tissues of the vagina and cervix by a telescopic system located outside the vagina. It is used to diagnose abnormalities and select areas for biopsy. This generic type of device may include a light source, cables, and component parts.(b)
Classification. Class II (special controls). The device, when it is a standard colposcope (or colpomicroscope) that uses only a white light source, does not use filters other than a green filter, does not include image analysis software, and is not smartphone-based, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 884.9.