(203 days)
The CooperSurgical Digital Colposcopy System combines a standard colposcope with a computer-based Digital Documentation System. The colposcope is intended to permit direct magnified viewing of the tissues of the vagina, cervix and external genitalia in order to diagnose abnormalities and select areas for biopsy. The Digital Documentation System is intended to provide documentation of the image in the field of view of the colposcope. The image can be viewed on a color monitor, printed on a color printer, or archived for storage and subsequent retrieval.
The colposcope portion of the CooperSurgical Digital Colposcopy System consists of a stereo microscope with a halogen light source and optional green filter, and is mounted on a mobile base. The Digital Documentation System consists of a CCD camera, an embedded computer, an LCD monitor, a "palm-mouse" pointing device, an optional keyboard, and an optional printer. The functional requirements of the Digital Documentation System include:
- Storing digital images for viewing during the colposcopy exam, and for printing and/or later review
- Storing textual information about a patient's medical history related to colposcopy
- Storing textual information about observations seen during a colposcopy examination
- Printing a colposcopy report that integrates images and textual information.
- Implementation of the software green filter.
- A patent-pending procedure to reduce the amount of distracting glare which is often present in pictures of the cervix and other wet tissue.
The provided document (K972636, P192, and K972630) does not contain information regarding traditional acceptance criteria, performance studies, or clinical validation data often associated with modern medical device submissions, especially for AI/ML-driven devices. This is likely due to the nature and vintage of the submission, which pre-dates many requirements for sophisticated performance evaluations.
The CooperSurgical Digital Colposcopy System, described in a 510(k) submission from 1997, is essentially a colposcope with an integrated digital documentation system. It is not an AI/ML-driven diagnostic or assistive device that would have quantifiable performance metrics like sensitivity, specificity, accuracy, or effect sizes for human readers.
Instead, its "acceptance criteria" and "study" are focused on demonstrating substantial equivalence to predicate devices. The performance of the device is implicitly tied to its ability to perform its stated functions, such as image acquisition, storage, and display, comparable to existing devices, rather than achieving specific diagnostic thresholds.
Here's an analysis based on the provided text, addressing the points where information is available and noting where it is absent for a device of this type and era:
1. A table of acceptance criteria and the reported device performance
No explicit acceptance criteria with numerical targets (e.g., sensitivity > X%, specificity > Y%) are stated in the document, nor are there reported device performance metrics in that context. The "performance" is described in terms of functional capabilities and comparison to predicate devices.
| Acceptance Criteria (Implied/Functional) | Reported Device Performance (as described) |
|---|---|
| Permit direct magnified viewing of tissues of the vagina, cervix, and external genitalia. | The colposcope portion consists of a stereo microscope with a halogen light source and optional green filter, mounted on a mobile base, enabling direct magnified viewing for diagnosis and biopsy selection. |
| Provide documentation of the image in the field of view of the colposcope. | The Digital Documentation System provides this function. |
| Allow image viewing on a color monitor. | The system includes an LCD monitor for image viewing. |
| Allow image printing on a color printer. | The system allows for printing images on an optional color printer. |
| Allow archiving for storage and subsequent retrieval. | The system is intended to archive images for storage and retrieval. |
| Store digital images for viewing during exam, printing, and later review. | The Digital Documentation System fulfills this requirement. |
| Store textual information about patient medical history related to colposcopy. | The Digital Documentation System fulfills this requirement. |
| Store textual information about observations seen during colposcopy examination. | The Digital Documentation System fulfills this requirement. |
| Print a colposcopy report integrating images and textual information. | The Digital Documentation System fulfills this requirement. |
| Implement a software green filter. | The Digital Documentation System includes implementation of a software green filter. |
| Reduce distracting glare in images of the cervix and other wet tissue. | The Digital Documentation System includes "A patent-pending procedure to reduce the amount of distracting glare which is often present in pictures of the cervix and other wet tissue." |
| Substantially equivalent to predicate colposcopes and video colposcopes in intended use and technology. | The device is described as substantially equivalent to the Leisegang Model 1D Colposcope (K940094) and Welch Allyn Model 88000 and 89000 Video Colposcopes (K955635), sharing the same intended purpose of direct viewing and imaging of tissues to diagnose abnormalities. |
2. Sample size used for the test set and the data provenance
The document does not describe a "test set" in the context of a clinical performance study with human subjects or retrospective data. The evaluation for substantial equivalence would have been based on technical specifications, functional testing, and comparison to predicate devices, not, for example, a dataset of patient images.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. No "ground truth" establishment by experts for a test set is described, as it's not an AI/ML diagnostic device requiring such validation. The primary diagnostic function (viewing tissues to diagnose abnormalities) remains with the physician using the colposcope.
4. Adjudication method for the test set
Not applicable, as no test set requiring ground truth adjudication is mentioned.
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 such study was conducted or mentioned. The device is a "Digital Colposcopy System," which implies an enhancement in documentation and viewing capabilities, not an AI-assisted diagnostic tool that would demonstrate improvement in human reader performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. The device is not an algorithm-only diagnostic. It is a system intended to be used by a healthcare professional (human-in-the-loop) for visual examination and documentation.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Not applicable. Ground truth, in the context of diagnostic accuracy, is not mentioned because this device's validation focuses on functional equivalence and safety, not on its own diagnostic accuracy. The physician's diagnosis (potentially confirmed by pathology from biopsies) constitutes the ground truth for patient management, but the device itself is a tool for the physician.
8. The sample size for the training set
Not applicable. There is no mention of a training set, as the device does not employ machine learning or AI models that require data for training.
9. How the ground truth for the training set was established
Not applicable, as no training set is mentioned.
§ 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.