(58 days)
The Retina Workplace is a FORUM application intended for processing and displaying fundus image and optical coherence tomography data. It is also intended for generating reports that contain results from optical coherence tomography and fundus photography.
The Retina Workplace uses CIRRUS algorithms and normative databases as a quantitative tool for the comparison of macular thickness data to a database of normal subjects. It supports the processing and displaying of CIRRUS OCT-Angiography data, which is indicated as an aid in the visualization of vascular structures of the retina and choroid.
The Retina Workplace is intended to aid trained healthcare professionals in the detection, monitoring and management of ocular diseases including, but not limited to, macular edema, diabetic retinopathy and age-related macular degeneration.
The Retina Workplace is designed in conjunction with the FORUM PACS system, which support clinically focused client workplaces to aid the optometric and ophthalmology clinicians with the processing, display, review, management, and storage of digital data contained in patient records. The Retina Workplace is software application of FORUM Archive and Viewer PACs workplace. FORUM is a software system designed for storage, processing, and review of images, videos, and reports originating from computerized diagnostic instruments or electronic documentation systems over a network. The Retina Workplace is connected to the FORUM server via an internal interface. The Retina Workplace retrieves CIRRUS OCT exam data and fundus images from the FORUM server. The Retina Workplace is intended to support the physician with a clinically focused workplace for the retina by using the imported OCT exam data from CIRRUS HD-OCT and CIRRUS Photo to report and display the results.
The Retina Workplace (version 2.5) is the latest generation device in the Retina Workplace series. The version of the 2.5 that is the subject of this submission is a modified version of the Retina Workplace (version 2.0) cleared under K170638.
Like its predecessors, Retina Workplace version 2.5 is designed to process and display CIRRUS OCT exams by using the algorithms and databases that are currently in use on the FDA cleared CIRRUS HD-OCT version 8 (K150977) and CIRRUS Photo (K133217). The CIRRUS HD-OCT OCT-Angiography was also cleared in K150977.
The provided text describes the Retina Workplace device and its substantial equivalence to predicate devices, but it does not contain the specific details required to answer all parts of your request regarding acceptance criteria and a study proving the device meets those criteria.
The document is a 510(k) summary for a medical device cleared by the FDA, which generally focuses on demonstrating substantial equivalence to existing devices rather than presenting the full details of a clinical performance study with specific acceptance criteria, sample sizes, and expert adjudication as you've requested.
Here's what can be extracted and what is missing:
What is present/can be inferred:
- Device Performance: The document generally states that "All criteria for the verification and validation testing were met; the results demonstrate that the Retina Workplace meets all performance specifications and requirements." and "Retina Workplace v2.5 performs as well as the predicate devices." However, it does not specify what those performance specifications and requirements (acceptance criteria) were.
- Study type: "Software testing was conducted to establish the ability of the subject Retina Workplace (version 2.5 - K182318) to meet design and customer requirements. Verification and validation activities for the Retina Workplace were conducted... The system verification test report provides the test cases, expected results for each test case and the actual results obtained. Validation testing was conducted to ensure that the device meets the customer's requirements with respect to performance." This indicates that verification and validation (V&V) testing was performed, typical for software devices, rather than a prospective clinical trial. It sounds more like functional and performance testing against internal specifications.
- Human-in-the-loop/Standalone: The device is intended "to aid trained healthcare professionals," suggesting a human-in-the-loop context. No information on standalone algorithm performance is provided.
- Ground Truth: The document states "The Retina Workplace uses CIRRUS algorithms and normative databases as a quantitative tool for the comparison of macular thickness data to a database of normal subjects." This implies that existing, cleared algorithms and normative databases from the predicate devices (CIRRUS HD-OCT) are leveraged as the "ground truth" or reference for quantitative measurements.
- Training Set (Inferred): Since the device uses "CIRRUS algorithms and reference databases" that are already "currently in use on the FDA cleared CIRRUS HD-OCT version 8 (K150977) and CIRRUS Photo (K133217)", it suggests that the training of these core algorithms would have occurred as part of the predicate device development. No specific "training set" for the Retina Workplace v2.5 itself (as a new algorithm being trained) is mentioned, as its primary function is processing and displaying data using existing cleared algorithms.
What is missing from the provided text:
- A table of acceptance criteria and the reported device performance: The specific criteria (e.g., sensitivity, specificity, accuracy targets, imaging quality metrics) are not listed. Only a general statement that "all criteria... were met" is provided.
- Sample size used for the test set and the data provenance: No details on the number of cases or patients used in the verification and validation (V&V) testing, nor the origin (country, retrospective/prospective) of the data.
- Number of experts used to establish the ground truth for the test set and the qualifications of those experts: As this appears to be software/functional V&V rather than a clinical reader study, expert ground truth establishment for a test set in the way you describe is not explicitly mentioned. If the V&V largely relies on output comparison to predicate devices or established algorithms, then the "ground truth" might be the output of those validated predicate systems.
- Adjudication method: Not mentioned.
- Multi-Reader Multi-Case (MRMC) comparative effectiveness study: Not mentioned. The focus is on the device using existing, cleared algorithms, not on how human readers perform with or without its assistance.
- Standalone performance: While the device leverages algorithms, no specific standalone performance metrics (e.g., diagnostic accuracy of an automated detection) for the Retina Workplace itself are presented, implying it's an "aid" rather than a fully autonomous diagnostic tool.
- The sample size for the training set: Not applicable and not mentioned, as the device leverages existing, cleared algorithms.
- How the ground truth for the training set was established: Not applicable and not mentioned, as the device leverages existing, cleared algorithms.
Conclusion based on the provided text:
The document describes the Retina Workplace (version 2.5) as a software application that integrates and processes data using algorithms and databases already cleared and present in predicate devices (CIRRUS HD-OCT and CIRRUS Photo). The "study" proving it meets acceptance criteria appears to be a software verification and validation (V&V) process, ensuring that the new version correctly implements and displays the functionalities of the existing, cleared algorithms and processes data as intended. It does not appear to involve a new clinical performance study with human readers, novel algorithm training, or the establishment of new, independent ground truth for a diagnostic AI. The acceptance criteria were internal performance specifications for the software, which were reportedly met.
To get the detailed information you're asking for, one would need to refer to the full 510(k) submission (if publicly available beyond this summary) or documentation from the predicate devices (K150977 for CIRRUS HD-OCT version 8 and K133217 for CIRRUS Photo).
§ 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).