(13 days)
EyeSuite Imaging is a software program intended for use for controlling digital imaging devices and for acceptance. transfer, display, storage and digital processing of documentational ophthalmic images and videos, acquired from computerized diagnostic instruments, through direct connection or through networks.
EyeSuite Basic is a patient and examination management system, acting as a base and communication platform for other EyeSuite software components.
EyeSuite Imaging is a software used by eye care professionals together with imaging systems on Haaq-Streit slit lamps or other devices. EveSuite Imaging requires a computer running Microsoft Windows in one of the following versions:
- Windows XP, SP3 (32 Bit) ●
- Windows Vista, SP2 (32 and 64 Bit) .
- . Windows 7. SP1 (32 and 64 Bit)
- Windows 8 and 8.1 (32 and 64 Bit) .
A slit lamp is an instrument consisting of a light source that can be focused to shine a thin sheet of light into the eye. It is used in conjunction with a biomicroscope. The lamp facilitates an examination of the anterior segment, or frontal structures and posterior segment, of the human eye. With an imaging system a two dimensional image or video of what is seen through the biomicroscope can be recorded into widely used data formats, such as TIFF or JPEG in case of still images or MJPEG in case of a video. These records can be used for documentational purpose or to explain findings to the patient. It is optionally possible to connect the software to a DICOM PACS for storing the recorded image data.
EyeSuite Imaging allows the user to control the Haag-Streit imaging devices attached to the slit lamp or other devices, enables recording of images or videos, allows to view, modify and store the results together with accompanying information such as patient data, information on camera settings or notes of the examiner. The examiner may also highlight significant image features by using the provided draw and measure tools that allow to add predefined overlays, pixel measurements or angle measurements in the image plane. The software is not able and not intended to provide any diagnosis, but it helps the user to examine the visible structures of the eye and enables him to present and store his findings.
EyeSuite Imaging is a software application which is part of the Haag-Streit EyeSuite software product family that is licensed to customers of Haag-Streit Imaging devices. All imaging data acquisition, processing or consistency-check related features are provided by the EyeSuite Imaging Extension component and the EyeSuite Imaging Viewer component. Standard elements such as user management, patient management. database connections, basic settings, installation and backup routines are provided by the EyeSuite Basic component. The architectural decision of isolating standard features into the EyeSuite Basic component was made to reuse these features in other EyeSuite software products.
The imaging modules supported by EyeSuite Imaging are the Haag-Streit IM900 and the Haag-Streit CM900. The EyeSuite Imaging software allows to take control of camera features such as exposure time, camera gain or white balance settings. The release modules supported by EyeSuite Imaging are the Haag-Streit RM01, the Haag-Streit RMX01 and the Haag-Streit Footswitch. These supplementary devices are registered accessory parts to the class II slit lamp microscope (FDA clearance number K100202),
The provided document is a 510(k) summary for the EyeSuite Imaging software. It describes the device's intended use and compares it to predicate devices to establish substantial equivalence. However, it explicitly states that the device is not intended to provide any diagnosis and therefore no clinical or non-clinical performance data was necessary to verify its safety and efficacy in terms of diagnostic performance. The validation primarily focuses on software functionality and compliance with standards.
Therefore, the requested information regarding acceptance criteria for diagnostic performance, details of a study proving such criteria are met, sample sizes for test/training sets, ground truth establishment, expert involvement, or MRMC studies for diagnostic improvement are not applicable or available in this document.
Here's a breakdown of the requested information based on the provided text, highlighting what is (and isn't) present:
1. A table of acceptance criteria and the reported device performance:
Since the device does not provide diagnosis, there are no diagnostic performance acceptance criteria (e.g., sensitivity, specificity, accuracy) or reported performance metrics for diagnostic tasks. The document focuses on functional performance and compliance with software standards.
| Acceptance Criteria (Functional/Compliance) | Reported Device Performance |
|---|---|
| Software Functional Requirements | |
| Capture Imaging Data (Test Case 006) | Performed as intended |
| Drawing Overlays (Test Case 003) | Performed as intended |
| Quantities and units (Test Case 017) | Performed as intended |
| Image Evaluation (Test Case 007) | Performed as intended |
| Design Verification (Test Case 000) | Met requirements |
| Instructions for Use (Test Case 024) | Met requirements |
| DICOM Compliance | |
| DICOM PS 3:2011 | Compliant |
| JPEG Compression Compliance | |
| IEC 10918-1:1994 + Technical Corrigendum 1:2005 (Test Case U40) | Compliant |
| Risk Management | |
| ISO 14971:2007 + Corrected version 2007-10-01 | Complied with |
| IEC 62366:2007 | Complied with |
| Software Life Cycle Processes | |
| IEC 62304:2006 | Complied with |
| Electrical Safety (for integrated system, not just software) | |
| IEC 60601-1:2005 + A1:2012 | Complied with |
The study that proves the device meets these criteria is the "Software validation testing and image capture testing" mentioned in section 11. Specifically, the test cases listed (e.g., 1182_1021525_06011_Test Case 006) are the documented evidence of this validation.
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective):
Not applicable/provided. Since the performance validation is focused on software functionality and image handling rather than diagnostic accuracy, specific "test sets" of patient images for diagnostic evaluation, their sample size, or provenance of patient data are not detailed. The testing described appears to be internal software validation.
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):
Not applicable. As the software does not provide diagnosis, there's no "ground truth" to establish for diagnostic purposes in the context of patient data. The validation focused on verifying software behavior and compliance with specifications.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
Not applicable. No diagnostic adjudication method is described as the software does not perform diagnosis.
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. The document explicitly states: "As the software is not able and not intended to provide any diagnosis, no clinical performance data was necessary to verify the safety and efficacy of the device." Therefore, no MRMC study for diagnostic effectiveness or human reader improvement was conducted or reported.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Yes, in a sense, the software validation testing documented in section 11 (e.g., "Software validation testing and image capture testing were performed on the EyeSuite Imaging Software") represents the standalone performance evaluation of the software's specified functionalities (capture, display, storage, processing, control). However, this is for functional performance, not diagnostic performance.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
For the functional software validation, the "ground truth" would be the expected behavior defined by the software's design specifications and the requirements of the standards it aims to comply with. For example, for image capture, the ground truth is that the captured image accurately reflects the input from the device. For DICOM compliance, the ground truth is adherence to the DICOM standard. This is not patient-specific diagnostic ground truth.
8. The sample size for the training set:
Not applicable/provided. This device is not described as an AI/ML diagnostic algorithm that would require a "training set" of data in the common sense. It's an image management and control software.
9. How the ground truth for the training set was established:
Not applicable, as there is no mention of a training set or an AI/ML model for diagnostic purposes.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).